KR102439323B1 - Plant Condition Management System - Google Patents

Abstract

Embodiments provide a plant condition management system. The plant condition management system may include: a server; one or more devices constituting the plant; Client; and a plurality of sensors for detecting the state of the one or more devices, wherein the server includes: a processor; transceiver; and a memory, wherein the memory stores a state anomaly detection model, the transceiver receives a plurality of sensor signals corresponding to the respective sensors from the plurality of sensors during a first time interval, and the processor comprises: Preprocessing the plurality of sensor signals of the first time interval using a preprocessing model to generate first sensor data of the first time interval including an element corresponding to each of the plurality of sensor signals, the transceiver, Receives a plurality of sensor signals corresponding to the respective sensors from the plurality of sensors during a second time period, and the processor preprocesses the plurality of sensor signals of the second time period using the preprocessing model to obtain the plurality of sensor signals. generates second sensor data of the second time interval including an element corresponding to each sensor signal of Based on the second time period, the information about the status abnormality of the one or more devices may be output.

Description

Plant condition management system {SYSTEM FOR PLANT CONDITION MANAGEMENT}

Embodiments of the present invention relate to a technology for managing the state of a plant, and to a technology for managing the state of a plant based on a sensor signal of a device included in the plant.

An existing typical factory consists of a production facility, a control system, and a system leading to factory management. In the existing system, the condition of production equipment is manually inspected and managed. As the control and management of production facilities are manually performed, it is difficult to lower the defect rate below a certain level, and there is a disadvantage in productivity and cost.

Laid-Open Patent Publication No. 10-2017-0125237

Embodiments may provide a plant condition management system capable of achieving a reduction in the defect rate of products produced in a plant, improvement in productivity, cost reduction, and shortening of a manufacturing period.

The technical problems to be achieved in the embodiments are not limited to those mentioned above, and other technical problems not mentioned may be considered by those of ordinary skill in the art from various embodiments to be described below. can

A plant condition management system according to an embodiment includes a server; one or more devices constituting the plant; Client; and a plurality of sensors for detecting the state of the one or more devices, wherein the server includes: a processor; transceiver; and a memory, wherein the memory stores a state anomaly detection model, the transceiver receives a plurality of sensor signals corresponding to the respective sensors from the plurality of sensors during a first time interval, and the processor comprises: Preprocessing the plurality of sensor signals of the first time interval using a preprocessing model to generate first sensor data of the first time interval including an element corresponding to each of the plurality of sensor signals, the transceiver, Receives a plurality of sensor signals corresponding to the respective sensors from the plurality of sensors during a second time period, and the processor preprocesses the plurality of sensor signals of the second time period using the preprocessing model to obtain the plurality of sensor signals. generates second sensor data of the second time interval including an element corresponding to each sensor signal of Based on the second time period, the information about the status abnormality of the one or more devices may be output.

The memory stores a plurality of scenario corresponding operations corresponding to each of a plurality of registered state anomalies, and the processor is configured to: map the state anomaly information and the plurality of registered state anomalies, and a scenario corresponding to the mapped registered state anomaly Load a corresponding operation, control the one or more devices according to the loaded scenario corresponding operation, and the transceiver may transmit the output status abnormality and the control result to the client.

The pre-processing model includes an input layer, one or more hidden layers, and an output layer, and the pre-processing model receives a plurality of sensor signals and outputs a dimension and sensor data in a range corresponding to each dimension, and relates to the plurality of sensor signals. A plurality of training data is input to the input layer of the preprocessing model and passes through the one or more hidden layers and output layers to output an output vector, and the output vector is input to a loss function layer connected to the output layer, and the loss The function layer outputs a loss value using a loss function that compares the output vector with the correct vector for each training data, and the dimension of the pre-processing model and the range corresponding to each dimension are smaller in the loss value. learning in the direction

[Equation]

The loss function follows the above equation, where N is the number of the plurality of training data, n is a natural number identifying the training data, k is a natural number identifying the value of the nth training data, nk is the nth It may mean the k-th value of the training data, t may mean correct answer data, y may mean the output vector, and E may mean a loss value.

The processor is configured to: output a temporary vector for the second time period based on the first sensor data and the second sensor data, using the condition abnormality detection model, and A state vector may be output by comparing reference vectors included in the classification layer, and the state vector may be input to a final layer of the state anomaly detection model to output the state anomaly information.

The transceiver receives, from the client, a first feedback signal generated in a third time interval and a second feedback signal generated in a fourth time interval, and the third time interval and the fourth time interval are the first time longer than the interval and the second time interval, and the processor may update the reference vector of the abnormality detection model for the fourth time interval based on the first feedback signal and the second feedback signal.

The state anomaly detection model may include a first encoder; a first decoder; and a classification layer, wherein the first encoder comprises a plurality of cells comprising a first cell and a second cell, the first decoder comprises a plurality of cells comprising a third cell and a fourth cell, and , the processor is configured to: input the first sensor data of the first time interval to the first cell of the first encoder to output a first hidden state, and the first hidden state and the second time interval A third hidden state is obtained by inputting second sensor data into the second cell of the first encoder to output a first context vector, and inputting the first context vector and a start vector to the third cell of the first decoder output, and output a first attention distribution including an attention weight of the third hidden state for each of the first hidden state and the second hidden state of the first encoder, and the first attention distribution and the first output a first attention value based on the first hidden state and the second hidden state of the encoder, output a first temporary vector based on the first attention value and the third hidden state, and the third concealment inputting a state and the first temporary vector into the fourth cell of the first decoder to output a fourth hidden state, and the fourth for each of the first hidden state and the second hidden state of the first encoder outputting a second attention distribution including an attention weight of a hidden state, and outputting a second attention value based on the second attention distribution and the first hidden state and the second hidden state of the first encoder; A second temporary vector is output based on a second attention value and the fourth hidden state, the second temporary vector is compared with a reference vector of the state anomaly detection model, and the state vector is output, and the state vector is used as the state vector. The state anomaly information may be output by inputting it to the final layer of the state anomaly detection model.

The processor is configured to update the reference vector of the abnormal state detection model based on the first feedback signal and the second feedback signal by using a reference vector update model, wherein the reference vector update model includes: a second encoder; and a second decoder, wherein the second encoder comprises a plurality of cells comprising a fifth cell and a sixth cell, and wherein the second decoder comprises a plurality of cells comprising a seventh cell and an eighth cell. and the processor is configured to: input the first feedback signal of the third time interval to the fifth cell of the second encoder to output a fifth hidden state, the fifth hidden state and the fourth time interval The second feedback signal is input to the sixth cell of the second encoder to output a second context vector, and the second context vector and the start vector are input to the seventh cell of the second decoder to provide a seventh concealment. output a state, and output a third attention distribution including an attention weight of the seventh hidden state for each of the fifth and sixth hidden states of the second encoder, the third attention distribution and the third 2 output a third attention value based on the fifth hidden state and the sixth hidden state of the encoder, output a third temporary vector based on the third attention value and the seventh hidden state, and the seventh An eighth hidden state is output by inputting a hidden state and the third temporary vector into the eighth cell of the second decoder, and the fifth hidden state and the sixth hidden state of the second encoder are respectively output a fourth attention distribution including the attention weight of 8 hidden states, and output a fourth attention value based on the fourth attention distribution and the fifth and sixth hidden states of the second encoder; A fourth temporary vector is output based on the fourth attention value and the eighth hidden state, a loss value between the fourth temporary vector and the reference vector is output using a loss function, and a direction in which the loss value decreases to learn the reference vector.

According to the embodiments, the plant condition management system may achieve a reduction in a defective rate of a product produced in a plant, an improvement in productivity, a reduction in cost, and a reduction in the production period.

Effects obtainable from the embodiments are not limited to the effects mentioned above, and other effects not mentioned are clearly derived and understood by those of ordinary skill in the art based on the following detailed description. can be

BRIEF DESCRIPTION OF THE DRAWINGS The accompanying drawings, which are included as part of the detailed description to aid understanding of the embodiments, provide various embodiments and, together with the detailed description, explain technical features of the various embodiments.
1 is a diagram illustrating a configuration of an electronic device according to an exemplary embodiment.
2 is a diagram illustrating a configuration of a program according to an exemplary embodiment.
3 is a schematic diagram illustrating a plant condition management system according to an embodiment.
4 is a flowchart illustrating an operation of a plant condition management system according to an embodiment.
5 is a diagram illustrating a structure of a state anomaly detection model according to an exemplary embodiment.
6 is a diagram illustrating a configuration of a server included in a plant condition management system according to an exemplary embodiment.

The following embodiments combine elements and features of the embodiments in a predetermined form. Each component or feature may be considered optional unless explicitly stated otherwise. Each component or feature may be implemented in a form that is not combined with other components or features. In addition, various embodiments may be configured by combining some components and/or features. The order of operations described in various embodiments may be changed. Some features or features of one embodiment may be included in another embodiment, or may be replaced with corresponding features or features of another embodiment.

In the description of the drawings, procedures or steps that may obscure the gist of various embodiments are not described, and procedures or steps that can be understood at the level of those of ordinary skill in the art are also not described. did.

Throughout the specification, when a part is said to "comprising or including" a certain component, it does not exclude other components unless otherwise stated, meaning that other components may be further included. do. In addition, terms such as "... unit", "... group", and "module" described in the specification mean a unit that processes at least one function or operation, which is hardware or software or a combination of hardware and software. can be implemented as Also, "a or an", "one", "the" and like related terms are used herein in the context of describing various embodiments (especially in the context of the claims that follow). Unless otherwise indicated or clearly contradicted by context, it may be used in a sense including both the singular and the plural.

Hereinafter, embodiments according to various embodiments will be described in detail with reference to the accompanying drawings. DETAILED DESCRIPTION The detailed description set forth below in conjunction with the appended drawings is intended to describe exemplary embodiments of various embodiments, and is not intended to represent the only embodiments.

In addition, specific terms used in various embodiments are provided to help the understanding of various embodiments, and the use of these specific terms may be changed to other forms without departing from the technical spirit of various embodiments. .

1 is a diagram illustrating a configuration of an electronic device according to an exemplary embodiment.

1 is a block diagram of an electronic device 101 in a network environment 100, according to various embodiments. Referring to FIG. 1 , in a network environment 100 , an electronic device 101 communicates with an electronic device 102 through a first network 198 (eg, a short-range wireless communication network) or a second network 199 . It may communicate with at least one of the electronic device 104 and the server 108 through (eg, a long-distance wireless communication network). According to an embodiment, the electronic device 101 may communicate with the electronic device 104 through the server 108 . According to an embodiment, the electronic device 101 includes a processor 120 , a memory 130 , an input module 150 , a sound output module 155 , a display module 160 , an audio module 170 , and a sensor module ( 176), interface 177, connection terminal 178, haptic module 179, camera module 180, power management module 188, battery 189, communication module 190, subscriber identification module 196 , or an antenna module 197 . In some embodiments, at least one of these components (eg, the connection terminal 178 ) may be omitted or one or more other components may be added to the electronic device 101 . In some embodiments, some of these components (eg, sensor module 176 , camera module 180 , or antenna module 197 ) are integrated into one component (eg, display module 160 ). can be The electronic device 101 may also be referred to as a client, a terminal, or a peer.

The processor 120, for example, executes software (eg, a program 140) to execute at least one other component (eg, a hardware or software component) of the electronic device 101 connected to the processor 120. It can control and perform various data processing or operations. According to one embodiment, as at least part of data processing or operation, the processor 120 converts commands or data received from other components (eg, the sensor module 176 or the communication module 190 ) to the volatile memory 132 . may be stored in , process commands or data stored in the volatile memory 132 , and store the result data in the non-volatile memory 134 . According to an embodiment, the processor 120 is the main processor 121 (eg, a central processing unit or an application processor) or a secondary processor 123 (eg, a graphic processing unit, a neural network processing unit (eg, a graphic processing unit, a neural network processing unit) a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor). For example, when the electronic device 101 includes the main processor 121 and the sub-processor 123 , the sub-processor 123 uses less power than the main processor 121 or is set to be specialized for a specified function. can The auxiliary processor 123 may be implemented separately from or as a part of the main processor 121 .

The secondary processor 123 may, for example, act on behalf of the main processor 121 while the main processor 121 is in an inactive (eg, sleep) state, or when the main processor 121 is active (eg, executing an application). ), together with the main processor 121, at least one of the components of the electronic device 101 (eg, the display module 160, the sensor module 176, or the communication module 190) It is possible to control at least some of the related functions or states. According to an embodiment, the coprocessor 123 (eg, an image signal processor or a communication processor) may be implemented as part of another functionally related component (eg, the camera module 180 or the communication module 190 ). have. According to an embodiment, the auxiliary processor 123 (eg, a neural network processing device) may include a hardware structure specialized for processing an artificial intelligence model. Artificial intelligence models can be created through machine learning. Such learning may be performed, for example, in the electronic device 101 itself on which the artificial intelligence model is performed, or may be performed through a separate server (eg, the server 108). The learning algorithm may include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but in the above example not limited The artificial intelligence model may include a plurality of artificial neural network layers. Artificial neural networks include deep neural networks (DNNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), restricted boltzmann machines (RBMs), deep belief networks (DBNs), bidirectional recurrent deep neural networks (BRDNNs), It may be one of deep Q-networks or a combination of two or more of the above, but is not limited to the above example. The artificial intelligence model may include, in addition to, or alternatively, a software structure in addition to the hardware structure.

The memory 130 may store various data used by at least one component (eg, the processor 120 or the sensor module 176 ) of the electronic device 101 . The data may include, for example, input data or output data for software (eg, the program 140 ) and instructions related thereto. The memory 130 may include a volatile memory 132 or a non-volatile memory 134 .

The program 140 may be stored as software in the memory 130 , and may include, for example, an operating system 142 , middleware 144 , or an application 146 .

The input module 150 may receive a command or data to be used by a component (eg, the processor 120 ) of the electronic device 101 from the outside (eg, a user) of the electronic device 101 . The input module 150 may include, for example, a microphone, a mouse, a keyboard, a key (eg, a button), or a digital pen (eg, a stylus pen).

The sound output module 155 may output a sound signal to the outside of the electronic device 101 . The sound output module 155 may include, for example, a speaker or a receiver. The speaker can be used for general purposes such as multimedia playback or recording playback. The receiver can be used to receive incoming calls. According to one embodiment, the receiver may be implemented separately from or as part of the speaker.

The display module 160 may visually provide information to the outside (eg, a user) of the electronic device 101 . The display module 160 may include, for example, a control circuit for controlling a display, a hologram device, or a projector and a corresponding device. According to an embodiment, the display module 160 may include a touch sensor configured to sense a touch or a pressure sensor configured to measure the intensity of a force generated by the touch.

The audio module 170 may convert a sound into an electric signal or, conversely, convert an electric signal into a sound. According to an embodiment, the audio module 170 acquires a sound through the input module 150 , or an external electronic device (eg, a sound output module 155 ) connected directly or wirelessly with the electronic device 101 . The electronic device 102) (eg, a speaker or headphones) may output a sound.

The sensor module 176 detects an operating state (eg, power or temperature) of the electronic device 101 or an external environmental state (eg, a user state), and generates an electrical signal or data value corresponding to the sensed state. can do. According to an embodiment, the sensor module 176 may include, for example, a gesture sensor, a gyro sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, It may include a temperature sensor, a humidity sensor, or an illuminance sensor.

The interface 177 may support one or more specified protocols that may be used by the electronic device 101 to directly or wirelessly connect with an external electronic device (eg, the electronic device 102 ). According to an embodiment, the interface 177 may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

The connection terminal 178 may include a connector through which the electronic device 101 can be physically connected to an external electronic device (eg, the electronic device 102 ). According to an embodiment, the connection terminal 178 may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (eg, a headphone connector).

The haptic module 179 may convert an electrical signal into a mechanical stimulus (eg, vibration or movement) or an electrical stimulus that the user can perceive through tactile or kinesthetic sense. According to an embodiment, the haptic module 179 may include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

The camera module 180 may capture still images and moving images. According to an embodiment, the camera module 180 may include one or more lenses, image sensors, image signal processors, or flashes.

The power management module 188 may manage power supplied to the electronic device 101 . According to an embodiment, the power management module 188 may be implemented as, for example, at least a part of a power management integrated circuit (PMIC).

The battery 189 may supply power to at least one component of the electronic device 101 . According to one embodiment, battery 189 may include, for example, a non-rechargeable primary cell, a rechargeable secondary cell, or a fuel cell.

The communication module 190 is a direct (eg, wired) communication channel or a wireless communication channel between the electronic device 101 and an external electronic device (eg, the electronic device 102, the electronic device 104, or the server 108). It can support establishment and communication performance through the established communication channel. The communication module 190 may include one or more communication processors that operate independently of the processor 120 (eg, an application processor) and support direct (eg, wired) communication or wireless communication. According to one embodiment, the communication module 190 is a wireless communication module 192 (eg, a cellular communication module, a short-range communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module 194 (eg, : It may include a local area network (LAN) communication module, or a power line communication module). A corresponding communication module among these communication modules is a first network 198 (eg, a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network 199 (eg, legacy It may communicate with the external electronic device 104 through a cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (eg, a telecommunication network such as a LAN or a WAN). These various types of communication modules may be integrated into one component (eg, a single chip) or may be implemented as a plurality of components (eg, multiple chips) separate from each other. The wireless communication module 192 uses subscriber information (eg, International Mobile Subscriber Identifier (IMSI)) stored in the subscriber identification module 196 within a communication network such as the first network 198 or the second network 199 . The electronic device 101 may be identified or authenticated.

The wireless communication module 192 may support a 5G network after a 4G network and a next-generation communication technology, for example, a new radio access technology (NR). NR access technology includes high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and access to multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low-latency) -latency communications)). The wireless communication module 192 may support a high frequency band (eg, mmWave band) to achieve a high data rate, for example. The wireless communication module 192 uses various techniques for securing performance in a high-frequency band, for example, beamforming, massive multiple-input and multiple-output (MIMO), all-dimensional multiplexing. It may support technologies such as full dimensional MIMO (FD-MIMO), an array antenna, analog beam-forming, or a large scale antenna. The wireless communication module 192 may support various requirements defined in the electronic device 101 , an external electronic device (eg, the electronic device 104 ), or a network system (eg, the second network 199 ). According to an embodiment, the wireless communication module 192 may include a peak data rate (eg, 20 Gbps or more) for realizing eMBB, loss coverage (eg, 164 dB or less) for realizing mMTC, or U-plane latency for realizing URLLC ( Example: Downlink (DL) and uplink (UL) each 0.5 ms or less, or round trip 1 ms or less) can be supported.

The antenna module 197 may transmit or receive a signal or power to the outside (eg, an external electronic device). According to an embodiment, the antenna module 197 may include an antenna including a conductor formed on a substrate (eg, a PCB) or a radiator formed of a conductive pattern. According to an embodiment, the antenna module 197 may include a plurality of antennas (eg, an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network such as the first network 198 or the second network 199 is connected from the plurality of antennas by, for example, the communication module 190 . can be selected. A signal or power may be transmitted or received between the communication module 190 and an external electronic device through the selected at least one antenna. According to some embodiments, other components (eg, a radio frequency integrated circuit (RFIC)) other than the radiator may be additionally formed as a part of the antenna module 197 .

According to various embodiments, the antenna module 197 may form a mmWave antenna module. According to one embodiment, the mmWave antenna module comprises a printed circuit board, an RFIC disposed on or adjacent to a first side (eg, bottom side) of the printed circuit board and capable of supporting a designated high frequency band (eg, mmWave band); and a plurality of antennas (eg, an array antenna) disposed on or adjacent to a second side (eg, top or side) of the printed circuit board and capable of transmitting or receiving signals of the designated high frequency band. can do.

At least some of the components are connected to each other through a communication method between peripheral devices (eg, a bus, general purpose input and output (GPIO), serial peripheral interface (SPI), or mobile industry processor interface (MIPI)) and a signal ( e.g. commands or data) can be exchanged with each other.

According to an embodiment, the command or data may be transmitted or received between the electronic device 101 and the external electronic device 104 through the server 108 connected to the second network 199 . Each of the external electronic devices 102 or 104 may be the same as or different from the electronic device 101 . According to an embodiment, all or a part of operations executed in the electronic device 101 may be executed in one or more external electronic devices 102 , 104 , or 108 . For example, when the electronic device 101 needs to perform a function or service automatically or in response to a request from a user or other device, the electronic device 101 may perform the function or service itself instead of executing the function or service itself. Alternatively or additionally, one or more external electronic devices may be requested to perform at least a part of the function or the service. One or more external electronic devices that have received the request may execute at least a part of the requested function or service, or an additional function or service related to the request, and transmit a result of the execution to the electronic device 101 . The electronic device 101 may process the result as it is or additionally and provide it as at least a part of a response to the request. For this purpose, for example, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used. The electronic device 101 may provide an ultra-low latency service using, for example, distributed computing or mobile edge computing. In another embodiment, the external electronic device 104 may include an Internet of things (IoT) device. The server 108 may be an intelligent server using machine learning and/or neural networks. According to an embodiment, the external electronic device 104 or the server 108 may be included in the second network 199 . The electronic device 101 may be applied to an intelligent service (eg, smart home, smart city, smart car, or health care) based on 5G communication technology and IoT-related technology.

The server 108 is connected to the electronic device 101 and may provide a service to the connected electronic device 101 . In addition, the server 108 may store and manage various types of information of users who have joined as members by performing a membership registration procedure, and may provide various purchase and payment functions related to services. Also, the server 108 may share execution data of a service application executed in each of the plurality of electronic devices 101 in real time so that the service can be shared among users. The server 108 may have the same configuration as a typical web server (Web Server) or WAP server (WAP Server) in terms of hardware. However, in terms of software, it may include a program module that is implemented through any language such as C, C++, Java, Visual Basic, or Visual C and performs various functions. In addition, the server 108 is generally connected to an unspecified number of clients and/or other servers through an open computer network such as the Internet, receives a request to perform a task from a client or other server, and derives and provides the work result. It means a computer system and the computer software (server program) installed therefor. In addition, the server 108, in addition to the above-described server program, a series of application programs (Application Program) operating on the server 108 and in some cases, various databases (DB: Database, hereinafter " DB") should be understood as a broad concept including. Accordingly, the server 108 classifies, stores and manages member registration information, various information and data about the game in a DB, and this DB may be implemented inside or outside the server 108 . In addition, the server 108 uses a server program that is provided in various ways according to operating systems such as DOS, Windows, Linux, UNIX, and Macintosh in general server hardware. As a representative example, a website used in a Windows environment, Internet Information Server (IIS), and CERN, NCSA, APPACH, etc. used in a Unix environment may be used. In addition, the server 108 may cooperate with an authentication system and a payment system for user authentication of a service or a purchase payment related to a service.

The first network 198 and the second network 199 are a connection structure capable of exchanging information between respective nodes such as terminals and servers, or a network connecting the server 108 and the electronic devices 101 and 104 . (Network). The first network 198 and the second network 199 are Internet (Internet), LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), 3G , 4G, LTE, 5G, Wi-Fi, and the like. The first network 198 and the second network 199 may be the closed first network 198 and the second network 199 such as a LAN or a WAN, but preferably an open type such as the Internet. The Internet is a TCP/IP protocol and several services existing in its upper layers, namely HTTP (HyperText Transfer Protocol), Telnet, FTP (File Transfer Protocol), DNS (Domain Name System), SMTP (Simple Mail Transfer Protocol), SNMP ( Simple Network Management Protocol), NFS (Network File Service), and NIS (Network Information Service) means a worldwide open computer first network 198 and second network 199 structure.

The database may have a general data structure implemented in a storage space (hard disk or memory) of a computer system using a database management program (DBMS). The database may have a data storage form in which data can be freely searched (extracted), deleted, edited, added, and the like. Database is a relational database management system (RDBMS) such as Oracle, Infomix, Sybase, DB2, or object-oriented database management such as Gemston, Orion, O2, etc. It can be implemented for the purpose of an embodiment of the present disclosure by using a system (OODBMS) and an XML-only database (XML Native Database) such as Excelon, Tamino, and Sekaiju, and its function It may have an appropriate field or elements to achieve .

2 is a diagram illustrating a configuration of a program according to an exemplary embodiment.

2 is a block diagram 200 illustrating a program 140 in accordance with various embodiments. According to an embodiment, the program 140 executes an operating system 142 , middleware 144 , or an application 146 executable in the operating system 142 for controlling one or more resources of the electronic device 101 . may include Operating system 142 may include, for example, Android™, iOS™, Windows™, Symbian™, Tizen™, or Bada™. At least some of the programs 140 are, for example, preloaded into the electronic device 101 at the time of manufacture, or an external electronic device (eg, the electronic device 102 or 104 ), or a server (eg, the electronic device 102 or 104 ) when used by a user ( 108)), or may be updated. All or part of the program 140 may include a neural network.

The operating system 142 may control management (eg, allocation or retrieval) of one or more system resources (eg, a process, memory, or power) of the electronic device 101 . The operating system 142 may additionally or alternatively include other hardware devices of the electronic device 101 , for example, the input module 150 , the sound output module 155 , the display module 160 , and the audio module 170 . , sensor module 176 , interface 177 , haptic module 179 , camera module 180 , power management module 188 , battery 189 , communication module 190 , subscriber identification module 196 , or It may include one or more driver programs for driving the antenna module 197 .

The middleware 144 may provide various functions to the application 146 so that functions or information provided from one or more resources of the electronic device 101 may be used by the application 146 . The middleware 144 includes, for example, an application manager 201 , a window manager 203 , a multimedia manager 205 , a resource manager 207 , a power manager 209 , a database manager 211 , and a package manager 213 . ), a connectivity manager 215 , a notification manager 217 , a location manager 219 , a graphics manager 221 , a security manager 223 , a call manager 225 , or a voice recognition manager 227 . can

The application manager 201 may manage the life cycle of the application 146 , for example. The window manager 203 may manage one or more GUI resources used in the screen, for example. The multimedia manager 205, for example, identifies one or more formats required for playback of media files, and encodes or decodes a corresponding media file among the media files using a codec suitable for the selected format. can be done The resource manager 207 may manage the space of the source code of the application 146 or the memory of the memory 130 , for example. The power manager 209 may, for example, manage the capacity, temperature, or power of the battery 189 , and determine or provide related information required for the operation of the electronic device 101 by using the corresponding information. . According to an embodiment, the power manager 209 may interwork with a basic input/output system (BIOS) (not shown) of the electronic device 101 .

The database manager 211 may create, retrieve, or change a database to be used by the application 146 , for example. The package manager 213 may manage installation or update of an application distributed in the form of a package file, for example. The connectivity manager 215 may manage, for example, a wireless connection or a direct connection between the electronic device 101 and an external electronic device. The notification manager 217 may provide, for example, a function for notifying the user of the occurrence of a specified event (eg, an incoming call, a message, or an alarm). The location manager 219 may manage location information of the electronic device 101 , for example. The graphic manager 221 may manage, for example, one or more graphic effects to be provided to a user or a user interface related thereto.

Security manager 223 may provide, for example, system security or user authentication. The telephony manager 225 may manage, for example, a voice call function or a video call function provided by the electronic device 101 . The voice recognition manager 227, for example, transmits the user's voice data to the server 108, and based at least in part on the voice data, a command corresponding to a function to be performed in the electronic device 101; Alternatively, the converted text data may be received from the server 108 based at least in part on the voice data. According to an embodiment, the middleware 244 may dynamically delete some existing components or add new components. According to an embodiment, at least a portion of the middleware 144 may be included as a part of the operating system 142 or implemented as software separate from the operating system 142 .

Application 146 includes, for example, home 251 , dialer 253 , SMS/MMS 255 , instant message (IM) 257 , browser 259 , camera 261 , alarm 263 . , contacts 265, voice recognition 267, email 269, calendar 271, media player 273, album 275, watch 277, health 279 (such as exercise or blood sugar) measuring biometric information), or environmental information 281 (eg, measuring atmospheric pressure, humidity, or temperature information). According to an embodiment, the application 146 may further include an information exchange application (not shown) capable of supporting information exchange between the electronic device 101 and an external electronic device. The information exchange application may include, for example, a notification relay application configured to transmit specified information (eg, call, message, or alarm) to an external electronic device, or a device management application configured to manage the external electronic device. have. The notification relay application, for example, transmits notification information corresponding to a specified event (eg, mail reception) generated in another application (eg, the email application 269 ) of the electronic device 101 to the external electronic device. can Additionally or alternatively, the notification relay application may receive notification information from the external electronic device and provide it to the user of the electronic device 101 .

The device management application is, for example, a power source (eg, turn-on or turn-off) of an external electronic device that communicates with the electronic device 101 or some components thereof (eg, a display module or a camera module of the external electronic device). ) or a function (eg brightness, resolution, or focus). The device management application may additionally or alternatively support installation, deletion, or update of an application operating in an external electronic device.

Throughout this specification, a neural network, a neural network network, and a network function may be used interchangeably. A neural network may be composed of a set of interconnected computational units, which may generally be referred to as “nodes”. These “nodes” may also be referred to as “neurons”. A neural network is configured to include at least two or more nodes. Nodes (or neurons) constituting neural networks may be interconnected by one or more “links”.

In a neural network, two or more nodes connected through a link may relatively form a relationship between an input node and an output node. The concepts of an input node and an output node are relative, and any node in an output node relationship with respect to one node may be in an input node relationship in a relationship with another node, and vice versa. As described above, an input node to output node relationship may be created around a link. One or more output nodes may be connected to one input node through a link, and vice versa.

In the relationship between the input node and the output node connected through one link, the value of the output node may be determined based on data input to the input node. Here, a node interconnecting the input node and the output node may have a weight. The weight may be variable, and may be changed by a user or an algorithm in order for the neural network to perform a desired function. For example, when one or more input nodes are interconnected to one output node by respective links, the output node sets values input to input nodes connected to the output node and links corresponding to the respective input nodes. An output node value may be determined based on the weight.

As described above, in a neural network, two or more nodes are interconnected through one or more links to form an input node and an output node relationship within the neural network. The characteristics of the neural network may be determined according to the number of nodes and links in the neural network, the correlation between the nodes and the links, and the value of a weight assigned to each of the links. For example, when the same number of nodes and links exist and there are two neural network networks having different weight values between the links, the two neural network networks may be recognized as different from each other.

3 is a schematic diagram illustrating a plant condition management system according to an embodiment.

According to an embodiment, the plant condition management system includes a server 310 (eg, the electronic device 101 of FIG. 1 ), a client 320 (eg, the electronic device 104 of FIG. 1 ), a network 340 ( For example, the second network 199 of FIG. 1 ) may include physical resources 331 and 332 . The physical resources 331 and 332 may be examples of one or more devices constituting a plant. The server 310 includes a processor (eg, the processor 120 of FIG. 1 ), a transceiver (eg, the communication module 190 of FIG. 1 ) and a memory (eg, the memory 130 of FIG. 1 ). may include The memory may store a state anomaly detection model. The memory may store a server program (eg, the program 140 of FIG. 1 and the program 140 of FIG. 2 ) for the operation of the plant condition management system. The memory may store a preprocessing model and a state anomaly detection model to be described below.

The plant condition management system can automatically collect the status of production equipment through sensors. The plant condition management system transmits the collected information to the server, and the server can analyze the collected data through artificial intelligence. The server can manage the physical resources of the factory based on the analysis result. Through this, the plant condition management system can achieve a reduction in the defect rate of the produced product, an improvement in productivity, a reduction in cost, and a shortening of the production period.

The plant condition management system can be composed of four hierarchical structures. The plant condition management system may be composed of a physical resource layer, a network layer, a cloud application layer, and a terminal layer. Referring to FIG. 1 , physical resources 331 and 332 may be included in a physical resource layer. The network 340 may be included in the network layer. The server 310 may be included in the cloud application layer. The client 320 may be included in the terminal layer.

The physical resource layer is a layer including all physical resources, and the physical resource includes all manufacturing resources and may include physical devices such as mechanical equipment such as equipment robots used in a manufacturing process. The state of these physical resources may be measured through various sensors. Here, the sensor is for measuring the quality, performance or failure of equipment or devices in order to perform factory automation, etc., RFID, PLC, Smart Meter, proximity sensor, capacitive sensor, inclination angle sensor, acceleration sensor, ultrasonic sensor, It may include any sensor, such as a photo sensor, a vision sensor, or a stability sensor. As an example, the sensor data may include data or values obtained from the above-described sensors, and may include sensor data including various types of variables according to the type of sensor or the type of equipment or equipment measured by the sensor. have. The foregoing is merely an example, and the present disclosure is not limited thereto.

The network layer can deliver a large amount of sensor signals that measure the state of physical resources to the cloud application layer. The network layer can perform reliable and high-speed data transmission while satisfying QoS (Quality of Service) required for plant condition management. The network layer may use, for example, Real-time Ethernet (RTE), wireless AP, industrial switching, access network, and the like. However, these are merely examples and are not limited thereto.

The cloud application layer can perform the functions of storing, processing, analyzing, and judging data transmitted over a trusted network. Since the amount of data measured in physical resources is generally large and collected continuously, efficient methods such as data processing, data search, and data analysis according to the amount of collected data are required. The cloud application layer can perform operation status and fault diagnosis based on real-time sensor signals of facilities and devices.

The terminal layer may perform a function of providing the user with the results analyzed in the cloud application layer. In the terminal layer, items for real-time/non-real-time data can be provided separately. Here, the real-time data may include data on an operation form of an automated facility/robot, and the non-real-time data may include data provided based on accumulated data such as fault diagnosis.

According to an embodiment, a plurality of sensors for sensing the state of one or more devices may correspond to each of the physical resources 331 and 332 . The sensor may generate a sensor signal by measuring the state of the physical resources 331 and 332 .

The transceiver of the server 310 may receive a plurality of sensor signals corresponding to each sensor from a plurality of sensors during the first time period. Here, the first time period may mean a time-series analysis unit for processing a plurality of sensor signals. For example, the sensor signal may be accumulated in units of one second and analyzed by the server 310 in units of one second.

The processor of the server 310 may preprocess a plurality of sensor signals of a predetermined time interval using the preprocessing model to generate sensor data including elements corresponding to each of the plurality of sensor signals. One sensor data may include an element corresponding to each of a plurality of sensors sensing one device as a component of a vector. The preprocessing model may include an input layer, one or more hidden layers, and an output layer, and the preprocessing model may receive a plurality of sensor signals and output a dimension and sensor data in a range corresponding to each dimension.

The preprocessing model may be pre-trained in a supervised learning method through training data representing a plurality of sensor signals. For example, a plurality of learning data and correct answer data corresponding to each of the learning data may be obtained from data accumulated through log recording. For example, a plurality of sensor signals collected at 01:00 AM - 01:01 AM on January 25, 2021 and the type of failure occurring at this time may be normalized to one training data pair.

The learning apparatus may input a plurality of learning data related to a plurality of sensor signals to an input layer of the preprocessing model. The output of the input layer may output an output vector by passing through one or more hidden layers and output layers constituting the preprocessing model. The output vector may be input to a loss function layer connected to the output layer. The loss function layer may output a loss value using a loss function that compares the output vector with the correct vector for each training data. The dimension of the preprocessing model and the range corresponding to each dimension may be learned in a direction in which the loss value becomes smaller.

[Equation]

For example, the loss function may be calculated according to the following equation. Here, N is the number of a plurality of training data, n is a natural number identifying the training data, k is a natural number identifying the value of the n-th training data, nk is the k-th value of the n-th training data, and t is the correct answer may mean data, y may mean an output vector, and E may mean a loss value.

For example, the processor of the server 310 pre-processes the plurality of sensor signals of the first time section using the pre-processing model, and the first sensor data of the first time section including an element corresponding to each of the plurality of sensor signals can create Here, the first sensor data may be in a vector format, and an element may mean each element of the first sensor data. Each sensor signal collected during the first time period may be expressed in a vector format having a unique number of dimensions through statistical processing. An element may correspond to each vector derived in this way. For example, first sensor data corresponding to the first sensor may be expressed as a vector x1, and x1 may have an element of L1 as an L1 dimension. Similarly, n-th sensor data corresponding to the n-th sensor may be expressed as a vector xn, where xn may have elements of Ln as an Ln dimension.

The transceiver of the server 310 may receive a plurality of sensor signals corresponding to each sensor from a plurality of sensors during the second time period. The processor of the server 310 pre-processes the plurality of sensor signals of the second time section using the pre-processing model to generate second sensor data of the second time section including an element corresponding to each of the plurality of sensor signals. have. Here, the second time section may mean a time section that does not overlap the first time section. The second time period may be after the first market period.

The server 310 may determine the abnormality of the current state of the physical resources 331 and 332 in consideration of the sensor data of the previous time section as well as the sensor data of the current time section. The processor of the server 310 may output status abnormality information of one or more devices for the second time period based on the first sensor data and the second sensor data using the abnormal state detection model. Here, the state anomaly information is information about the state of the physical resource, and may include, for example, various information such as a degree of performance deterioration, a failure state, and whether replacement is necessary. However, these are only examples, and various types of data about the device may be included in the status abnormality information.

As such, the plant condition management system can grasp the condition of the plant with higher accuracy than when simply analyzing the condition abnormality using the current sensor data.

The processor of the server 310 may output a temporary vector for the second time period based on the first sensor data and the second sensor data using the abnormal state detection model. Here, the temporary vector may refer to input data in a vector format that is input to the classification layer of the state anomaly detection model. A detailed process for deriving the temporary vector will be described in more detail with reference to FIG. 4 below.

The processor may output the state vector by comparing the temporary vector with the reference vector included in the classification layer of the state anomaly detection model. A classification layer may include one or more reference vectors. Here, the reference vector may be data in a vector format corresponding to an abnormal state of each device. For example, a reference vector indicating that the state of the first configuration of the physical resource 331 is inoperable may be expressed as (0.1, 0, 0.5, 0.2, 0.3, 0, 0). Similarly, a reference vector indicating an abnormal state of each configuration constituting each of the plurality of physical resources may be predefined or learned.

The state vector may mean a vector indicating a result of comparison with each reference vector. Temporary vectors may be compared with respect to each reference vector indicating an abnormal state defined in one device. For example, the processor may derive a scalar value by performing a dot product on the temporary vector and the reference vector. A scalar value for each reference vector may be defined as an element constituting a state vector, respectively. Here, the number of dimensions of the state vector may be the number of types of states of a particular device.

The processor may output the state anomaly information by inputting the state vector into the final layer of the state anomaly detection model. The final layer may examine each element of the state vector and output the state having the highest probability as state abnormality information of the corresponding device. The status abnormality information may be expressed in various formats. For example, the status abnormality information may be expressed as text or a predefined code or number.

According to an embodiment, the server 310 may update the reference vector set for each device constituting the plant based on the feedback signal generated in response to a series of events closest to the current time. Through this, the plant condition management system can manage the plant more precisely by time-series update of a reference vector that is a reference indicating an abnormal condition.

The transceiver of the server 310 may receive a plurality of feedback signals from the client 320 . For example, the server 310 may receive a first feedback signal generated in the third time interval and a second feedback signal generated in the fourth time interval from the client 320 . Here, the time interval reflected in the reference vector may be longer than the time interval for indicating the current state of the device. For example, the third time interval and the fourth time interval may be longer than the first time interval and the second time interval. In this way, the reference vector can more precisely define the state anomalies of the device over a longer period of time, and the sensor data can more accurately capture the instantaneous state of the device.

The processor may update the reference vector of the abnormal state detection model for the fourth time interval based on the first feedback signal and the second feedback signal. The process of updating the reference vector of the state anomaly detection model will be described in more detail below with reference to FIG. 4 .

The memory of the server 310 may store a plurality of scenario corresponding operations corresponding to each of a plurality of registered state abnormalities. Here, the registered state anomaly is information in which the type of the state anomaly is defined and registered in advance. The scenario response operation refers to a series of operations established in advance as a method for solving a state abnormality in response to a specific state abnormality.

According to an embodiment, the processor of the server 310 may map status abnormality information and a plurality of registered state abnormalities. The processor may load a scenario response action corresponding to the mapped registration state abnormality. The processor may control one or more devices according to the loaded scenario corresponding operation. The processor may perform a series of pre-established operations as a method for resolving a state abnormality. The processor may collect a result of the performed operation to generate a control result. Through this, the plant condition management system can monitor and immediately respond to predefined condition abnormalities in real time.

The transceiver of the server 310 may transmit the output status abnormality and control result to the client 320 . The client 320 may display a status abnormality and a control result to the user. In this way, the plant condition management system can provide a service that allows the administrator to remotely check the status abnormality and control result easily.

4 is a flowchart illustrating an operation of a plant condition management system according to an embodiment.

According to an embodiment, in operation S401 , the transceiver of the server 310 may receive a plurality of sensor signals corresponding to each sensor from a plurality of sensors during the first time period.

According to an embodiment, in operation S402, the processor of the server 310 pre-processes the plurality of sensor signals of the first time interval using the pre-processing model to include an element corresponding to each of the plurality of sensor signals. First sensor data of one time period may be generated.

According to an embodiment, in operation S403 , the transceiver of the server 310 may receive a plurality of sensor signals corresponding to each sensor from a plurality of sensors during the second time period.

According to an embodiment, in operation S404, a plurality of sensor signals of the second time section are pre-processed using the pre-processing model of the server 310 to include an element corresponding to each of the plurality of sensor signals for a second time period. Second sensor data of the section may be generated.

According to an embodiment, in operation S405 , the processor of the server 310 uses the state anomaly detection model to determine the state anomaly of one or more devices for a second time interval based on the first sensor data and the second sensor data. information can be printed.

5 is a diagram illustrating a structure of a state anomaly detection model according to an exemplary embodiment.

According to an embodiment, the server 310 may analyze time-series information of a sensor signal using the abnormal state detection model. The state anomaly detection model may include a first encoder, a second encoder, and a classification layer 550 . The first encoder may include a plurality of cells including a first cell and a second cell. The first decoder may include a plurality of cells including a third cell and a fourth cell. Referring to FIG. 5 , an RNN cell 521 , an RNN cell 522 , and an RNN cell 523 may be sequentially connected in an encoder. In the decoder, the RNN cell 541 , the RNN cell 542 , and the RNN cell 543 may be sequentially connected.

The processor of the server 310 may output the first hidden state by inputting the first sensor data of the first time period to the first cell of the first encoder. The processor may output the first context vector by inputting the second sensor data of the first hidden state and the second time period to the second cell of the first encoder.

Referring to FIG. 5 , each of the RNN cells 521 , 522 , and 523 may receive continuous sensor data, respectively. The RNN cell 521, the RNN cell 522, and the RNN cell 523 have sensor data 511 at time tn-2, sensor data 512 at time tn-1, and sensor data 513 at time tn, respectively. can be entered. Each of the RNN cells 521 , 522 , and 523 may output a hidden state 514 , a hidden state 515 , and a context vector 516 from sensor data at each time point.

The processor may output the third hidden state by inputting the first context vector and the start vector to the third cell of the first decoder. The processor may output a first attention distribution including an attention weight of the third hidden state for each of the first hidden state and the second hidden state of the first encoder. The processor may output the first attention value based on the first attention distribution and the first and second hidden states of the first encoder. The processor may output the first temporary vector based on the first attention value and the third hidden state.

The processor may output the fourth hidden state by inputting the third hidden state and the first temporary vector to the fourth cell of the first decoder. The processor may output a second attention distribution including an attention weight of the fourth hidden state for each of the first hidden state and the second hidden state of the first encoder. The processor may output the second attention value based on the second attention distribution and the first hidden state and the second hidden state of the first encoder. The processor may output a second temporary vector based on the second attention value and the fourth hidden state.

For example, referring to FIG. 5 , the RNN cell 541 of the first decoder may output a hidden state 534 based on the context vector 516 and the start vector 531 . An attention distribution including an attention weight may be calculated through the loss function 524 according to the relationship between the hidden state 534 and each hidden state of the first encoder. A temporary vector 532 may be output based on the attention distribution and the hidden state 534 .

The RNN cell 542 of the first decoder may output the hidden state 535 based on the hidden state 534 and the temporary vector 532 . An attention distribution including an attention weight may be calculated through the loss function 524 according to the relationship between the hidden state 535 and each hidden state of the first encoder. A temporary vector 533 may be output based on the attention distribution and the hidden state 535 .

The RNN cell 543 of the first decoder may output the hidden state 536 based on the hidden state 535 and the temporary vector 533 . An attention distribution including an attention weight may be calculated through the loss function 524 according to the relationship between the hidden state 535 and each hidden state of the first encoder. A temporary vector 534 may be output based on the attention distribution and the hidden state 535 .

The processor may output a state vector by comparing the second temporary vector with a reference vector of the state anomaly detection model. For example, referring to FIG. 5 , the final temporary vector 534 may be input to the classification layer 550 . Here, the reference vector is a vector included in the classification layer 550 , and referring to FIG. 5 , Z1, Z2, ?? , can be expressed as Zn.

The processor may output the state anomaly information by inputting the state vector into a final layer (not shown) of the state anomaly detection model. The final layer may perform a function of matching the state anomaly information based on the elements of the state vector.

According to an embodiment, the server 310 may update the reference vector set for each device constituting the plant based on the feedback signal generated in response to a series of events closest to the current time. Through this, the plant condition management system can manage the plant more precisely by time-series update of a reference vector that is a reference indicating an abnormal condition.

The transceiver of the server 310 may receive a plurality of feedback signals from the client 320 . For example, the server 310 may receive a first feedback signal generated in the third time interval and a second feedback signal generated in the fourth time interval from the client 320 . The processor may update the reference vector of the abnormal state detection model based on the first feedback signal and the second feedback signal by using the reference vector update model.

The reference vector update model may include a second encoder and a second decoder. The second encoder may include a plurality of cells including a fifth cell and a sixth cell, and the second decoder may include a plurality of cells including a seventh cell and an eighth cell. Referring to FIG. 5 , the second encoder may include an RNN cell 571 and an RNN cell 572 . The second decoder may include an RNN cell 591 and an RNN cell 592 .

The processor may output the fifth hidden state by inputting the first feedback signal of the third time interval to the fifth cell of the second encoder. The processor may output the second context vector by inputting the second feedback signal of the fifth hidden state and the fourth time interval to the sixth cell of the second encoder.

Referring to FIG. 5 , each of the RNN cells 571 and 572 may receive continuous sensor data, respectively. A feedback signal 561 at a time Tn-1 and a feedback signal 512 at a time Tn may be input to the RNN cell 571 and the RNN cell 572 , respectively. Each of the RNN cells 571 and 572 may output a hidden state 563 and a hidden state 564 from the feedback signal at each time point.

The processor may output the seventh hidden state by inputting the second context vector and the start vector to the seventh cell of the second decoder. The processor may output a third attention distribution including an attention weight of the seventh hidden state for each of the fifth and sixth hidden states of the second encoder. The processor may output the third attention value based on the third attention distribution and the fifth and sixth hidden states of the second encoder. The processor may output a third temporary vector based on the third attention value and the seventh hidden state.

The processor may output the eighth hidden state by inputting the seventh hidden state and the third temporary vector to the eighth cell of the second decoder. The processor may output a fourth attention distribution including an attention weight of the eighth hidden state for each of the fifth and sixth hidden states of the second encoder. The processor may output the fourth attention value based on the fourth attention distribution and the fifth and sixth hidden states of the second encoder. The processor may output a fourth temporary vector based on the fourth attention value and the eighth hidden state.

For example, the processor may output the hidden state 583 of the RNN cell 591 of the second decoder based on the context vector 564 and the start vector 581 . An attention distribution including an attention weight may be calculated according to the relationship between the hidden state 583 and each hidden state of the first encoder through the loss function 574 . A temporary vector 582 may be output based on the attention distribution and the hidden state 583 .

The processor may output the hidden state 584 of the RNN cell 592 of the second decoder based on the hidden state 583 and the temporary vector 582 . An attention distribution including an attention weight may be calculated according to the relationship between the hidden state 584 and each hidden state of the first encoder through the loss function 574 . A temporary vector 585 may be output based on the attention distribution and the hidden state 584 .

The processor may output a loss value between the fourth temporary vector and the reference vector using the loss function. For example, the processor may use the loss function 593 to generate a temporary vector 585 and a reference vector Z1 ?? A loss value can be output by comparing one of Zn. The processor may learn the corresponding reference vector in a direction in which the loss value becomes smaller.

6 is a diagram illustrating a configuration of a server included in a plant condition management system according to an exemplary embodiment.

According to an embodiment, the server 600 (eg, the server 310 of FIG. 3 ) may include a memory 610 , a processor 620 , and a transceiver 630 . The memory 610 may store a preprocessing model and a state abnormality detection model.

The transceiver 630 may receive a plurality of sensor signals corresponding to each sensor from a plurality of sensors during the first time period. The processor 620 may preprocess the plurality of sensor signals of the first time interval using the preprocessing model to generate first sensor data of the first time interval including elements corresponding to each of the plurality of sensor signals.

The transceiver 630 may receive a plurality of sensor signals corresponding to each sensor from a plurality of sensors during the second time period. The processor 620 may preprocess the plurality of sensor signals of the second time period using the preprocessing model to generate second sensor data of the second time period including elements corresponding to each of the plurality of sensor signals.

The processor 620 may output status abnormality information of one or more devices for a second time period based on the first sensor data and the second sensor data using the abnormal state detection model.

The embodiments described above may be implemented by a hardware component, a software component, and/or a combination of a hardware component and a software component. For example, the apparatus, methods and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate (FPGA). array), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions, may be implemented using one or more general purpose or special purpose computers. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, although one processing device is sometimes described as being used, one of ordinary skill in the art will recognize that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that may include For example, the processing device may include a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as parallel processors.

The software may comprise a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device. The software and/or data may be any kind of machine, component, physical device, virtual equipment, computer storage medium or device, to be interpreted by or to provide instructions or data to the processing device. , or may be permanently or temporarily embody in a transmitted signal wave. The software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic such as floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

As described above, although the embodiments have been described with reference to the limited drawings, those skilled in the art may apply various technical modifications and variations based on the above. For example, the described techniques are performed in a different order than the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (5)

A plant condition management system comprising:
The plant condition management system includes: a server; one or more devices constituting the plant; Client; and a plurality of sensors for sensing the state of the one or more devices,
The server includes a processor; transceiver; and a memory, wherein the memory stores a state anomaly detection model,
The transceiver receives a plurality of sensor signals corresponding to each sensor from the plurality of sensors during a first time period, and the processor pre-processes the plurality of sensor signals of the first time period using a pre-processing model. generating first sensor data of the first time interval including an element corresponding to each of the plurality of sensor signals;
The transceiver receives a plurality of sensor signals corresponding to the respective sensors from the plurality of sensors during a second time interval, and the processor receives the plurality of sensor signals of the second time interval using the pre-processing model. Pre-processing to generate second sensor data of the second time interval including an element corresponding to each of the plurality of sensor signals,
The processor outputs, based on the first sensor data and the second sensor data, the abnormal state information of the one or more devices for the second time period using the abnormal state detection model,
The processor is:
Using the condition abnormality detection model,
outputting a temporary vector for the second time interval based on the first sensor data and the second sensor data,
output a state vector by comparing the temporary vector with a reference vector included in the classification layer of the state anomaly detection model;
outputting the state anomaly information by inputting the state vector to the final layer of the state anomaly detection model;
The transceiver receives, from the client, a first feedback signal generated in a third time interval and a second feedback signal generated in a fourth time interval, and the third time interval and the fourth time interval are the first time longer than the interval and the second time interval,
The processor updates the reference vector of the abnormal state detection model for the fourth time interval based on the first feedback signal and the second feedback signal,
The state anomaly detection model may include a first encoder; a first decoder; and a classification layer, wherein the first encoder comprises a plurality of cells comprising a first cell and a second cell, the first decoder comprises a plurality of cells comprising a third cell and a fourth cell, and ,
The processor is:
outputting a first hidden state by inputting the first sensor data of the first time interval into the first cell of the first encoder;
outputting a first context vector by inputting the second sensor data of the first hidden state and the second time interval to the second cell of the first encoder;
outputting a third hidden state by inputting the first context vector and the start vector to the third cell of the first decoder;
output a first attention distribution including an attention weight of the third hidden state for each of the first hidden state and the second hidden state of the first encoder;
outputting a first attention value based on the first attention distribution and the first hidden state and the second hidden state of the first encoder;
outputting a first temporary vector based on the first attention value and the third hidden state;
outputting a fourth hidden state by inputting the third hidden state and the first temporary vector to the fourth cell of the first decoder;
outputting a second attention distribution including an attention weight of the fourth hidden state for each of the first hidden state and the second hidden state of the first encoder;
outputting a second attention value based on the second attention distribution and the first hidden state and the second hidden state of the first encoder;
outputting a second temporary vector based on the second attention value and the fourth hidden state;
outputting the state vector by comparing the second temporary vector with a reference vector of the state anomaly detection model;
outputting the state anomaly information by inputting the state vector to the final layer of the state anomaly detection model,
Plant condition management system. According to claim 1,
The memory stores a plurality of scenario corresponding operations corresponding to each of a plurality of registered state abnormalities,
The processor is:
mapping the state anomaly information and the plurality of registered state anomalies;
loading a scenario response action corresponding to the mapped registration state abnormal,
Control the one or more devices according to the loaded scenario corresponding operation,
The transceiver transmits the output state abnormality and the control result to the client,
Plant condition management system. delete delete delete

Images