CN117675821A - Intelligent mining working face distributed edge data real-time processing system - Google Patents
Intelligent mining working face distributed edge data real-time processing system Download PDFInfo
- Publication number
- CN117675821A CN117675821A CN202311715562.XA CN202311715562A CN117675821A CN 117675821 A CN117675821 A CN 117675821A CN 202311715562 A CN202311715562 A CN 202311715562A CN 117675821 A CN117675821 A CN 117675821A
- Authority
- CN
- China
- Prior art keywords
- real
- working condition
- condition data
- data
- time working
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005065 mining Methods 0.000 title claims abstract description 43
- 238000012545 processing Methods 0.000 title claims abstract description 23
- 238000003745 diagnosis Methods 0.000 claims abstract description 61
- 239000003245 coal Substances 0.000 claims abstract description 31
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- 238000000034 method Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 9
- 239000000839 emulsion Substances 0.000 claims description 6
- 238000005520 cutting process Methods 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 2
- 230000005540 biological transmission Effects 0.000 abstract description 4
- 238000003860 storage Methods 0.000 abstract description 4
- 206010063385 Intellectualisation Diseases 0.000 abstract description 3
- 238000004364 calculation method Methods 0.000 description 7
- 238000010276 construction Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 238000013500 data storage Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013144 data compression Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
- G06F9/505—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the load
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a distributed edge data real-time processing system of an intelligent mining working face, and belongs to the technical field of coal mine intellectualization. The system comprises a coal mining equipment group, a sensor group, an edge distributed group and a cloud server; the sensor cluster is used for collecting real-time working condition data of each fully mechanized coal mining equipment and sending the real-time working condition data to the edge distributed cluster; the edge distributed cluster is used for preprocessing real-time working condition data and storing the real-time working condition data, managing nodes of the master node and the plurality of slave nodes, and performing intelligent diagnosis based on the preprocessed real-time working condition data and an intelligent diagnosis model issued by the cloud server; the cloud server is used for storing the preprocessed real-time working condition data and constructing an intelligent diagnosis model. By arranging the edge distributed clusters on the working face, partial tasks of the cloud server are issued from the cloud server, the storage pressure of the server is reduced, and meanwhile, the network delay of data remote transmission is effectively reduced.
Description
Technical Field
The invention relates to the technical field of coal mine intellectualization, in particular to a distributed edge data real-time processing system of an intelligent mining working face.
Background
The intelligent technology is a core technology for high-efficiency production of a coal mining working face, along with deep application of various intelligent sensors on the working face, the data volume of the intelligent sensors is explosively increased at billions of speeds every day, and the potential value of the data can be mined by utilizing the big data and artificial intelligent technology, so that a real-time early warning and auxiliary decision-making model is constructed, and the high-efficiency mining of the coal mining process is guided.
The traditional coal mine working face data processing system only transmits all data to an uphole cloud server through a ring network, the data are stored in a historical database after being uniformly screened and processed through the cloud server, and meanwhile the cloud server also needs to bear various calculation tasks such as construction of an excavation model and equipment fault early warning, so that the calculation resources cannot be reasonably distributed and a network link is too congested. The large amount of data transmission and calculation tasks restrict the further development of the current working face intellectualization.
Disclosure of Invention
In order to solve the technical problems, the invention provides a distributed edge data real-time processing system for an intelligent mining working face. The technical scheme of the invention is as follows:
a distributed edge data real-time processing system of an intelligent mining working face comprises a coal mining equipment group, a sensor group, an edge distributed group and a cloud server;
the coal mining equipment group comprises a plurality of fully-mechanized coal mining equipment of a working face; the sensor cluster comprises a plurality of sensors of various types installed on fully-mechanized equipment; the edge distributed cluster comprises a master node and a plurality of slave nodes, the master node and the plurality of slave nodes are connected into the underground looped network to form a network path, and each sensor in the sensor cluster is connected with the master node and/or the plurality of slave nodes; the cloud server is connected with the master node and/or a plurality of slave nodes;
the sensor clusters are used for collecting real-time working condition data of each fully mechanized coal mining equipment and sending the real-time working condition data to the edge distributed clusters; the edge distributed cluster is used for preprocessing the real-time working condition data, storing the real-time working condition data, managing the nodes of the master node and the plurality of slave nodes, and performing intelligent diagnosis based on the preprocessed real-time working condition data and an intelligent diagnosis model issued by the cloud server; the cloud server is used for storing the preprocessed real-time working condition data, constructing an intelligent diagnosis model based on the preprocessed real-time working condition data and managing the edge distributed cluster.
Optionally, the coal mining equipment group comprises a coal mining machine, a hydraulic support, a reversed loader, an emulsion pump and a belt conveyor;
the sensor cluster includes: a speed sensor, a current sensor and a temperature sensor are arranged on a traction motor and a cutting motor of the coal mining machine; the angle sensor, the pressure sensor and the elevation sensor are arranged on the top beam and the upright post of the hydraulic support; a temperature sensor, a current sensor and a voltage sensor are arranged on a motor of the reversed loader; a pump station of the emulsion pump, a temperature sensor and a pressure sensor are arranged on the oil tank; a speed sensor and a current sensor which are arranged on a tail roller motor of the belt conveyor.
Optionally, when the edge distributed cluster performs preprocessing and real-time data storage on the real-time working condition data, when new real-time working condition data is monitored, the master node divides the data preprocessing operation into different tasks according to the data volume of the new real-time working condition data, queries computing resources to each slave node, feeds back the computing resources to the master node by each slave node, and creates a data stream after determining the current idle slave node according to the feedback result; the current idle slave node receives new real-time working condition data, judges whether the new real-time working condition data has missing values and noise data, processes the missing values and the noise data to obtain preliminarily processed real-time working condition data, and extracts effective characteristics in the preliminarily processed real-time working condition data as the preprocessed real-time working condition data and stores the preprocessed real-time working condition data; the main node records the subject and the address of the second real-time working condition data obtained by each slave node, compresses the preprocessed real-time working condition data obtained by each slave node according to the time granularity, obtains the average value of all preprocessed real-time working condition data of a time period by using a sliding window, and sends the average value to the cloud server.
Optionally, when the current idle slave node judges whether the new real-time working condition data has the missing value and the noise data, the current idle slave node judges whether the new real-time working condition data has the missing value through logical non-operation, and judges whether the new real-time working condition data is the noise data according to a preset threshold range.
Optionally, when the current idle slave node processes the missing value and the noise data, the data of the location of the missing value and the noise data is reset after linear interpolation is performed according to the effective working condition data before and after the missing value and the noise data.
Optionally, when the edge distributed cluster performs node management on the master node and the plurality of slave nodes, the edge distributed cluster includes the following contents:
1. after the master node receives the task sent by the cloud server, dividing a plurality of jobs according to the size of task data volume, distributing idle slave nodes of computing resources according to the job volume to perform the jobs, and logging off the master node to release the occupied computing resources after all the jobs are operated;
2. each slave node periodically reports the heartbeat signal and available computing resources to the master node, and the master node periodically updates the state information of each slave node; and the master node judges whether any slave node fails according to a pre-configured heartbeat timeout threshold, and when any slave node fails, the master node locally clears the data of the failed slave node and sends the failure information to the cloud server for display through the ring network.
Optionally, when the edge distributed cluster performs intelligent diagnosis based on the preprocessed real-time working condition data and the intelligent diagnosis model issued by the cloud server, inputting the preprocessed real-time working condition data into the intelligent diagnosis model issued by the cloud server, obtaining an intelligent diagnosis result according to an output result of the intelligent diagnosis model issued by the cloud server, and sending the intelligent diagnosis result to the cloud server for display.
Optionally, when the cloud server builds the intelligent diagnosis model based on the preprocessed real-time working condition data, the intelligent diagnosis model is trained through the preprocessed real-time working condition data received by the history stored in the history database of the cloud server, a trained intelligent diagnosis model is obtained, the trained intelligent diagnosis model is updated through the preprocessed real-time working condition data sent by the edge distributed cluster in real time, and the updated intelligent diagnosis model is issued to the master node and the slave node in the edge distributed cluster.
Optionally, when the cloud server manages the edge distributed cluster, the cloud server queries the state information of the master node and each slave node from the master node in real time, and displays the state information of the master node and each slave node.
All the above optional technical solutions can be arbitrarily combined, and the detailed description of the structures after one-to-one combination is omitted.
By means of the scheme, the beneficial effects of the invention are as follows:
according to the invention, the edge distributed cluster is deployed on the working face, so that part of processing tasks (preprocessing of real-time working condition data and application of an intelligent diagnosis model) of the cloud server are issued from the cloud server, the storage pressure of the server is reduced, and meanwhile, the network delay of data remote transmission is effectively reduced. The node management of the master node and the plurality of slave nodes is realized through the interaction of the cloud server and the edge distributed cluster, and the reasonable allocation of hardware resources is realized.
The foregoing description is only an overview of the present invention, and is intended to provide a better understanding of the present invention, as it is embodied in the following description, with reference to the preferred embodiments of the present invention and the accompanying drawings.
Drawings
Fig. 1 is a schematic diagram of the system constitution of the present invention.
Fig. 2 is a schematic diagram of an interaction process between an edge distributed cluster and a cloud server in a system according to an embodiment of the present invention.
Detailed Description
The following describes in further detail the embodiments of the present invention with reference to the drawings and examples. The following examples are illustrative of the invention and are not intended to limit the scope of the invention.
As shown in fig. 1, the distributed edge data real-time processing system for the intelligent mining working face provided by the embodiment of the invention comprises a coal mining equipment group, a sensor group, an edge distributed group and a cloud server;
the coal mining equipment group comprises a plurality of fully-mechanized coal mining equipment of a working face; the sensor cluster comprises a plurality of sensors of various types installed on fully-mechanized equipment; the edge distributed cluster comprises a master node and a plurality of slave nodes, the master node and the plurality of slave nodes are connected into the underground looped network to form a network path, and each sensor in the sensor cluster is connected with the master node and/or the plurality of slave nodes; the cloud server is connected with the master node and/or a plurality of slave nodes; the sensor clusters are used for collecting real-time working condition data of each fully mechanized coal mining equipment and sending the real-time working condition data to the edge distributed clusters; the edge distributed cluster is used for preprocessing the real-time working condition data, storing the real-time working condition data, managing the nodes of the master node and the plurality of slave nodes, and performing intelligent diagnosis based on the preprocessed real-time working condition data and an intelligent diagnosis model issued by the cloud server; the cloud server is used for storing the preprocessed real-time working condition data, constructing an intelligent diagnosis model based on the preprocessed real-time working condition data and managing the edge distributed cluster.
When the embodiment of the invention is implemented, the master node and the slave node in the edge distributed cluster adopt cheap and easily-expandable raspberry-set edge computers, and after the network communication among the edge computers is realized through the underground ring network, the distributed data real-time processing cluster is formed by deploying a distributed computing framework (Hadoop) of an Apache community and components (Kafka and Flink) thereof.
The coal mining equipment group comprises a coal mining machine, a hydraulic support, a reversed loader, an emulsion pump and a belt. The sensor cluster includes: the speed sensor, the current sensor and the temperature sensor are arranged on the traction motor and the cutting motor of the coal cutter and are used for collecting the traction speed, the cutting current and the cutting temperature of the coal cutter; the angle sensor, the pressure sensor and the elevation sensor are arranged on the top beam and the upright post of the hydraulic support and are used for acquiring the angle of the top beam/the base, the pressure of the upright post and elevation data of the support; the temperature sensor, the current sensor and the voltage sensor are arranged on the motor of the reversed loader and are used for collecting the temperature, the current and the voltage of the reversed loader; the temperature sensor and the pressure sensor are arranged on a pump station of the emulsion pump and an oil tank and are used for collecting the temperature, the oil temperature and the oil pressure of a bearing; and the speed sensor and the current sensor are arranged on the tail roller motor of the belt conveyor and are used for collecting the speed of the belt and the current of the motor. The real-time working condition data collected by the sensor cluster are transmitted to the edge distributed cluster through the CAN/Modbus/OPC protocol.
As a specific implementation manner, when the edge distributed cluster performs preprocessing and real-time data storage on the real-time working condition data, when new real-time working condition data is monitored, the cloud server sends a task to the main node, after the main node receives the task, the main node automatically triggers the link data preprocessing streaming job, and the job manager is started to be responsible for coordination and management of the whole job. Specifically, the master node divides the data preprocessing operation into different tasks according to the data quantity of the new real-time working condition data, queries the computing resources from each slave node, feeds back the computing resources to the master node from each slave node, and creates a data stream after determining the current idle slave node according to the feedback result, wherein the data stream is used for distributing the task quantity of the task of each slave node. And receiving new real-time working condition data by the current idle slave node, judging whether the new real-time working condition data has missing values and noise data, if so, processing the missing values and the noise data to obtain preliminarily processed real-time working condition data, and extracting effective characteristics in the preliminarily processed real-time working condition data as the preprocessed real-time working condition data and storing the preliminarily processed real-time working condition data. The valid characteristics may include, among other things, a value, a timestamp, a variable name, and the like. By extracting the effective characteristics, the data format of the real-time working condition data collected by each sensor in the sensor cluster can be unified. When the master node or the slave node stores the preprocessed real-time working condition data, the preprocessed real-time working condition data are stored into a Kafka message queue. The main node records the subject and the address of the preprocessed real-time working condition data obtained by each slave node. And compressing the preprocessed real-time working condition data obtained from each slave node according to the time granularity, obtaining the average value of all the preprocessed real-time working condition data in the time period by using a sliding window, and then sending the average value to the cloud server. The topics are used to represent data summaries and the addresses are used to represent data storage addresses. The problem of inconsistent acquisition time sequence can be solved by compressing according to the time granularity and calculating the average value in the sliding window. The host node can well configure user parameters through the JDBC interface and import the processed real-time working condition data into a historical database of the cloud server. And the cloud server stores the preprocessed real-time working condition data to a historical database.
Optionally, when the current idle slave node judges whether the new real-time working condition data has the missing value and the noise data, the current idle slave node judges whether the new real-time working condition data has the missing value through logical non-operation, and judges whether the new real-time working condition data is the noise data according to a preset threshold range. Further, when the current idle slave node processes the missing value and the noise data, the data of the position where the missing value and the noise data are located is reset after linear interpolation is carried out according to the effective working condition data before and after the missing value and the noise data.
By means of the mode of preprocessing the real-time working condition data, four problems of the real-time working condition data collected by the sensor cluster can be solved: (1) The noise appears in the real-time working condition data due to the interference of factors such as humidity and vibration. (2) Due to environmental complexity and equipment operating problems, some real-time operating condition data may be missing or lost, resulting in incomplete data sets. (3) Due to signal transmission delay, inconsistent acquisition frequency or equipment synchronization problems, inaccurate time sequence of real-time working condition data acquired by different sensors may be caused. (4) Due to the possible differences in data acquisition modes, frequencies, formats and the like among different devices, the data formats of the real-time working conditions are inconsistent.
As a specific implementation, the master node and the slave node of the cluster are customized when the edge distributed cluster is constructed. The embodiment of the invention comprises the following contents when carrying out node management on a master node and a plurality of slave nodes:
1. after the master node receives the tasks sent by the cloud server, a plurality of jobs are divided according to the size of task data, the idle slave nodes of the computing resources are distributed according to the number of the jobs to perform the jobs, and the master node logs off the slave node to release the occupied computing resources after all the jobs are operated.
2. Each slave node periodically reports the heartbeat signal and the available computing resources to the master node, and the master node periodically updates the state information (resource utilization rate, load condition and the like) of each slave node; and the master node judges whether any slave node fails according to a pre-configured heartbeat timeout threshold, and when any slave node fails, the master node locally clears the data of the failed slave node and sends the failure information to the cloud server for display through the ring network. And after the cloud server receives the fault information, scheduling technicians to solve the problem so as to ensure the normal operation of the edge distributed clusters.
In the embodiment of the invention, a cloud server is used as a hardware foundation by a server of a ground centralized control center and is responsible for constructing a data mining model, a user logs in the cloud server to check real-time working conditions of a working face through a front end interface of the coal mine ground centralized control center, constructs an intelligent diagnosis model, and transmits the constructed intelligent diagnosis model to an edge distributed cluster for operation. Specifically, when the cloud server builds the intelligent diagnosis model based on the preprocessed real-time working condition data, the intelligent diagnosis model is trained through the preprocessed real-time working condition data received by the history stored in the history database of the cloud server, a trained intelligent diagnosis model is obtained, the trained intelligent diagnosis model is updated through the preprocessed real-time working condition data sent by the edge distributed cluster in real time, and the updated intelligent diagnosis model is issued to a master node and a slave node in the edge distributed cluster. When intelligent diagnosis is performed based on the preprocessed real-time working condition data and the intelligent diagnosis model issued by the cloud server, the edge distributed cluster inputs the preprocessed real-time working condition data into the intelligent diagnosis model issued by the cloud server, obtains an intelligent diagnosis result according to an output result of the intelligent diagnosis model issued by the cloud server, and sends the intelligent diagnosis result to the cloud server for display.
Because machine learning model training consumes a large amount of computing resources, the embodiment of the invention puts the complicated work of intelligent diagnosis model construction on a cloud server for execution, and the cloud server issues the intelligent diagnosis model file to the edge distributed cluster after the intelligent diagnosis model construction is completed. When intelligent diagnosis is needed, the edge distributed cluster inputs the preprocessed real-time working condition data into an intelligent diagnosis model, the intelligent diagnosis model outputs an intelligent diagnosis result and sends the intelligent diagnosis result to a cloud server, and the cloud server displays the intelligent diagnosis result in real time. If the maintenance is needed, the staff is prompted to carry out the maintenance.
With respect to the type and purpose of the intelligent diagnostic model, embodiments of the present invention are not particularly limited. For example, the intelligent diagnosis model may be a fault diagnosis model for diagnosing a fault of the coal mining machine, a classification model for identifying a fault type, or the like. Fig. 2 is a schematic diagram of an interaction process between an edge distributed cluster and a cloud server in the system according to the embodiment of the present invention.
In addition, the cloud server in the embodiment of the invention is also responsible for managing the edge distributed clusters. And particularly, when the edge distributed cluster is managed, the cloud server inquires the state information of the master node and each slave node from the master node in real time and displays the state information of the master node and each slave node.
In summary, the system provided by the embodiment of the invention transmits a part of tasks such as data preprocessing and intelligent diagnosis from the cloud server to the edge distributed cluster, and various real-time working condition data of the working face are temporarily stored on a master node or a slave node in the edge distributed cluster after being preprocessed, and on the other hand, the data are stored in a historical database of the cloud server on the well, so that the real-time performance of data processing can be ensured, network blockage can be reduced, and the calculation pressure of the cloud server is released.
The system provided by the embodiment of the invention has the following characteristics:
1. and the edge distributed clusters are deployed on the working face to share the storage and calculation tasks of a part of the cloud server, so that the real-time performance of data processing can be effectively improved. The master node and the slave node are arranged to be cheap and easily-expanded raspberry-set edge computers, so that the whole system is low in cost.
2. By setting the edge distributed clusters, load balance is realized in the calculation process, and the situation that the calculation resource consumption of one computer is huge and other computers are not utilized is avoided.
3. The cloud server is released from redundant data transmission and processing, and the computing resource is mainly applied to mining and construction of the intelligent diagnosis model.
4. The edge distributed clusters split the data, so that the real-time performance of the data can be guaranteed, the data can be stored into the historical database of the cloud server through a data compression algorithm, and the increase of the storage pressure of the historical database due to the overhigh acquisition frequency is avoided.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, and it should be noted that it is possible for those skilled in the art to make several improvements and modifications without departing from the technical principle of the present invention, and these improvements and modifications should also be regarded as the protection scope of the present invention.
Claims (9)
1. The intelligent mining working face distributed edge data real-time processing system is characterized by comprising a coal mining equipment group, a sensor group, an edge distributed group and a cloud server;
the coal mining equipment group comprises a plurality of fully-mechanized coal mining equipment of a working face; the sensor cluster comprises a plurality of sensors of various types installed on fully-mechanized equipment; the edge distributed cluster comprises a master node and a plurality of slave nodes, the master node and the plurality of slave nodes are connected into the underground looped network to form a network path, and each sensor in the sensor cluster is connected with the master node and/or the plurality of slave nodes; the cloud server is connected with the master node and/or a plurality of slave nodes;
the sensor clusters are used for collecting real-time working condition data of each fully mechanized coal mining equipment and sending the real-time working condition data to the edge distributed clusters; the edge distributed cluster is used for preprocessing the real-time working condition data, storing the real-time working condition data, managing the nodes of the master node and the plurality of slave nodes, and performing intelligent diagnosis based on the preprocessed real-time working condition data and an intelligent diagnosis model issued by the cloud server; the cloud server is used for storing the preprocessed real-time working condition data, constructing an intelligent diagnosis model based on the preprocessed real-time working condition data and managing the edge distributed cluster.
2. The intelligent mining face distributed edge data real-time processing system according to claim 1, wherein the coal mining equipment group comprises a coal mining machine, a hydraulic support, a reversed loader, an emulsion pump and a belt conveyor;
the sensor cluster includes: a speed sensor, a current sensor and a temperature sensor are arranged on a traction motor and a cutting motor of the coal mining machine; the angle sensor, the pressure sensor and the elevation sensor are arranged on the top beam and the upright post of the hydraulic support; a temperature sensor, a current sensor and a voltage sensor are arranged on a motor of the reversed loader; a pump station of the emulsion pump, a temperature sensor and a pressure sensor are arranged on the oil tank; a speed sensor and a current sensor which are arranged on a tail roller motor of the belt conveyor.
3. The intelligent mining working face distributed edge data real-time processing system according to claim 1, wherein when the edge distributed cluster preprocesses and stores the real-time working condition data, when new real-time working condition data is monitored, a master node divides a data preprocessing operation into different tasks according to the data quantity of the new real-time working condition data, and inquires computing resources to slave nodes, the slave nodes feed back the computing resources to the master node, and the master node establishes a data stream after determining the current idle slave nodes according to the feedback result; the current idle slave node receives new real-time working condition data, judges whether the new real-time working condition data has missing values and noise data, processes the missing values and the noise data to obtain preliminarily processed real-time working condition data, and extracts effective characteristics in the preliminarily processed real-time working condition data as the preprocessed real-time working condition data and stores the preprocessed real-time working condition data; the main node records the subject and the address of the second real-time working condition data obtained by each slave node, compresses the preprocessed real-time working condition data obtained by each slave node according to the time granularity, obtains the average value of all preprocessed real-time working condition data of a time period by using a sliding window, and sends the average value to the cloud server.
4. The intelligent mining working face distributed edge data real-time processing system according to claim 3, wherein when the current idle slave node judges whether the new real-time working condition data has the missing value and the noise data, the current idle slave node judges whether the new real-time working condition data has the missing value through logical non-operation, and judges whether the new real-time working condition data is the noise data according to a preset threshold range.
5. The intelligent mining working face distributed edge data real-time processing system according to claim 3, wherein when the current idle slave node processes the missing value and the noise data, the data of the missing value and the noise data in the position is reset after linear interpolation is carried out according to the effective working condition data before and after the missing value and the noise data.
6. The intelligent mining face distributed edge data real-time processing system according to claim 3, 4 or 5, wherein the edge distributed cluster comprises the following contents when performing node management on a master node and a plurality of slave nodes:
1. after the master node receives the task sent by the cloud server, dividing a plurality of jobs according to the size of task data volume, distributing idle slave nodes of computing resources according to the job volume to perform the jobs, and logging off the master node to release the occupied computing resources after all the jobs are operated;
2. each slave node periodically reports the heartbeat signal and available computing resources to the master node, and the master node periodically updates the state information of each slave node; and the master node judges whether any slave node fails according to a pre-configured heartbeat timeout threshold, and when any slave node fails, the master node locally clears the data of the failed slave node and sends the failure information to the cloud server for display through the ring network.
7. The intelligent mining working face distributed edge data real-time processing system according to claim 1, wherein when intelligent diagnosis is performed based on the preprocessed real-time working condition data and an intelligent diagnosis model issued by a cloud server, the edge distributed cluster inputs the preprocessed real-time working condition data into the intelligent diagnosis model issued by the cloud server, obtains an intelligent diagnosis result according to an output result of the intelligent diagnosis model issued by the cloud server, and sends the intelligent diagnosis result to the cloud server for display.
8. The intelligent mining working face distributed edge data real-time processing system according to claim 1, wherein when the cloud server builds the intelligent diagnosis model based on the preprocessed real-time working condition data, the intelligent diagnosis model is trained through the preprocessed real-time working condition data received by the histories stored in the histories database of the cloud server, a trained intelligent diagnosis model is obtained, the trained intelligent diagnosis model is updated through the preprocessed real-time working condition data sent by the edge distributed cluster in real time, and the updated intelligent diagnosis model is issued to a master node and a slave node in the edge distributed cluster.
9. The intelligent mining working face distributed edge data real-time processing system according to claim 1, wherein the cloud server queries state information of a master node and each slave node from the master node in real time and displays the state information of the master node and each slave node when managing the edge distributed clusters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311715562.XA CN117675821A (en) | 2023-12-13 | 2023-12-13 | Intelligent mining working face distributed edge data real-time processing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311715562.XA CN117675821A (en) | 2023-12-13 | 2023-12-13 | Intelligent mining working face distributed edge data real-time processing system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117675821A true CN117675821A (en) | 2024-03-08 |
Family
ID=90073162
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311715562.XA Pending CN117675821A (en) | 2023-12-13 | 2023-12-13 | Intelligent mining working face distributed edge data real-time processing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117675821A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118433186A (en) * | 2024-07-03 | 2024-08-02 | 天津恒达文博科技股份有限公司 | Management data batch quick processing method for intelligent navigation machine |
-
2023
- 2023-12-13 CN CN202311715562.XA patent/CN117675821A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118433186A (en) * | 2024-07-03 | 2024-08-02 | 天津恒达文博科技股份有限公司 | Management data batch quick processing method for intelligent navigation machine |
| CN118433186B (en) * | 2024-07-03 | 2024-09-13 | 天津恒达文博科技股份有限公司 | Management data batch quick processing method for intelligent navigation machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102520044B1 (en) | Alert log compression method, device, and system, and storage medium | |
| CN106452881B (en) | Operation and maintenance data processing system based on cloud adding mode | |
| CN103338261B (en) | The storage of a kind of track traffic Monitoring Data and processing method and system | |
| CN101667034B (en) | Scalable monitoring system supporting hybrid clusters | |
| CN103532744B (en) | A kind of intelligent grid information communication integral supporting platform | |
| CN111242807B (en) | Method for accessing substation data into ubiquitous power Internet of things | |
| CN101095307A (en) | Network management appliance | |
| CN109214704A (en) | A kind of distributed intelligence operation platform, method, apparatus and readable storage medium storing program for executing | |
| CN107968482B (en) | New energy power generation station management platform | |
| CN103761309A (en) | Operation data processing method and system | |
| CN104616205A (en) | Distributed log analysis based operation state monitoring method of power system | |
| CN105843182A (en) | Power dispatching accident handling scheme preparing system and power dispatching accident handling scheme preparing method based on OMS | |
| CN108092813A (en) | Data center's total management system server hardware Governance framework and implementation method | |
| CN101902497B (en) | Cloud computing based internet information monitoring system and method | |
| CN108156225B (en) | Micro-application monitoring system and method based on container cloud platform | |
| CN117675821A (en) | Intelligent mining working face distributed edge data real-time processing system | |
| CN110427298A (en) | A kind of Automatic Feature Extraction method of distributed information log | |
| CN115733762A (en) | Monitoring system with big data analysis capability | |
| CN115277409A (en) | Method and device for collecting and reporting buried point data in real time, acquisition system and terminal | |
| CN104601374A (en) | Network fault processing method and device for numerical control machine tool | |
| CN109634808A (en) | A kind of chain type monitor event root cause analysis method based on association analysis | |
| CN114037298A (en) | Intelligent mining comprehensive management system for coal mine | |
| CN103226572A (en) | Expandable monitoring method and monitoring system based on data compression | |
| CN114615013B (en) | Comprehensive auditing method and system for network shooting range | |
| CN115543345A (en) | Distributed computing system for power time sequence data and implementation method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |