CN117905683A - Intelligent control method for lithium battery air compressor - Google Patents
Intelligent control method for lithium battery air compressor Download PDFInfo
- Publication number
- CN117905683A CN117905683A CN202410119702.5A CN202410119702A CN117905683A CN 117905683 A CN117905683 A CN 117905683A CN 202410119702 A CN202410119702 A CN 202410119702A CN 117905683 A CN117905683 A CN 117905683A
- Authority
- CN
- China
- Prior art keywords
- operation state
- air compressor
- time sequence
- sequence
- lithium
- 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.)
- Granted
Links
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 title claims abstract description 177
- 229910052744 lithium Inorganic materials 0.000 title claims abstract description 177
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000002159 abnormal effect Effects 0.000 claims abstract description 46
- 238000012098 association analyses Methods 0.000 claims abstract description 12
- 239000013598 vector Substances 0.000 claims description 84
- 238000012549 training Methods 0.000 claims description 60
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 claims description 30
- 229910001416 lithium ion Inorganic materials 0.000 claims description 30
- 230000005856 abnormality Effects 0.000 claims description 15
- 238000013527 convolutional neural network Methods 0.000 claims description 14
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 abstract description 9
- 238000013135 deep learning Methods 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 abstract description 5
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 description 12
- 238000012423 maintenance Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 230000000737 periodic effect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000006835 compression Effects 0.000 description 3
- 238000007906 compression Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000007774 longterm Effects 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 230000002542 deteriorative effect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
- F04B—POSITIVE-DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS
- F04B51/00—Testing machines, pumps, or pumping installations
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
- F04B—POSITIVE-DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS
- F04B35/00—Piston pumps specially adapted for elastic fluids and characterised by the driving means to their working members, or by combination with, or adaptation to, specific driving engines or motors, not otherwise provided for
- F04B35/04—Piston pumps specially adapted for elastic fluids and characterised by the driving means to their working members, or by combination with, or adaptation to, specific driving engines or motors, not otherwise provided for the means being electric
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
- F04B—POSITIVE-DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS
- F04B49/00—Control, e.g. of pump delivery, or pump pressure of, or safety measures for, machines, pumps, or pumping installations, not otherwise provided for, or of interest apart from, groups F04B1/00 - F04B47/00
- F04B49/06—Control using electricity
- F04B49/065—Control using electricity and making use of computers
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
- F04B—POSITIVE-DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS
- F04B49/00—Control, e.g. of pump delivery, or pump pressure of, or safety measures for, machines, pumps, or pumping installations, not otherwise provided for, or of interest apart from, groups F04B1/00 - F04B47/00
- F04B49/10—Other safety measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mechanical Engineering (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Computer Hardware Design (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses an intelligent control method of a lithium battery air compressor, which relates to the technical field of intelligent control of air compressors, and is characterized in that operation state data such as current, rotating speed, temperature, exhaust temperature, pressure, lithium battery voltage, lithium battery capacity and the like of the lithium battery air compressor are collected through real-time monitoring, time sequence characteristic association analysis of the operation state data of the lithium battery air compressor is carried out by utilizing a data processing and deep learning technology, so that whether the operation state of the lithium battery air compressor is abnormal or not is judged based on real-time operation conditions, and an early warning prompt is sent out by suspending the monitored lithium battery air compressor when the operation state is judged to be abnormal.
Description
Technical Field
The application relates to the technical field of intelligent control of air compressors, in particular to an intelligent control method of a lithium battery air compressor.
Background
A lithium battery air compressor is an air compressor using a lithium battery as an energy source, which generates power by storing air in a container under compression and then releasing the compressed air when necessary. Lithium batteries provide portability and flexibility as an energy source such that such compressors are commonly used for outdoor activities, automotive maintenance and emergency situations.
The running state of the lithium battery air compressor has important influence on the aspects of performance, energy efficiency, service life and the like of equipment, and the abnormal running state is timely detected and processed, so that preventive maintenance and regular maintenance are carried out, the normal running of the equipment can be ensured, and the reliability of the equipment is improved.
However, the abnormal detection of the operation state of the traditional lithium air compressor generally needs to manually observe and judge the operation state of equipment, which may be affected by human subjective factors, so that the detection result is inaccurate or unreliable. In addition, the conventional anomaly detection method generally analyzes and judges collected specific data after the device is operated. However, this approach cannot monitor the state of the device during operation in real time and comprehensively, thereby affecting the accuracy of abnormality determination.
Accordingly, an optimized intelligent control scheme for lithium electric air compressors is desired.
Disclosure of Invention
The present application has been made to solve the above-mentioned technical problems. The embodiment of the application provides an intelligent control method for a lithium battery air compressor, which is characterized in that operation state data such as current, rotating speed, temperature, exhaust temperature, pressure, lithium battery voltage, lithium battery capacity and the like of the lithium battery air compressor are monitored and collected in real time, time sequence characteristic association analysis of the operation state data of the lithium battery air compressor is carried out by utilizing a data processing and deep learning technology, so that whether the operation state of the lithium battery air compressor is abnormal or not is judged based on the real-time operation condition of the lithium battery air compressor, and the monitored lithium battery air compressor is paused and an early warning prompt is sent when the operation state is judged to be abnormal. Therefore, the running state of the lithium battery air compressor can be monitored and analyzed in real time, so that the degree of automation and the degree of accuracy of abnormality detection of the lithium battery air compressor are improved, the service life and the performance of the lithium battery air compressor are optimized, and the safety and the stability of the lithium battery air compressor are ensured.
According to an aspect of the present application, there is provided an intelligent control method of a lithium battery air compressor, including:
acquiring a time sequence of operation state data of the monitored lithium battery air compressor in a preset time period, wherein the operation state data comprise compressor current, compressor rotating speed, compressor temperature, compressor exhaust temperature, compressor pressure, lithium battery voltage and lithium battery capacity;
performing sequence segmentation on the time sequence of the running state data based on a preset time scale to obtain a sequence of a local time sequence of the running state data;
Performing operation state local time sequence semantic analysis on each operation state data local time sequence in the sequence of the operation state data local time sequence to obtain a sequence of operation state local time domain associated semantic feature vectors;
Performing full-time-domain operation state time sequence semantic association analysis on the sequence of the operation state local time sequence semantic association feature vectors to obtain operation state time sequence semantic association feature vectors of the monitored lithium battery air compressor as operation state time sequence semantic association features of the monitored lithium battery air compressor;
Based on the time sequence semantic association characteristics of the running state of the monitored lithium-ion air compressor, determining whether the running state is abnormal, determining whether to pause the monitored lithium-ion air compressor and sending out an early warning prompt.
Compared with the prior art, the intelligent control method for the lithium battery air compressor provided by the application has the advantages that the current, the rotating speed, the temperature, the exhaust temperature, the pressure, the lithium battery voltage, the lithium battery capacity and other operation state data of the lithium battery air compressor are monitored and collected in real time, the time sequence characteristic association analysis of the operation state data of the lithium battery air compressor is carried out by utilizing the data processing and deep learning technology, so that whether the operation state of the lithium battery air compressor is abnormal or not is judged on the basis of the real-time operation condition of the lithium battery air compressor, the monitored lithium battery air compressor is suspended and an early warning prompt is sent out when the operation state is judged to be abnormal, the operation state of the lithium battery air compressor can be monitored and analyzed in real time, the degree of automation and the degree of abnormality detection of the lithium battery air compressor are improved, the service life and the performance of the lithium battery air compressor are optimized, and the safety and the stability of the lithium battery air compressor are ensured.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing embodiments of the present application in more detail with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and together with the embodiments of the application, and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.
Fig. 1 is a flowchart of an intelligent control method of a lithium battery air compressor according to an embodiment of the present application.
Fig. 2 is a schematic diagram of an intelligent control method of a lithium battery air compressor according to an embodiment of the application.
Fig. 3 is a flowchart of determining whether an abnormality exists in an operation state and determining whether to suspend the monitored lithium air compressor and sending out an early warning prompt according to the operation state time sequence semantic association feature of the monitored lithium air compressor in the intelligent control method of the lithium air compressor according to the embodiment of the application.
Fig. 4 is a flowchart of training the operational state time sequence feature extractor based on the convolutional neural network model, the operational state time sequence correlation feature extractor based on the LSTM model, and the classifier in the intelligent control method of the lithium-ion battery air compressor according to the embodiment of the application.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure have been shown in the accompanying drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.
It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order and/or performed in parallel. Furthermore, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.
In describing embodiments of the present disclosure, the term "comprising" and its like should be taken to be open-ended, i.e., including, but not limited to. The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first," "second," and the like, may refer to different or the same object. Other explicit and implicit definitions are also possible below.
It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be construed unless the context clearly indicates otherwise.
A lithium battery air compressor is an air compressor that uses a lithium battery as an energy source. The air compressor is driven to work by converting electric energy into mechanical energy, and air is compressed into high-pressure gas. The lithium battery has the advantages of high energy density, long service life, environmental protection and the like as an energy source, and can provide stable power for the air compressor. Lithium-ion air compressors are widely used in situations where portability, wireless and low noise are desirable, such as outdoor sports, auto repair, inflation tools, etc. The compressor device does not need an external power supply, has flexibility and convenience, and is efficient and reliable.
The operation state of the lithium battery air compressor has an important influence on the performance and the use effect thereof, and in particular, one of the influence of the operation state is the compression efficiency of the compressor. The compression efficiency of a compressor may vary under different operating conditions, such as different pressure, temperature and load conditions. The efficient compressor is able to more efficiently compress air into high pressure gas, providing more power and higher inflation speed. Lithium battery air compressors use lithium batteries as an energy source, and thus battery life is an important consideration. The operation state can influence the charge and discharge cycle times, current load, charge speed and the like of the battery. The normal running state can prolong the service life of the battery and improve the reliability and durability of the lithium battery air compressor. In addition, the performance and life of lithium batteries are greatly affected by temperature. The operation state can influence the heat dissipation effect, temperature control and protection mechanism of the equipment. Therefore, the operation state of the lithium battery air compressor has important influence on the aspects of performance, battery life, temperature management and the like. Reasonable operating conditions can improve the efficiency, reliability and durability of the device while providing better use experience and protection measures.
However, the conventional abnormality detection method generally needs to rely on manual observation and judgment of the operation state of the apparatus, which may be affected by artificial subjective factors, resulting in inaccurate or unreliable detection results. In addition, the conventional anomaly detection method generally analyzes and judges collected specific data after the device is operated. The method has a certain delay, and cannot comprehensively monitor the state change of the equipment in the running process in real time. Thus, if an abnormality occurs in the device at a certain instant, but the data acquisition at that abnormal instant has not been analyzed, the abnormality may be delayed or missed.
Therefore, aiming at the technical problems, the technical conception of the application is that the operation state data such as the compressor current, the compressor rotating speed, the compressor temperature, the compressor exhaust temperature, the compressor pressure, the lithium battery voltage, the lithium battery capacity and the like of the lithium battery air compressor are collected through real-time monitoring, the time sequence characteristic association analysis of the operation state data of the lithium battery air compressor is carried out by utilizing the data processing and deep learning technology, so that whether the operation state of the lithium battery air compressor is abnormal or not is judged based on the real-time operation condition of the lithium battery air compressor, and the monitored lithium battery air compressor is paused when the operation state is judged to be abnormal, and an early warning prompt is sent. Therefore, the running state of the lithium battery air compressor can be monitored and analyzed in real time, so that the degree of automation and the degree of accuracy of abnormality detection of the lithium battery air compressor are improved, the service life and the performance of the lithium battery air compressor are optimized, and the safety and the stability of the lithium battery air compressor are ensured.
Fig. 1 is a flowchart of an intelligent control method of a lithium battery air compressor according to an embodiment of the present application. Fig. 2 is a schematic diagram of an intelligent control method of a lithium battery air compressor according to an embodiment of the application. As shown in fig. 1 and 2, the intelligent control method of the lithium battery air compressor according to the embodiment of the application comprises the following steps: s110, acquiring a time sequence of operation state data of the monitored lithium battery air compressor in a preset time period, wherein the operation state data comprise compressor current, compressor rotating speed, compressor temperature, compressor exhaust temperature, compressor pressure, lithium battery voltage and lithium battery capacity; s120, performing sequence segmentation on the time sequence of the running state data based on a preset time scale to obtain a sequence of a local time sequence of the running state data; s130, performing operation state local time sequence semantic analysis on each operation state data local time sequence in the sequence of the operation state data local time sequence to obtain a sequence of operation state local time domain associated semantic feature vectors; s140, carrying out full-time-domain operation state time sequence semantic association analysis on the sequence of operation state local time sequence semantic association feature vectors to obtain operation state time sequence semantic association feature vectors of the monitored lithium air compressor as operation state time sequence semantic association features of the monitored lithium air compressor; and S150, determining whether the running state is abnormal or not based on the time sequence semantic association characteristic of the running state of the monitored lithium-ion air compressor, determining whether to pause the monitored lithium-ion air compressor and sending out an early warning prompt.
In step S110, a time series of monitored operating state data of the lithium battery air compressor over a predetermined period of time is acquired, wherein the operating state data includes compressor current, compressor speed, compressor temperature, compressor discharge temperature, compressor pressure, lithium battery voltage, and lithium battery capacity. It should be appreciated that the various operating parameters in the monitored lithium air compressor operating state data over the predetermined period of time provide information regarding the actual operation of the lithium air compressor, which can be used to determine the operation of the device, load levels, energy consumption, health and potential faults. Based on the above, in the technical scheme of the application, the time sequence of the running state data of the monitored lithium-ion air compressor in the preset time period is obtained, and various parameters of the lithium-ion air compressor can be monitored and processed and analyzed to judge whether the lithium-ion air compressor has abnormal states, such as abnormal current, over-high temperature, abnormal pressure and the like, so that the safety and stability of equipment are improved.
In step S120, the time series of the operation state data is subjected to sequence slicing based on a predetermined time scale to obtain a sequence of the operation state data local time series. Accordingly, it is contemplated that the operating conditions of the lithium battery air compressor may have different patterns and trends over different time periods, that is, abnormal changes and fluctuations in the operating condition parameters may occur only over certain time periods and may not be apparent over the entire time sequence. Based on the above, in the technical scheme of the application, the time sequence of the running state data is further subjected to sequence segmentation based on a preset time scale to obtain the sequence of the local time sequence of the running state data, so that the time sequence characteristics of the running state of the lithium battery air compressor can be better captured. It should be appreciated that by slicing the time series, the series of operational state data may be segmented into shorter time periods, each time period representing the operational state of the lithium-ion air compressor during that partially continuous time period. In this way, the operation state data in a specific time period can be analyzed, for example, the operation state data can be segmented into time periods of hours, days, weeks or months, so that the performance change of the equipment on different time scales can be better known, the abnormality or trend of the operation state of the equipment can be found, and corresponding measures can be timely taken for adjustment, maintenance or prediction.
In step S130, performing a local time-sequence semantic analysis of the running state on each running state data local time sequence in the sequence of the running state data local time sequences to obtain a sequence of running state local time-domain associated semantic feature vectors. Specifically, in an embodiment of the present application, performing a running state local time sequence semantic analysis on each running state data local time sequence in the sequence of the running state data local time sequence to obtain a sequence of running state local time domain associated semantic feature vectors, including: and performing feature extraction on the sequence of the operation state data local time sequence by using an operation state time sequence feature extractor based on a deep neural network model to obtain the sequence of the operation state local time domain associated semantic feature vector. In particular, the operational state time sequence feature extractor based on the deep neural network model is an operational state time sequence feature extractor based on a convolutional neural network model. It should be understood that it is considered that the local time series of each of the operation state data contains time-series association information about the operation state data, and that there is a certain correlation between the operation state data at adjacent time points, such as an operation mode, a periodic fluctuation, an abnormal mode, or the like, with time-series association between the respective operation state data items. The convolutional neural network can effectively capture local time sequence correlation characteristics when processing time sequence data. Therefore, in order to better capture the time sequence characteristics in the running state data and better understand the time sequence association between the running state data, in the technical scheme of the application, the sequence of the running state data local time sequence is subjected to characteristic extraction by using a running state time sequence characteristic extractor based on a convolutional neural network model to obtain the sequence of the running state local time domain association semantic characteristic vector, so that the local association time sequence characteristics about each data item in the running state data in each local time period can be extracted, and the change modes and trends of the running state data in different local time sequences are captured. It is worth mentioning that the convolutional neural network can automatically learn and extract the local time sequence mode of the running state through the convolutional operation and the pooling operation, so that the time sequence characteristics of the running state, including time sequence mode, trend, periodicity and the like, can be captured better, and the basis and support can be provided for the abnormal judgment of the subsequent running state.
In step S140, the sequence of the operation state local time domain associated semantic feature vectors is subjected to full time domain operation state time sequence semantic association analysis to obtain the operation state time sequence semantic associated feature vector of the monitored lithium air compressor as the operation state time sequence semantic associated feature of the monitored lithium air compressor. Accordingly, it is considered that the operation state of the lithium air compressor is a dynamic process, in which a large amount of time series data is included, for example, including changes in pressure, temperature, voltage, current, etc. And the operation parameters of the lithium battery air compressor have interaction and influence. Therefore, in the technical scheme of the application, the sequence of the operation state local time domain associated semantic feature vectors is further subjected to full time domain operation state time sequence semantic association analysis to obtain the operation state time sequence semantic associated feature vectors of the monitored lithium electric air compressor as the operation state time sequence semantic associated features of the monitored lithium electric air compressor, so that the overall trend, the periodic variation and the abnormal behavior of the operation of the lithium electric air compressor are understood, and some modes and rules hidden behind data, such as time sequence relations among different operation state parameters, the periodic variation of the operation state, the time sequence features of abnormal events and the like, are found, so that whether the operation state of the equipment is normal or not can be better, more accurately and accurately judged.
Specifically, in an embodiment of the present application, performing full-time domain operation state time sequence semantic association analysis on the sequence of operation state local time sequence semantic association feature vectors to obtain a monitored lithium air compressor operation state time sequence semantic association feature vector as a monitored lithium air compressor operation state time sequence semantic association feature, including: and the sequence of the operation state local time domain associated semantic feature vectors passes through an operation state time sequence associated feature extractor based on an LSTM model to obtain the operation state time sequence semantic associated feature vector of the monitored lithium air compressor as the operation state time sequence semantic associated feature of the monitored lithium air compressor. It should be appreciated that it is contemplated that in operational state data, the state at the current time tends to be related to the state at the past time, that is, the operational state data has a dependency between contexts at each time period. It is worth mentioning that LSTM is a Recurrent Neural Network (RNN) variant suitable for processing time series data. Compared with the traditional RNN model, the LSTM can effectively capture and memorize long-term dependency relationship in time series data. Therefore, in order to better capture semantic association information among various time periods of the operation state data, in the technical scheme of the application, the sequence of the operation state local time domain association semantic feature vectors passes through an operation state time sequence association feature extractor based on an LSTM model to obtain the operation state time sequence semantic association feature vector of the monitored lithium-ion air compressor so as to better understand the context semantic association feature information among the local time sequence association features of various operation state data items in the operation state data in different local time periods.
In particular, it is worth mentioning that the operational state time-series associated feature extractor based on the LSTM (long-short-term memory) model is a model for extracting meaningful features from time-series data. In detail, LSTM is a variant of Recurrent Neural Network (RNN) dedicated to processing time series data. Compared with the traditional RNN, the LSTM model can better process long-term dependence and avoid the problems of gradient disappearance or gradient explosion. That is, in the running state timing related feature extractor, the LSTM model is used as a main feature extraction tool. The method receives a sequence of the operation state local time domain associated semantic feature vectors as input, and extracts higher-level semantic features by learning time sequence association in the sequence. The LSTM model can capture long-term dependencies in time series data by adaptively updating and forgetting the states of memory cells. It can remember past information and use this information in a subsequent time step to influence the current output. This mechanism enables the LSTM model to model patterns and rules in the time series data. Through the LSTM model, the specific time sequence correlation characteristic suitable for the running state of the lithium battery air compressor can be learned. These characteristics may be timing relationships between different parameters, periodic changes in operating conditions, timing characteristics of abnormal events, etc. The extracted time sequence semantic association feature vector can be used as a representation of the running state of the monitored lithium-ion battery air compressor for subsequent abnormality detection, fault diagnosis or other related tasks. Therefore, the LSTM model-based operation state time sequence correlation feature extractor can learn meaningful time sequence correlation features from time sequence data, and provides more comprehensive and accurate description for the operation state of the lithium battery air compressor.
In step S150, based on the time sequence semantic association characteristic of the operation state of the monitored lithium-ion battery air compressor, whether the operation state is abnormal or not is determined, whether the monitored lithium-ion battery air compressor is suspended or not is determined, and an early warning prompt is sent. Fig. 3 is a flowchart of determining whether an abnormality exists in an operation state and determining whether to suspend the monitored lithium air compressor and sending out an early warning prompt according to the operation state time sequence semantic association feature of the monitored lithium air compressor in the intelligent control method of the lithium air compressor according to the embodiment of the application. Specifically, in the embodiment of the present application, as shown in fig. 3, based on the time sequence semantic association feature of the operation state of the monitored lithium air compressor, determining whether there is an abnormality in the operation state, and determining whether to suspend the monitored lithium air compressor and send out an early warning prompt, including: s210, passing the time sequence semantic association feature vector of the operation state of the monitored lithium-ion air compressor through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the operation state is abnormal or not; and S220, suspending the monitored lithium battery air compressor and sending out an early warning prompt in response to the classification result that the running state is abnormal.
Specifically, the step S210 is to pass the time sequence semantic association feature vector of the monitored lithium air compressor running state through a classifier to obtain a classification result, where the classification result is used for indicating whether the running state is abnormal or not. Specifically, in an embodiment of the present application, the monitored lithium-ion air compressor operation state time sequence semantic association feature vector is passed through a classifier to obtain a classification result, where the classification result is used to indicate whether an abnormality exists in the operation state, and the method includes: performing full-connection coding on the operation state time sequence semantic association characteristic vector of the monitored lithium air compressor by using a full-connection layer of the classifier to obtain a classification characteristic vector of the operation state time sequence semantic association coding of the monitored lithium air compressor; and inputting the time sequence semantic association coding classification feature vector of the operation state of the monitored lithium-ion air compressor into a Softmax classification function of the classifier to obtain the classification result. That is, the time sequence semantic association characteristic of the operation state of the monitored lithium battery air compressor is utilized to carry out classification processing, so that whether the operation state is abnormal or not is automatically judged based on the real-time operation state of the monitored lithium battery air compressor. In this way, further expansion of equipment faults can be avoided, faults and downtime can be reduced, and corresponding repair or maintenance measures can be taken, so that the reliability, stability and usability of the equipment can be improved. It should be understood that the operation state time sequence semantic association feature vector of the monitored lithium battery air compressor is classified by the classifier, so that whether the operation state is abnormal or not can be judged. It should be noted that the classifier is a machine learning model that can learn the mapping relationship from input data (i.e., feature vectors) to output categories (normal or abnormal). The classifier can find abnormal modes or characteristics from the time sequence semantic association characteristic vectors of the monitored lithium-ion air compressor running state, so that whether the running state is abnormal or not is judged.
Specifically, in S220, in response to the classification result that the running state is abnormal, the monitored lithium battery air compressor is suspended and an early warning prompt is sent. Accordingly, when the classification result output by the classifier indicates that the running state is abnormal, corresponding measures are required to be taken to protect equipment and ensure safety. One common response is to pause the monitored lithium air compressor and issue a warning prompt. This prevents further worsening of the abnormal condition and reduces potential risks and losses. It should be appreciated that the lithium battery air compressor being monitored is paused in order to avoid further impact of abnormal conditions on the equipment. By suspending the operation, the operation of the apparatus can be stopped, preventing an abnormal state from causing more serious malfunction or damage. Meanwhile, the early warning prompt can be sent out to inform related personnel in time, so that the related personnel can take appropriate measures to handle abnormal conditions, such as performing fault removal, maintenance or replacing equipment. In this way, measures can be taken in time to prevent the abnormal state from further deteriorating, and provide opportunities for troubleshooting and maintenance, thereby protecting the safety of the equipment.
It should be noted that those skilled in the art should know that the deep neural network model needs to be trained before the deep neural network model is applied to make the inference so that the deep neural network can implement a specific function.
Specifically, in the embodiment of the present application, the method further includes a training step: the method is used for training the operation state time sequence feature extractor based on the convolutional neural network model, the operation state time sequence associated feature extractor based on the LSTM model and the classifier.
Fig. 4 is a flowchart of training the operational state time sequence feature extractor based on the convolutional neural network model, the operational state time sequence correlation feature extractor based on the LSTM model, and the classifier in the intelligent control method of the lithium-ion battery air compressor according to the embodiment of the application. As shown in fig. 4, the training step includes: s310, training data is acquired, wherein the training data comprises a time sequence of training operation state data of the monitored lithium battery air compressor in a preset time period, and whether an abnormal true value exists in the operation state; s320, performing sequence segmentation on the time sequence of the training operation state data based on a preset time scale to obtain a sequence of a local time sequence of the training operation state data; s330, performing feature extraction on the sequence of the training operation state data local time sequence by using the operation state time sequence feature extractor based on the convolutional neural network model to obtain a sequence of training operation state local time domain associated semantic feature vectors; s340, passing the sequence of the training operation state local time domain associated semantic feature vectors through the operation state time sequence associated feature extractor based on the LSTM model to obtain training monitored lithium battery air compressor operation state time sequence semantic associated feature vectors; s350, passing the training monitored lithium battery air compressor running state time sequence semantic association feature vector through the classifier to obtain a classification loss function value; and S360, training the operation state time sequence feature extractor based on the convolutional neural network model, the operation state time sequence associated feature extractor based on the LSTM model and the classifier based on the classification loss function value and through back propagation of gradient descent, wherein the operation state time sequence associated feature vector of the lithium air compressor to be trained is optimized each time the operation state time sequence associated feature vector of the lithium air compressor to be trained is iterated through classification regression of the classifier.
Specifically, in step S360, the operation state time sequence feature extractor based on the convolutional neural network model, the operation state time sequence associated feature extractor based on the LSTM model and the classifier are trained based on the classification loss function value and through back propagation of gradient descent, wherein each time the operation state time sequence semantic associated feature vector of the training monitored lithium air compressor is iterated through the classifier for classification regression, the operation state time sequence semantic associated feature vector of the training monitored lithium air compressor is optimized. It should be understood that in the above technical solution, each training operation state local time domain associated semantic feature vector in the sequence of training operation state local time domain associated semantic feature vectors expresses a time sequence-sample associated semantic feature of the training operation state data in the local time domain, and after the sequence of training operation state local time domain associated semantic feature vectors passes through the operation state time sequence associated feature extractor based on the LSTM model, the obtained training monitored lithium air compressor operation state time sequence associated semantic feature vectors may further represent a global time sequence-sample associated semantic feature based on short-long-range dual context time sequence association between local time domains.
However, when the training operation state local time domain associated semantic feature vector contains semantic feature representations based on time sequence association and sample association, and the training monitored lithium air compressor operation state time sequence associated semantic feature vector fuses local-global time sequence associated semantic features, the feature distribution information saliency of the training operation state local time domain associated semantic feature vector based on specific feature distribution of the training operation state local time domain associated semantic feature vector is also influenced, so that when the training monitored lithium air compressor operation state time sequence semantic associated semantic feature vector is classified by a classifier, the training operation state time sequence semantic associated semantic feature vector is difficult to stably focus on the salient local distribution of the feature, and the training speed is influenced. Based on the above, in the technical scheme of the application, the operation state time sequence semantic association feature vector of the lithium air compressor to be monitored is optimized when the operation state time sequence semantic association feature vector of the lithium air compressor to be monitored is subjected to the iteration of classification regression through the classifier each time.
More specifically, in the embodiment of the present application, each time the training monitored lithium air compressor operation state time sequence semantic association feature vector performs an iteration of classification regression through the classifier, optimizing the training monitored lithium air compressor operation state time sequence semantic association feature vector includes: when each time of the training of the operation state time sequence semantic association feature vector of the monitored lithium air compressor carries out iteration of classification regression through the classifier, the training of the operation state time sequence semantic association feature vector of the monitored lithium air compressor is optimized according to the following optimization formula; wherein, the optimization formula is:
wherein, And/>The training of the operation state time sequence semantic association feature vector/> of the monitored lithium air compressor is respectively thatSquare of 1-norm and 2-norm,/>Is the training monitored lithium air compressor running state time sequence semantic association feature vector/>And/>Is a weight superparameter,/>Is the/>, in the training of the time sequence semantic association feature vector of the operation state of the monitored lithium-ion air compressorCharacteristic value of individual position,/>Is the/>, in the optimized training of the operation state time sequence semantic association feature vector of the monitored lithium-ion battery air compressorCharacteristic value of individual position,/>Is a logarithmic function value based on 2.
In particular, by timing semantically correlating feature vectors based on the training of the monitored lithium air compressor operating stateGeometric registration of the high-dimensional characteristic manifold shape is carried out by the scale and structural parameters of the lithium battery air compressor, and the training of the operation state time sequence semantic association characteristic vector/>, of the monitored lithium battery air compressor, can be focused onFeatures with rich feature semantic information in feature sets formed by feature values, namely distinguishable stable interest features representing dissimilarity based on local context information when the classifier classifies, so that the training of the time sequence semantic association feature vector/>, of the running state of the monitored lithium-ion air compressor, is realizedAnd the feature information significance is marked in the classification process, so that the training speed of the classifier is improved. Therefore, the running state of the lithium battery air compressor can be monitored and analyzed in real time, so that the accuracy of anomaly detection is improved, the service life and performance of the lithium battery air compressor are optimized, and the safety and stability of the lithium battery air compressor are ensured.
In summary, the intelligent control method of the lithium battery air compressor based on the embodiment of the application is clarified, by monitoring and collecting the operation state data such as the compressor current, the compressor rotating speed, the compressor temperature, the compressor exhaust temperature, the compressor pressure, the lithium battery voltage, the lithium battery capacity and the like of the lithium battery air compressor in real time, and carrying out time sequence feature association analysis on the operation state data of the lithium battery air compressor by utilizing the data processing and deep learning technology, thereby judging whether the operation state of the lithium battery air compressor is abnormal or not based on the real-time operation condition of the lithium battery air compressor, and suspending the monitored lithium battery air compressor and sending an early warning prompt when judging that the operation state is abnormal. Therefore, the running state of the lithium battery air compressor can be monitored and analyzed in real time, so that the degree of automation and the degree of accuracy of abnormality detection of the lithium battery air compressor are improved, the service life and the performance of the lithium battery air compressor are optimized, and the safety and the stability of the lithium battery air compressor are ensured.
The foregoing is merely illustrative of the principles of this disclosure and various modifications can be made by those skilled in the art without departing from the scope of this disclosure. The above embodiments are presented for purposes of illustration and not limitation. The present disclosure may take many forms other than those explicitly described herein. Therefore, it is emphasized that the present disclosure is not limited to the specifically disclosed methods, systems and devices, but is intended to include variations and modifications that fall within the spirit of the appended claims.
Claims (9)
1. An intelligent control method for a lithium battery air compressor is characterized by comprising the following steps:
acquiring a time sequence of operation state data of the monitored lithium battery air compressor in a preset time period, wherein the operation state data comprise compressor current, compressor rotating speed, compressor temperature, compressor exhaust temperature, compressor pressure, lithium battery voltage and lithium battery capacity;
performing sequence segmentation on the time sequence of the running state data based on a preset time scale to obtain a sequence of a local time sequence of the running state data;
Performing operation state local time sequence semantic analysis on each operation state data local time sequence in the sequence of the operation state data local time sequence to obtain a sequence of operation state local time domain associated semantic feature vectors;
Performing full-time-domain operation state time sequence semantic association analysis on the sequence of the operation state local time sequence semantic association feature vectors to obtain operation state time sequence semantic association feature vectors of the monitored lithium battery air compressor as operation state time sequence semantic association features of the monitored lithium battery air compressor;
Based on the time sequence semantic association characteristics of the running state of the monitored lithium-ion air compressor, determining whether the running state is abnormal, determining whether to pause the monitored lithium-ion air compressor and sending out an early warning prompt.
2. The intelligent control method of a lithium-ion battery air compressor according to claim 1, wherein performing a local time-series semantic analysis of an operation state on each operation state data local time sequence in the sequence of operation state data local time sequences to obtain a sequence of operation state local time-domain associated semantic feature vectors, comprises: and performing feature extraction on the sequence of the operation state data local time sequence by using an operation state time sequence feature extractor based on a deep neural network model to obtain the sequence of the operation state local time domain associated semantic feature vector.
3. The intelligent control method of the lithium electric air compressor according to claim 2, wherein the operation state time sequence feature extractor based on the deep neural network model is an operation state time sequence feature extractor based on a convolutional neural network model.
4. The intelligent control method of a lithium electric air compressor according to claim 3, wherein performing full-time domain operation state time sequence semantic association analysis on the sequence of operation state local time sequence semantic association feature vectors to obtain a monitored lithium electric air compressor operation state time sequence semantic association feature vector as a monitored lithium electric air compressor operation state time sequence semantic association feature comprises: and the sequence of the operation state local time domain associated semantic feature vectors passes through an operation state time sequence associated feature extractor based on an LSTM model to obtain the operation state time sequence semantic associated feature vector of the monitored lithium air compressor as the operation state time sequence semantic associated feature of the monitored lithium air compressor.
5. The intelligent control method of a lithium-ion air compressor according to claim 4, wherein determining whether an abnormality exists in an operation state based on the time sequence semantic association characteristic of the operation state of the monitored lithium-ion air compressor, and determining whether to suspend the monitored lithium-ion air compressor and issue an early warning prompt, comprises:
Passing the time sequence semantic association feature vector of the operation state of the monitored lithium-ion air compressor through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the operation state is abnormal or not;
And responding to the classification result that the running state is abnormal, suspending the monitored lithium battery air compressor and sending out an early warning prompt.
6. The intelligent control method of a lithium electric air compressor according to claim 5, wherein the passing the monitored time sequence semantic association feature vector of the operation state of the lithium electric air compressor through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the operation state is abnormal or not, and the method comprises the following steps:
Performing full-connection coding on the operation state time sequence semantic association characteristic vector of the monitored lithium air compressor by using a full-connection layer of the classifier to obtain a classification characteristic vector of the operation state time sequence semantic association coding of the monitored lithium air compressor;
And inputting the time sequence semantic association coding classification feature vector of the running state of the monitored lithium-ion air compressor into a Softmax classification function of the classifier to obtain the classification result.
7. The intelligent control method of a lithium electric air compressor according to claim 6, further comprising the training step of: the method is used for training the operation state time sequence feature extractor based on the convolutional neural network model, the operation state time sequence associated feature extractor based on the LSTM model and the classifier.
8. The intelligent control method of a lithium electric air compressor according to claim 7, wherein the training step comprises:
Acquiring training data, wherein the training data comprises a time sequence of training operation state data of a monitored lithium battery air compressor in a preset time period, and whether an abnormal true value exists in the operation state;
Performing sequence segmentation on the time sequence of the training operation state data based on a preset time scale to obtain a sequence of a local time sequence of the training operation state data;
performing feature extraction on the sequence of the training operation state data local time sequence by using the operation state time sequence feature extractor based on the convolutional neural network model to obtain a sequence of training operation state local time domain associated semantic feature vectors;
The sequence of the training operation state local time domain associated semantic feature vectors passes through the operation state time sequence associated feature extractor based on the LSTM model to obtain the training monitored lithium battery air compressor operation state time sequence semantic associated feature vectors;
Passing the training monitored lithium battery air compressor running state time sequence semantic association feature vector through the classifier to obtain a classification loss function value;
Training the operation state time sequence feature extractor based on the convolutional neural network model, the operation state time sequence associated feature extractor based on the LSTM model and the classifier based on the classification loss function value and through back propagation of gradient descent, wherein the operation state time sequence semantic associated feature vector of the lithium air compressor to be trained is optimized each time the operation state time sequence semantic associated feature vector of the lithium air compressor to be trained is iterated through the classifier in classification regression.
9. The intelligent control method of a lithium battery air compressor according to claim 8, wherein passing the training monitored lithium battery air compressor operation state timing semantic association feature vector through the classifier to obtain a classification loss function value comprises:
passing the training monitored lithium battery air compressor running state time sequence semantic association feature vector through the classifier to obtain a training classification result;
And calculating a cross entropy loss function value between the training classification result and a true value of whether the running state is abnormal or not as the classification loss function value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410119702.5A CN117905683B (en) | 2024-01-29 | 2024-01-29 | Intelligent control method for lithium battery air compressor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410119702.5A CN117905683B (en) | 2024-01-29 | 2024-01-29 | Intelligent control method for lithium battery air compressor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117905683A true CN117905683A (en) | 2024-04-19 |
| CN117905683B CN117905683B (en) | 2024-10-18 |
Family
ID=90681984
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410119702.5A Active CN117905683B (en) | 2024-01-29 | 2024-01-29 | Intelligent control method for lithium battery air compressor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117905683B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118468558A (en) * | 2024-05-10 | 2024-08-09 | 中电华创(苏州)电力技术研究有限公司 | Heating surface tube fatigue analysis method and system based on deep peak regulation of power plants |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7403850B1 (en) * | 2005-09-29 | 2008-07-22 | Dynalco Controls Corporation | Automated fault diagnosis method and system for engine-compressor sets |
| US20100211192A1 (en) * | 2009-02-17 | 2010-08-19 | Honeywell International Inc. | Apparatus and method for automated analysis of alarm data to support alarm rationalization |
| CN102072144A (en) * | 2011-03-11 | 2011-05-25 | 大连大学 | Vibration and noise online monitoring and fault diagnosis system of scroll compressor |
| CN113095367A (en) * | 2021-03-16 | 2021-07-09 | 华中科技大学 | Compressor fault diagnosis method based on deep reinforcement learning |
| CN116130721A (en) * | 2023-04-11 | 2023-05-16 | 杭州鄂达精密机电科技有限公司 | Status diagnostic system and method for hydrogen fuel cell |
| CN116627708A (en) * | 2023-07-24 | 2023-08-22 | 湖南惟储信息技术有限公司 | Storage fault analysis system and method thereof |
| CN116772944A (en) * | 2023-08-25 | 2023-09-19 | 克拉玛依市燃气有限责任公司 | Intelligent monitoring system and method for gas distribution station |
| CN116992226A (en) * | 2023-06-16 | 2023-11-03 | 青岛西格流体技术有限公司 | Water pump motor fault detection method and system |
| CN117419828A (en) * | 2023-12-18 | 2024-01-19 | 南京品傲光电科技有限公司 | New energy battery temperature monitoring method based on optical fiber sensor |
| CN117454290A (en) * | 2023-10-26 | 2024-01-26 | 新疆工程学院 | Intelligent real-time data collection and analysis system for boiler heating |
-
2024
- 2024-01-29 CN CN202410119702.5A patent/CN117905683B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7403850B1 (en) * | 2005-09-29 | 2008-07-22 | Dynalco Controls Corporation | Automated fault diagnosis method and system for engine-compressor sets |
| US20100211192A1 (en) * | 2009-02-17 | 2010-08-19 | Honeywell International Inc. | Apparatus and method for automated analysis of alarm data to support alarm rationalization |
| CN102072144A (en) * | 2011-03-11 | 2011-05-25 | 大连大学 | Vibration and noise online monitoring and fault diagnosis system of scroll compressor |
| CN113095367A (en) * | 2021-03-16 | 2021-07-09 | 华中科技大学 | Compressor fault diagnosis method based on deep reinforcement learning |
| CN116130721A (en) * | 2023-04-11 | 2023-05-16 | 杭州鄂达精密机电科技有限公司 | Status diagnostic system and method for hydrogen fuel cell |
| CN116992226A (en) * | 2023-06-16 | 2023-11-03 | 青岛西格流体技术有限公司 | Water pump motor fault detection method and system |
| CN116627708A (en) * | 2023-07-24 | 2023-08-22 | 湖南惟储信息技术有限公司 | Storage fault analysis system and method thereof |
| CN116772944A (en) * | 2023-08-25 | 2023-09-19 | 克拉玛依市燃气有限责任公司 | Intelligent monitoring system and method for gas distribution station |
| CN117454290A (en) * | 2023-10-26 | 2024-01-26 | 新疆工程学院 | Intelligent real-time data collection and analysis system for boiler heating |
| CN117419828A (en) * | 2023-12-18 | 2024-01-19 | 南京品傲光电科技有限公司 | New energy battery temperature monitoring method based on optical fiber sensor |
Non-Patent Citations (1)
| Title |
|---|
| 张洁 等: "大数据驱动的智能车间运行分析与决策方法体系", 计算机集成制造系统, no. 5, 15 May 2016 (2016-05-15), pages 60 - 68 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118468558A (en) * | 2024-05-10 | 2024-08-09 | 中电华创(苏州)电力技术研究有限公司 | Heating surface tube fatigue analysis method and system based on deep peak regulation of power plants |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117905683B (en) | 2024-10-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zaher et al. | Online wind turbine fault detection through automated SCADA data analysis | |
| EP3055747B1 (en) | Correlation and annotation of time series data sequences to extracted or existing discrete data | |
| KR101955305B1 (en) | Gas turbine sensor failure detection utilizing a sparse coding methodology | |
| JP5364530B2 (en) | Equipment state monitoring method, monitoring system, and monitoring program | |
| US9483049B2 (en) | Anomaly detection and diagnosis/prognosis method, anomaly detection and diagnosis/prognosis system, and anomaly detection and diagnosis/prognosis program | |
| EP2869153A1 (en) | Health management system, fault diagnosis system, health management method, and fault diagnosis method | |
| EP3055746B1 (en) | Correlation and annotation of time series data sequences to extracted or existing discrete data | |
| CN118504794B (en) | Intelligent fault diagnosis system of electric spark forming machine | |
| CN117905683B (en) | Intelligent control method for lithium battery air compressor | |
| CN110469461B (en) | Fracture estimation method and device for fan toothed belt and readable storage medium | |
| CN117151684A (en) | Wind power fan data analysis early warning method, system, device and readable storage medium | |
| CN117879168A (en) | Real-time early warning system of thermal power station based on multimode fuses | |
| CN116562158A (en) | Remaining Life Estimation Method for Aeroengine Airway Components Based on Interpretable Attention Mechanism | |
| CN118376936A (en) | Intelligent diagnosis method and system for lithium battery state | |
| CN116502072A (en) | Robust fault diagnosis method for key components of wind generating set under complex variable working conditions | |
| Tolani et al. | Anomaly detection in aircraft gas turbine engines | |
| Zhang et al. | Review of remaining useful life prediction using support vector machine for engineering assets | |
| CN117807155B (en) | Method, equipment and storage medium for generating multi-dimensional early warning prompt information | |
| US20180087489A1 (en) | Method for windmill farm monitoring | |
| CN118400835A (en) | LED driving power supply fault early warning method and system based on deep learning | |
| CN111524336A (en) | Generator set early warning method and system | |
| CN116863664A (en) | Real-time monitoring method and system for gas equipment | |
| Losi et al. | Autoregressive Bayesian hierarchical model to predict gas turbine degradation | |
| CN115423051A (en) | Power inspection data mining, equipment status classification and risk prediction system and method | |
| CN118133947B (en) | AI processing method and system for air compressor energy system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |