CN115343623A - Online detection method and device for electrochemical energy storage battery fault - Google Patents
Online detection method and device for electrochemical energy storage battery fault Download PDFInfo
- Publication number
- CN115343623A CN115343623A CN202211055156.0A CN202211055156A CN115343623A CN 115343623 A CN115343623 A CN 115343623A CN 202211055156 A CN202211055156 A CN 202211055156A CN 115343623 A CN115343623 A CN 115343623A
- Authority
- CN
- China
- Prior art keywords
- battery
- fault
- image data
- ray image
- detection model
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/378—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC] specially adapted for the type of battery or accumulator
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2223/00—Investigating materials by wave or particle radiation
- G01N2223/40—Imaging
- G01N2223/401—Imaging image processing
-
- 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
Abstract
The invention discloses an electrochemical energy storage battery fault on-line detection method and a device, wherein the method comprises the following steps: collecting battery X-ray image data, analyzing the battery X-ray image data, and generating a battery state label; inputting the battery X-ray image data and the battery state label into an initial machine learning model for training to generate an X-ray imaging detection model; acquiring charge and discharge external characteristic data corresponding to the battery state label, inputting the battery state label and the charge and discharge external characteristic data into an X-ray imaging detection model for training, and generating a battery fault state detection model; and detecting the current battery operation fault by using the battery fault state detection model to generate an electrochemical energy storage battery fault detection result. The method ensures the coupling of internal and external mechanisms of the battery fault detection, and improves the intuitiveness and the accuracy of the battery fault detection analysis in the operating state of the electrochemical energy storage system.
Description
Technical Field
The invention relates to the technical field of battery fault detection, in particular to an electrochemical energy storage battery fault online detection method and device.
Background
Currently, for fault detection of an energy storage battery in an operating state, most external characteristic variables obtained by monitoring and calculating current, voltage, temperature, SOC (state of charge), SOH (storage battery capacity, health degree and performance state) and the like of a battery core, a module and the like through sensors reflect the actual state of the battery indirectly, however, the monitoring quantity of various external characteristics cannot well represent the characteristics of internal material change, battery structure abnormity and the like of the battery, prediction judgment and early prevention of abnormal conditions cannot be performed, the current detection mode of an off-line battery cannot reflect various change characteristics of internal mechanisms and structures of the battery in the operating state practically, and the actual application value of the battery detection technology cannot be fully exerted.
The fault detection of the current energy storage battery has the following defects: only the situation that the battery is taken to a laboratory for X-ray fault detection and analysis in an off-line state is considered, and the actual running state of the battery is not considered; the conventional electrochemical energy storage system can detect the battery fault only through external characteristics such as external current, voltage and the like in the operating state, and no way is provided for considering the fault factors that the actual internal structure and the external characteristics of the battery cannot be reflected; the actual conditions inside the operating batteries and the changes in the internal structure inside the electrochemical energy storage container cannot be directly and intuitively seen.
Disclosure of Invention
Therefore, the technical problem to be solved by the invention is to overcome the defect that the internal faults of a plurality of batteries cannot be found and processed in advance due to the fact that the battery fault detection in the electrochemical energy storage container is mostly judged and analyzed based on the external characteristic monitoring quantities of the batteries such as current, voltage, temperature and the like and the internal structure change characteristics of the operating batteries cannot be clearly and intuitively displayed and analyzed, so that the on-line detection method and the device for the faults of the electrochemical energy storage batteries are provided.
The embodiment of the invention provides an electrochemical energy storage battery fault online detection method, which comprises the following steps:
collecting battery X-ray image data, analyzing the battery X-ray image data, and generating a battery state label;
inputting the battery X-ray image data and the battery state label into an initial machine learning model for training to generate an X-ray imaging detection model;
acquiring charging and discharging external characteristic data corresponding to the battery state label, inputting the battery state label and the charging and discharging external characteristic data into an X-ray imaging detection model for training, and generating a battery fault state detection model;
and detecting the current battery operation fault by using the battery fault state detection model to generate an electrochemical energy storage battery fault detection result.
According to the electrochemical energy storage battery fault on-line detection method provided by the invention, the coupling of internal and external mechanisms of battery fault detection is ensured through the combined analysis of the battery X-ray image data and the charging and discharging external characteristic data, so that the analysis result is more visual and accurate, the automatic intelligent analysis of the fault detection is realized by using the battery fault state detection model, the internal characteristics of the battery are reflected through the battery X-ray image data, the original static off-line detection technology is used for on-line dynamic detection from the change of the internal characteristics of the battery, and the intuitiveness and the accuracy of the battery fault detection analysis in the operation state of the electrochemical energy storage system are improved to a certain extent.
Optionally, analyzing the battery X-ray image data to generate a battery status label, comprising:
carrying out image processing on the battery X-ray image data to generate processed X-ray image data;
acquiring expert evaluation results corresponding to the processed X-ray image data, extracting the same battery states in the expert evaluation results, and determining a plurality of weight probabilities based on the number of the same battery states;
and sequencing the multiple weight probabilities, and selecting the battery state corresponding to the maximum weight probability as a battery state label.
Optionally, inputting the battery X-ray image data and the battery state label into an initial machine learning model for training, and generating an X-ray imaging detection model, including:
inputting the battery X-ray image data into an initial machine learning model to generate an image analysis result;
and comparing the image analysis result with the battery state label, and generating an X-ray imaging detection model when the image analysis result is consistent with the battery state label.
Optionally, inputting the battery state label and the charging and discharging external characteristic data into an X-ray imaging detection model for training, and generating a battery fault state detection model, including:
inputting the battery state label into an X-ray imaging detection model to generate external characteristic monitoring amount change data;
and comparing the difference between the external characteristic monitoring quantity change data and the charging and discharging external characteristic data with a preset external monitoring range, and generating a battery fault state detection model when the difference between the external characteristic monitoring quantity change data and the charging and discharging external characteristic data conforms to the preset external monitoring range.
Optionally, the detecting a current battery operating fault by using the battery fault state detection model to generate a fault detection result of the electrochemical energy storage battery, including:
acquiring current X-ray image data, inputting the X-ray image data into an X-ray imaging detection model, and generating a battery internal defect type;
inputting the internal defect type of the battery into a battery fault state detection model to generate external characteristic monitoring quantity change data;
acquiring current battery external characteristic data corresponding to the battery internal defect type, comparing the external characteristic monitoring quantity change data with the current battery external characteristic data, and generating an electrochemical energy storage battery fault detection result based on the comparison result.
In a second aspect of the present application, there is also provided an online detection device for failure of an electrochemical energy storage cell, comprising:
the analysis module is used for acquiring the X-ray image data of the battery, analyzing the X-ray image data of the battery and generating a battery state label;
the training module is used for inputting the battery X-ray image data and the battery state label into an initial machine learning model for training to generate an X-ray imaging detection model;
the acquisition module is used for acquiring charge and discharge external characteristic data corresponding to the battery state label, inputting the battery state label and the charge and discharge external characteristic data into an X-ray imaging detection model for training, and generating a battery fault state detection model;
and the detection module is used for detecting the current battery operation fault by using the battery fault state detection model to generate an electrochemical energy storage battery fault detection result.
Optionally, an analysis module comprising:
the processing unit is used for carrying out image processing on the battery X-ray image data and generating processed X-ray image data;
the extraction unit is used for acquiring expert evaluation results corresponding to the processed X-ray image data, extracting the same battery state in the expert evaluation results, and determining a plurality of weight probabilities based on the number of the same battery state;
and the sequencing unit is used for sequencing the weight probabilities and selecting the battery state corresponding to the maximum weight probability as the battery state label.
Optionally, a training module comprising:
the generating unit is used for inputting the battery X-ray image data into the initial machine learning model and generating an image analysis result;
and the comparison unit is used for comparing the image analysis result with the battery state label and generating an X-ray imaging detection model when the image analysis result is consistent with the battery state label.
Optionally, the obtaining module includes:
the transmission unit is used for inputting the battery state label into the X-ray imaging detection model and generating external characteristic monitoring quantity change data;
and the judging unit is used for comparing the difference value between the external characteristic monitoring quantity change data and the charging and discharging external characteristic data with a preset external monitoring range, and generating a battery fault state detection model when the difference value between the external characteristic monitoring quantity change data and the charging and discharging external characteristic data conforms to the preset external monitoring range.
Optionally, the detection module comprises:
the acquisition unit is used for acquiring current X-ray image data, inputting the X-ray image data into an X-ray imaging detection model and generating a battery internal defect type;
the determining unit is used for inputting the internal defect type of the battery into the battery fault state detection model and generating external characteristic monitoring quantity change data;
and the detection unit is used for acquiring current battery external characteristic data corresponding to the battery internal defect type, comparing the external characteristic monitoring amount change data with the current battery external characteristic data, and generating an electrochemical energy storage battery fault detection result based on the comparison result.
In a third aspect of the present application, a computer device is also presented, comprising a processor and a memory, wherein the memory is used for storing a computer program, the computer program comprising a program, and the processor is configured to invoke the computer program to perform the method of the first aspect.
In a fourth aspect of the present application, the present invention provides a computer-readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method of the first aspect.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flow chart of an electrochemical energy storage cell fault on-line detection method in embodiment 1 of the present invention;
fig. 2 is a schematic diagram of the electrochemical energy storage container battery online fault detection system based on the X-ray imaging technology in embodiment 1 of the present invention;
FIG. 3 is a flowchart of step S101 in embodiment 1 of the present invention;
FIG. 4 is a flowchart of step S102 in embodiment 1 of the present invention;
FIG. 5 is a flowchart of step S103 in embodiment 1 of the present invention;
FIG. 6 is a flowchart of step S104 in embodiment 1 of the present invention;
fig. 7 is a schematic block diagram of an electrochemical energy storage cell failure online detection device in embodiment 2 of the present invention;
fig. 8 is a schematic block diagram of the analysis module 71 according to embodiment 2 of the present invention;
FIG. 9 is a schematic block diagram of a training module 72 according to embodiment 2 of the present invention;
fig. 10 is a schematic block diagram of the obtaining module 73 in embodiment 2 of the present invention;
fig. 11 is a schematic block diagram of the detection module 74 in embodiment 2 of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Example 1
The embodiment provides an online detection method for electrochemical energy storage battery faults, as shown in fig. 1, including:
s101, collecting battery X-ray image data, analyzing the battery X-ray image data, and generating a battery state label.
Wherein, as shown in fig. 2, considering the internal defect change of the battery in the electrochemical energy storage container under the operating condition and the fault problem that the structural change may bring, through combining portable X high frequency ray imaging technique, rationally combined the sealed environmental characteristics who is fit for carrying out X ray detection again in the electrochemical energy storage container, the customization carries out track design and automatic X ray emission collection scheme and sets for, wherein, remote control X high frequency ray machine's structure specifically does with the installation: firstly, at the beginning of container design, the internal design of a battery module is constrained, the modules are required to be arranged in a non-multi-row overlapping manner, each battery cell can be shot by X high-frequency rays, and an open-type module plug box design is adopted as much as possible; selecting a high-frequency X-ray machine and a corresponding X-ray detector which are suitable for use based on a size structure in the container, the size of the battery module and the type of the battery core; designing the tracks of the X high-frequency ray machine and the detector in the container to ensure that the X high-frequency ray machine and the detector can be mutually matched and moved to proper positions of each module to acquire the X-ray image of the battery; and (4) carrying out installation wiring and system server deployment on the four X high-frequency ray machines and matched detectors.
Furthermore, after the container system is powered on and operated, the X-ray generation and X-ray imaging and image data acquisition work of the battery in an operation state can be started, and the connectivity test of network communication in the container is carried out on the X-ray acquisition and analysis system, so that the normal operation of the system is ensured; setting parameters such as moving tracks, moving speeds, acquisition periods, frequencies and the like of the X-ray machine and the detector in the system; and remotely controlling the X high-frequency ray machine and the X ray detector to perform manual or automatic movement and acquisition work of X-ray images, and sequentially obtaining the X-ray images of different batteries from the detector.
And S102, inputting the battery X-ray image data and the battery state label into an initial machine learning model for training to generate an X-ray imaging detection model.
And S103, acquiring the charging and discharging external characteristic data corresponding to the battery state label, inputting the battery state label and the charging and discharging external characteristic data into the X-ray imaging detection model for training, and generating a battery fault state detection model.
Specifically, the external characteristics of the battery during charging and discharging are changed due to internal defects of the battery, the charging and discharging external characteristic data (such as parameters of current, voltage, SOC, SOH, temperature and the like) corresponding to the internal defects of the battery (namely, the battery state labels) are obtained in advance, and based on the charging and discharging external characteristic data list corresponding to the internal defects of the battery and the internal defects of the battery, model training is performed by using the charging and discharging external characteristic data to generate a battery fault state detection model.
Or comprehensively analyzing the battery X-ray image and the charging and discharging external characteristic data, wherein the charging and discharging external characteristic data have threshold ranges under different working conditions due to the fact that the battery X-ray image has a judgment result (namely a battery state label), and a battery fault exists if any one charging and discharging external characteristic data exceeds the standard; if the judgment result of the X-ray image of the battery is normal, but the temperature is always high or the temperature rises particularly fast, or the voltage and the current have sudden changes, the battery fault exists, and then whether the battery is in a fault state or abnormal or not needs to be analyzed by combining the charging and discharging external characteristic data with the judgment result of the X-ray image of the battery; furthermore, the battery fault state comprehensive analysis result obtained after the charging and discharging external characteristic data (such as parameters such as current, voltage, SOC, SOH, temperature and the like) of the battery and the battery state label are combined is added into a training model step by step, so that fusion analysis judgment of the machine learning model on the internal characteristic of the battery X-ray image and the external characteristic of the battery external monitoring quantity is realized, and when the matching degree of the judgment result and the expert judgment result is more than 95%, a battery fault state detection model is generated; and inputting the current X-ray image into a battery fault state detection model to generate a fault detection result of the electrochemical energy storage battery.
And S104, detecting the current battery operation fault by using the battery fault state detection model to generate a fault detection result of the electrochemical energy storage battery.
Specifically, after the machine learning model training is completed, the machine learning model can be gradually separated from an expert knowledge base, and the X-ray image and the current fault state of the battery do not need to be analyzed and judged subjectively by expert personnel, so that automatic internal and external characteristic analysis and fault diagnosis of the battery can be realized.
Further, when a battery failure occurs, automatic alarm and alarm information (namely, failure type, failure device and the like) are sent to inform operation and maintenance personnel to process the failed battery in time.
According to the online detection method for the faults of the electrochemical energy storage battery, the fault problems possibly caused by internal defect changes and structural changes of the battery in the electrochemical energy storage container in the running state are considered, a mobile X high-frequency ray imaging technology is combined, the environmental characteristics that the electrochemical energy storage container is internally sealed and is suitable for X-ray detection are reasonably combined, the track design and the setting of an automatic X-ray emission and acquisition scheme are customized, and the digitization of the internal fault detection of the battery in the container in the running state is realized; and through the combined analysis of the battery X-ray image data and the charging and discharging external characteristic data, the internal and external mechanism coupling of the battery fault detection is ensured, the analysis result is more visual and accurate, the automatic intelligent analysis of the fault detection is realized by utilizing a battery fault state detection model, the internal characteristics of the battery are reflected through the battery X-ray image data, the original static off-line detection technology is used for online dynamic detection starting from the change of the internal characteristics of the battery, and the intuitiveness and the accuracy of the battery fault detection analysis in the running state of the electrochemical energy storage system are improved to a certain extent.
Preferably, as shown in fig. 3, the step S101 of analyzing the battery X-ray image data to generate a battery status label includes:
s1011, image processing is performed on the battery X-ray image data to generate processed X-ray image data.
Specifically, image processing such as noise reduction processing and image enhancement processing is carried out on acquired X-ray image data of different batteries, the processed X-ray image data of different batteries at different time is stored in a local database, and an X-ray image can be selected from the local database to be checked and analyzed.
S1012, acquiring an expert evaluation result corresponding to the processed X-ray image data, extracting the same battery state in the expert evaluation result, and determining a plurality of weight probabilities based on the number of the same battery state.
The processed X-ray image of the battery is sent to operation and maintenance personnel and relevant experts of battery faults, the X-ray image of the battery is manually judged and analyzed, whether the battery has faults or not is analyzed through the X-ray image of the battery, for example, whether a battery diaphragm is damaged or not, whether a lithium analysis phenomenon exists or not exists in the case of a lithium battery or not is analyzed, whether faults and problems occur in the interior of the battery is judged, the judgment and analysis result comprises normal and faults, the faults are divided into faults such as abnormal diaphragm, lithium analysis, internal short circuit and the like, and the judgment and analysis result is stored in an expert knowledge base.
And S1013, sequencing the plurality of weight probabilities, and selecting the battery state corresponding to the maximum weight probability as the battery state label.
Specifically, statistical analysis is performed on expert evaluation results, expert analysis opinions and the same opinions of the X-ray image data of different batteries at different moments are summarized and given with weight probabilities, whether the battery is normal or fault is judged according to the weight probabilities, fault types are judged, corresponding analysis result labels (namely battery state labels) are marked on the X-ray image data of the batteries, and the battery state labels are as follows: normal/failure (separator abnormality/lithium precipitation/internal short circuit, etc.).
Preferably, as shown in fig. 4, in step S102, the inputting the battery X-ray image data and the battery state label into an initial machine learning model for training to generate an X-ray imaging detection model, includes:
and S1021, inputting the battery X-ray image data into the initial machine learning model to generate an image analysis result.
Specifically, the analysis results (namely battery state labels) of different X-ray images in the expert knowledge base are utilized to continuously and dynamically analyze and train the collected sample data of the X-ray images, and image analysis results recognized by machine learning are given.
S1022, comparing the image analysis result with the battery status flag, and generating the X-ray imaging detection model when the image analysis result matches the battery status flag.
Specifically, when the image analysis results corresponding to the X-ray images of more than one third of the batteries in the container in the full life cycle from the beginning of use to the retirement are compared with the battery state labels in the expert knowledge base, and the matching degree of the analysis results (namely the image analysis results) of the X-ray images of the batteries and the analysis judgment results (namely the battery state labels) given by the experts within one month reaches more than 95%, the initial machine learning model completes training, and the X-ray imaging detection model is generated.
Preferably, as shown in fig. 5, the step S103 of inputting the battery state label and the charge/discharge external characteristic data into the X-ray imaging detection model for training to generate a battery failure state detection model includes:
and S1031, inputting the battery state label into the X-ray imaging detection model to generate external characteristic monitoring amount change data.
And S1032, comparing the difference value between the external characteristic monitoring amount change data and the charging and discharging external characteristic data with a preset external monitoring range, and generating the battery fault state detection model when the difference value between the external characteristic monitoring amount change data and the charging and discharging external characteristic data conforms to the preset external monitoring range.
Specifically, when the difference between the external characteristic monitoring amount change data and the charge-discharge external characteristic data does not conform to the preset external monitoring range, the weight of the X-ray imaging detection model is adjusted, and training is performed again.
Preferably, as shown in fig. 6, the detecting a current battery operation fault by using the battery fault state detection model in step S104 to generate a fault detection result of the electrochemical energy storage battery includes:
s1041, collecting current X-ray image data, inputting the X-ray image data into the X-ray imaging detection model, and generating internal defect types (including internal impurities, positive and negative distortion, positive and negative short circuit, positive and negative fracture, diaphragm damage and the like) of the battery.
Specifically, the X-ray image is judged, and the corresponding battery internal defect type category is matched according to the image characteristics.
And S1042, inputting the internal defect type of the battery into the battery fault state detection model, and generating the external characteristic monitoring amount change data.
And S1043, acquiring current battery external characteristic data corresponding to the internal defect type of the battery, comparing the external characteristic monitoring amount change data with the current battery external characteristic data, and generating a fault detection result of the electrochemical energy storage battery based on a comparison result.
Specifically, as shown in fig. 2, after the internal battery internal defect type is determined according to the X-ray image, current battery external characteristic data (voltage, current, temperature, SOC, SOH, and other external characteristic data) transmitted by an in-box state detection system such as a PCS (process control system), a BMS (battery management system), and the like are collected, the external characteristic monitored quantity change data is compared with the current battery external characteristic data corresponding to the battery internal defect type, whether the value ranges and the change trends of the two are consistent or not is compared, and if the result is consistent or the situation is worse than the experimental result, it is indicated that the battery has an internal defect fault, resulting in external characteristics of the same level and more serious consequences; if the internal defect result obtained by X-ray analysis is consistent with the charging and discharging of a normal battery in terms of the external characteristic data of the charging and discharging operation of the battery, the observation is continuously carried out for three days, if the internal defect result is not abnormal, the internal defect of the battery is judged to be misjudged to be in a normal state, otherwise, the internal defect result is judged to be in a fault state if the internal defect result is abnormal.
Example 2
The present embodiment provides an apparatus for online detecting a fault of an electrochemical energy storage battery, as shown in fig. 7, including:
the analysis module 71 is configured to collect the battery X-ray image data, analyze the battery X-ray image data, and generate a battery status label.
Wherein, the trouble problem that battery internal defect under operating condition changes and the structural change probably brings in the electrochemistry energy storage container of considering, through combining portable X high frequency ray imaging technique, has rationally combined the interior environmental characteristics who seals and be fit for carrying out X ray detection again of electrochemistry energy storage container, and the customization carries out track design and automatic X ray emission collection scheme and sets for, and wherein, remote control X high frequency ray machine's structure specifically is with the installation: firstly, at the beginning of container design, the internal design of a battery module is constrained, the modules are required to be arranged in a non-multi-row overlapping manner, each battery cell can be shot by X high-frequency rays, and an open-type module plug box design is adopted as much as possible; selecting a high-frequency X-ray machine and a corresponding X-ray detector which are suitable for use based on the size structure in the container, the size of the battery module and the type of the battery core; designing the tracks of the X high-frequency ray machine and the detector in the container to ensure that the X high-frequency ray machine and the detector can be mutually matched and moved to proper positions of each module to acquire the X-ray image of the battery; and (4) carrying out installation wiring and system server deployment on the four X high-frequency ray machines and matched detectors.
Furthermore, after the container system is powered on to operate, the X-ray generation and X-ray imaging and image data acquisition work of the battery in an operating state can be started, and the connectivity test of network communication in the container is carried out on the X-ray acquisition and analysis system, so that the normal operation of the system is ensured; setting parameters such as moving tracks, moving speeds, acquisition periods, frequencies and the like of the X-ray machine and the detector in the system; and remotely controlling the X high-frequency ray machine and the X ray detector to perform manual or automatic movement and acquisition work of X-ray images, and sequentially obtaining the X-ray images of different batteries from the detector.
The training module 72 is configured to input the battery X-ray image data and the battery state label into an initial machine learning model for training, so as to generate an X-ray imaging detection model.
An obtaining module 73, configured to obtain charge and discharge external characteristic data corresponding to the battery state label, and input the battery state label and the charge and discharge external characteristic data into the X-ray imaging detection model for training to generate a battery fault state detection model.
Specifically, the external characteristics of the battery during charging and discharging are changed due to internal defects of the battery, the charging and discharging external characteristic data (such as parameters of current, voltage, SOC, SOH, temperature and the like) corresponding to the internal defects of the battery (namely, the battery state labels) are obtained in advance, and based on the charging and discharging external characteristic data list corresponding to the internal defects of the battery and the internal defects of the battery, model training is performed by using the charging and discharging external characteristic data to generate a battery fault state detection model.
Or comprehensively analyzing the battery X-ray image and the charging and discharging external characteristic data, wherein the charging and discharging external characteristic data have threshold ranges under different working conditions due to the fact that the battery X-ray image has a judgment result (namely a battery state label), and a battery fault exists if any one charging and discharging external characteristic data exceeds the standard; if the judgment result of the X-ray image of the battery is normal, but the temperature is always high or the temperature rises particularly fast, or the voltage and the current have sudden changes, the battery fault exists, and then whether the battery is in a fault state or abnormal or not needs to be analyzed by combining the charging and discharging external characteristic data with the judgment result of the X-ray image of the battery; furthermore, the battery fault state comprehensive analysis result obtained after the charging and discharging external characteristic data (such as parameters such as current, voltage, SOC, SOH, temperature and the like) of the battery and the battery state label are combined is added into a training model step by step, so that fusion analysis judgment of the machine learning model on the internal characteristic of the battery X-ray image and the external characteristic of the battery external monitoring quantity is realized, and when the matching degree of the judgment result and the expert judgment result is more than 95%, a battery fault state detection model is generated; and inputting the current X-ray image into the battery fault state detection model to generate a fault detection result of the electrochemical energy storage battery.
And the detecting module 74 is configured to detect a current battery operation fault by using the battery fault state detection model, and generate an electrochemical energy storage battery fault detection result.
Specifically, after the machine learning model training is completed, the expert knowledge base can be gradually separated, and the expert personnel do not need to subjectively analyze and judge the X-ray image and the current fault state of the battery, so that automatic internal and external battery characteristic analysis and fault diagnosis can be realized.
Further, when a battery fault occurs, automatic alarm and alarm information (namely fault type, fault device and the like) are sent to inform operation and maintenance personnel to process the fault battery in time.
The utility model provides an online detection device of electrochemistry energy storage battery trouble, through the combination analysis of battery X ray image data and charge-discharge external characteristics data, the internal and external mechanism coupling of battery fault detection has been ensured, make the analysis result more directly perceived accurate, and utilize battery fault state detection model to realize fault detection's automatic intelligent analysis, reflect battery internal feature through battery X ray image data, set out from battery internal feature change, static off-line detection technique with originally is used for online dynamic detection, battery fault detection analysis's under the electrochemistry energy storage system running state intuitionistic degree and the degree of accuracy have been promoted to a certain extent.
Preferably, the analysis module 71 includes:
a processing unit 711, configured to perform image processing on the battery X-ray image data to generate processed X-ray image data.
Specifically, image processing such as noise reduction processing and image enhancement processing is carried out on acquired X-ray image data of different batteries, the processed X-ray image data of different batteries at different time is stored in a local database, and an X-ray image can be selected from the local database to be checked and analyzed.
The extracting unit 712 is configured to obtain an expert evaluation result corresponding to the processed X-ray image data, extract the same battery state in the expert evaluation result, and determine a plurality of weight probabilities based on the number of the same battery state.
The processed X-ray image of the battery is sent to operation and maintenance personnel and relevant experts of battery faults, the X-ray image of the battery is judged and analyzed manually, whether the battery has faults or not is analyzed through the X-ray image of the battery, for example, whether a battery diaphragm is damaged or not, whether a lithium analysis phenomenon exists or not exists in a lithium battery or not is analyzed, whether faults and problems occur in the battery or not is judged, the judgment and analysis result comprises normality and faults, the faults are divided into faults such as abnormal diaphragm, lithium analysis, internal short circuit and the like, and the judgment and analysis result is stored in an expert knowledge base.
A sorting unit 713, configured to sort the plurality of weight probabilities, and select a battery state corresponding to the highest weight probability as the battery state label.
Specifically, statistical analysis is performed on expert evaluation results, expert analysis opinions and the same opinions of the X-ray image data of different batteries at different moments are summarized and given with weight probabilities, whether the battery is normal or fault is judged according to the weight probabilities, fault types are judged, corresponding analysis result labels (namely battery state labels) are marked on the X-ray image data of the batteries, and the battery state labels are as follows: normal/failure (separator abnormality/lithium precipitation/internal short circuit, etc.).
Preferably, the training module 72 includes:
a generating unit 721, configured to input the battery X-ray image data into the initial machine learning model, and generate an image analysis result.
Specifically, the analysis results (namely battery state labels) of different X-ray images in the expert knowledge base are utilized to continuously and dynamically analyze and train the collected sample data of the X-ray images and provide the image analysis results identified by machine learning.
A comparing unit 722, configured to compare the image analysis result with the battery status label, and generate the X-ray imaging detection model when the image analysis result matches the battery status label.
Specifically, when the image analysis results corresponding to the X-ray images of more than one third of the batteries in the container in the full life cycle from the beginning of use to the decommissioning are compared with the battery state labels in the expert knowledge base, and the matching degree between the analysis results (namely the image analysis results) of the X-ray images of the batteries and the analysis judgment results (namely the battery state labels) given by the experts in one month reaches more than 95%, the initial machine learning model finishes training, and the X-ray imaging detection model is generated.
Preferably, the obtaining module 73 includes:
and a transmission unit 731, configured to input the battery status label into the X-ray imaging detection model, and generate external characteristic monitoring amount change data.
A determining unit 732, configured to compare a difference between the external characteristic monitored quantity variation data and the charge/discharge external characteristic data with a preset external monitoring range, and generate the battery failure state detection model when the difference between the external characteristic monitored quantity variation data and the charge/discharge external characteristic data matches the preset external monitoring range.
Specifically, when the difference between the external characteristic monitoring amount change data and the charge-discharge external characteristic data does not conform to the preset external monitoring range, the weight of the X-ray imaging detection model is adjusted, and training is performed again.
Preferably, the detection module 74 includes:
and an acquisition unit 741, configured to acquire current X-ray image data, input the X-ray image data into the X-ray imaging detection model, and generate a battery internal defect type.
Specifically, the X-ray image is judged, and the corresponding battery internal defect type category is matched according to the image characteristics.
A determining unit 742 for inputting the internal defect type of the battery into the battery failure state detection model and generating the external characteristic monitoring amount change data.
The detecting unit 743 is configured to obtain current external characteristic data of the battery corresponding to the internal defect type of the battery, compare the external characteristic monitoring amount variation data with the current external characteristic data of the battery, and generate the fault detection result of the electrochemical energy storage battery based on the comparison result.
Specifically, after the internal battery internal defect type is judged according to an X-ray image, current battery external characteristic data (voltage, current, temperature, SOC, SOH and other external characteristic data) transmitted by an in-box state detection system such as a PCS (process control systems), a BMS (battery management system) and the like are collected, the external characteristic monitoring quantity change data and the current battery external characteristic data corresponding to the internal defect type of the battery are compared, whether the value ranges and the change trends of the external characteristic monitoring quantity change data and the current battery external characteristic data are consistent or not is compared, if the result is consistent or the situation is worse than the experimental result, the battery has internal defect faults, and the external characteristic with the same level and more serious consequences is caused; if the internal defect result obtained by X-ray analysis is consistent with the charging and discharging of a normal battery in terms of the external characteristic data of the charging and discharging operation of the battery, the observation is continuously carried out for three days, if the internal defect result is not abnormal, the internal defect of the battery is judged to be misjudged to be in a normal state, otherwise, the internal defect result is judged to be in a fault state if the internal defect result is abnormal.
Example 3
The present embodiment provides a computer device comprising a memory and a processor, wherein the processor is configured to read instructions stored in the memory to perform a method for online detection of a fault in an electrochemical energy storage battery in any of the above method embodiments.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Example 4
The present embodiments provide a computer-readable storage medium having stored thereon computer-executable instructions for performing a method for online detection of electrochemical energy storage cell failure in any of the above method embodiments. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk Drive (Hard Disk Drive, abbreviated as HDD), or a Solid State Drive (SSD); the storage medium may also comprise a combination of memories of the kind described above.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications derived therefrom are intended to be within the scope of the invention.
Claims (10)
1. An electrochemical energy storage battery fault online detection method is characterized by comprising the following steps:
collecting battery X-ray image data, analyzing the battery X-ray image data, and generating a battery state label;
inputting the battery X-ray image data and the battery state label into an initial machine learning model for training to generate an X-ray imaging detection model;
acquiring charge and discharge external characteristic data corresponding to the battery state label, inputting the battery state label and the charge and discharge external characteristic data into the X-ray imaging detection model for training, and generating a battery fault state detection model;
and detecting the current battery operation fault by using the battery fault state detection model to generate a fault detection result of the electrochemical energy storage battery.
2. The method of claim 1, wherein the analyzing the battery X-ray image data to generate a battery status label comprises:
performing image processing on the battery X-ray image data to generate processed X-ray image data;
acquiring an expert evaluation result corresponding to the processed X-ray image data, extracting the same battery state in the expert evaluation result, and determining a plurality of weight probabilities based on the number of the same battery state;
and sequencing the weight probabilities, and selecting the battery state corresponding to the maximum weight probability as the battery state label.
3. The method of claim 1, wherein the inputting the battery X-ray image data and the battery state label into an initial machine learning model for training to generate an X-ray imaging detection model comprises:
inputting the battery X-ray image data into the initial machine learning model to generate an image analysis result;
and comparing the image analysis result with the battery state label, and generating the X-ray imaging detection model when the image analysis result is consistent with the battery state label.
4. The method according to claim 1, wherein the step of inputting the battery state label and the charge-discharge external characteristic data into the X-ray imaging detection model for training to generate a battery failure state detection model comprises:
inputting the battery state label into the X-ray imaging detection model to generate external characteristic monitoring quantity change data;
comparing the difference between the external characteristic monitoring quantity change data and the charging and discharging external characteristic data with a preset external monitoring range, and generating the battery fault state detection model when the difference between the external characteristic monitoring quantity change data and the charging and discharging external characteristic data conforms to the preset external monitoring range.
5. The method according to claim 4, wherein the detecting the current battery operation fault by using the battery fault state detection model to generate the electrochemical energy storage battery fault detection result comprises:
acquiring current X-ray image data, inputting the X-ray image data into the X-ray imaging detection model, and generating a battery internal defect type;
inputting the type of the internal defect of the battery into the battery fault state detection model to generate the external characteristic monitoring amount change data;
and acquiring current battery external characteristic data corresponding to the battery internal defect type, comparing the external characteristic monitoring quantity change data with the current battery external characteristic data, and generating the electrochemical energy storage battery fault detection result based on the comparison result.
6. An electrochemical energy storage cell fault on-line detection device, comprising:
the analysis module is used for acquiring the X-ray image data of the battery, analyzing the X-ray image data of the battery and generating a battery state label;
the training module is used for inputting the battery X-ray image data and the battery state label into an initial machine learning model for training to generate an X-ray imaging detection model;
the acquisition module is used for acquiring the charging and discharging external characteristic data corresponding to the battery state label, inputting the battery state label and the charging and discharging external characteristic data into the X-ray imaging detection model for training, and generating a battery fault state detection model;
and the detection module is used for detecting the current battery operation fault by using the battery fault state detection model to generate a fault detection result of the electrochemical energy storage battery.
7. The device of claim 6, wherein the analysis module comprises:
the processing unit is used for carrying out image processing on the battery X-ray image data to generate processed X-ray image data;
the extraction unit is used for acquiring an expert evaluation result corresponding to the processed X-ray image data, extracting the same battery state in the expert evaluation result, and determining a plurality of weight probabilities based on the number of the same battery state;
and the sequencing unit is used for sequencing the multiple weight probabilities and selecting the battery state corresponding to the maximum weight probability as the battery state label.
8. The device of claim 6, wherein the training module comprises:
a generating unit, configured to input the battery X-ray image data into the initial machine learning model, and generate an image analysis result;
and the comparison unit is used for comparing the image analysis result with the battery state label and generating the X-ray imaging detection model when the image analysis result is consistent with the battery state label.
9. A computer device comprising a processor and a memory, wherein the memory is configured to store a computer program and the processor is configured to invoke the computer program to perform the steps of the method according to any of claims 1-5.
10. A computer-readable storage medium having stored thereon computer instructions, which, when executed by a processor, carry out the steps of the method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211055156.0A CN115343623B (en) | 2022-08-31 | 2022-08-31 | Online detection method and device for faults of electrochemical energy storage battery |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211055156.0A CN115343623B (en) | 2022-08-31 | 2022-08-31 | Online detection method and device for faults of electrochemical energy storage battery |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115343623A true CN115343623A (en) | 2022-11-15 |
| CN115343623B CN115343623B (en) | 2023-06-16 |
Family
ID=83956576
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211055156.0A Active CN115343623B (en) | 2022-08-31 | 2022-08-31 | Online detection method and device for faults of electrochemical energy storage battery |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115343623B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116699428A (en) * | 2023-08-08 | 2023-09-05 | 深圳市杰成镍钴新能源科技有限公司 | Defect detection method and device for retired battery |
| CN116706973A (en) * | 2023-08-09 | 2023-09-05 | 深圳康普盾科技股份有限公司 | Energy storage battery control method, system and medium based on multidimensional analysis |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111356930A (en) * | 2017-11-17 | 2020-06-30 | 皇家飞利浦有限公司 | Artificial intelligence enabled anatomical landmark localization |
| CN111929591A (en) * | 2020-08-21 | 2020-11-13 | 彩虹无线（北京）新技术有限公司 | Fault battery detection method, device, equipment and computer storage medium |
| US20210088591A1 (en) * | 2019-09-19 | 2021-03-25 | Samsung Electronics Co., Ltd. | Method and system for battery-management in devices |
| CN112881915A (en) * | 2021-01-18 | 2021-06-01 | 恒大新能源汽车投资控股集团有限公司 | Fault identification method and device for lithium battery and computer readable storage medium |
| CN113466706A (en) * | 2021-07-26 | 2021-10-01 | 上海伟翔众翼新能源科技有限公司 | Lithium battery echelon utilization residual life prediction method based on convolutional neural network |
| CN113533989A (en) * | 2021-06-09 | 2021-10-22 | 深圳先进技术研究院 | Battery detection system and battery detection method |
| CN113892149A (en) * | 2019-05-28 | 2022-01-04 | 皇家飞利浦有限公司 | Method for motion artifact detection |
| CN114047452A (en) * | 2022-01-13 | 2022-02-15 | 浙江玥视科技有限公司 | Method and device for determining cycle life of battery |
| CN114325400A (en) * | 2021-11-24 | 2022-04-12 | 北京百度网讯科技有限公司 | Method and device for determining remaining life of battery, electronic equipment and storage medium |
| CN114399660A (en) * | 2021-12-28 | 2022-04-26 | 北京百度网讯科技有限公司 | Fault type determination method and device, electronic equipment and storage medium |
-
2022
- 2022-08-31 CN CN202211055156.0A patent/CN115343623B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111356930A (en) * | 2017-11-17 | 2020-06-30 | 皇家飞利浦有限公司 | Artificial intelligence enabled anatomical landmark localization |
| CN113892149A (en) * | 2019-05-28 | 2022-01-04 | 皇家飞利浦有限公司 | Method for motion artifact detection |
| US20210088591A1 (en) * | 2019-09-19 | 2021-03-25 | Samsung Electronics Co., Ltd. | Method and system for battery-management in devices |
| CN111929591A (en) * | 2020-08-21 | 2020-11-13 | 彩虹无线（北京）新技术有限公司 | Fault battery detection method, device, equipment and computer storage medium |
| CN112881915A (en) * | 2021-01-18 | 2021-06-01 | 恒大新能源汽车投资控股集团有限公司 | Fault identification method and device for lithium battery and computer readable storage medium |
| CN113533989A (en) * | 2021-06-09 | 2021-10-22 | 深圳先进技术研究院 | Battery detection system and battery detection method |
| CN113466706A (en) * | 2021-07-26 | 2021-10-01 | 上海伟翔众翼新能源科技有限公司 | Lithium battery echelon utilization residual life prediction method based on convolutional neural network |
| CN114325400A (en) * | 2021-11-24 | 2022-04-12 | 北京百度网讯科技有限公司 | Method and device for determining remaining life of battery, electronic equipment and storage medium |
| CN114399660A (en) * | 2021-12-28 | 2022-04-26 | 北京百度网讯科技有限公司 | Fault type determination method and device, electronic equipment and storage medium |
| CN114047452A (en) * | 2022-01-13 | 2022-02-15 | 浙江玥视科技有限公司 | Method and device for determining cycle life of battery |
Non-Patent Citations (1)
| Title |
|---|
| 杨金堂;林孝毅;杨正群;柯昌美;: "废旧铅酸蓄电池的X射线图像识别分类研究", 机械设计与制造, no. 10, pages 156 - 158 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116699428A (en) * | 2023-08-08 | 2023-09-05 | 深圳市杰成镍钴新能源科技有限公司 | Defect detection method and device for retired battery |
| CN116706973A (en) * | 2023-08-09 | 2023-09-05 | 深圳康普盾科技股份有限公司 | Energy storage battery control method, system and medium based on multidimensional analysis |
| CN116706973B (en) * | 2023-08-09 | 2024-02-02 | 深圳康普盾科技股份有限公司 | Energy storage battery control method, system and medium based on multidimensional analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115343623B (en) | 2023-06-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115343623B (en) | Online detection method and device for faults of electrochemical energy storage battery | |
| CN111241154B (en) | Storage battery fault early warning method and system based on big data | |
| CN106324385A (en) | Testing system and method for battery management system | |
| CN107065720A (en) | Intelligent electric machine failure wave-recording early warning system | |
| CN115061049B (en) | Method and system for rapidly detecting UPS battery fault of data center | |
| CN111967620A (en) | Photovoltaic module diagnosis method, device, equipment and readable storage medium | |
| CN116629627A (en) | Intelligent detection system of power transmission on-line monitoring device | |
| CN113982850B (en) | Fan comprehensive health analysis method and system integrating high-low frequency signals | |
| CN110687851A (en) | Terminal operation monitoring system and method | |
| CN115037603A (en) | Diagnosis evaluation method, device and system of electricity consumption information acquisition equipment | |
| CN115943516A (en) | Vehicle battery unbalance detection method and device, electronic equipment and storage medium | |
| CN117331790A (en) | Machine room fault detection method and device for data center | |
| CN117474357A (en) | Power distribution room operation and maintenance management method and system based on deep learning | |
| CN111856299A (en) | Method, device and equipment for determining power supply state | |
| CN114152290B (en) | Method for diagnosing alternating current filter switch of convertor station | |
| CN112885049B (en) | Intelligent cable early warning system, method and device based on operation data | |
| CN114878960A (en) | Fault diagnosis method, storage medium, power acquisition terminal, and fault diagnosis system | |
| CN109698998A (en) | A kind of fault diagnosis system and its diagnostic method of sound system | |
| CN112540301A (en) | Battery detection method, device and storage medium | |
| CN117589444B (en) | Wind driven generator gear box fault diagnosis method based on federal learning | |
| CN114421041B (en) | Recycling method and device for high-power energy storage equipment | |
| CN117648612B (en) | Parallel battery pack fault detection method, device, electronic equipment and storage medium | |
| CN116413617A (en) | Test method of battery test system | |
| WO2023194833A1 (en) | Methods of operating electrochemical storage devices based on anomaly clustering, and software and systems including same | |
| CN114511417A (en) | Energy storage power station monitoring method and system and storage medium |
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 |