Method, device, system, storage medium and program product for diagnosing battery energy storage system fault
The BESS fault diagnosis model using multi-information source data input addresses the passive detection issue in existing systems, enabling early fault detection and proactive safety measures in BESS systems.
Patent Information
- Application Number
- PCT/CN2024/115218
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-08-28
- Publication Date
- 2026-03-05
AI Technical Summary
Existing methods for diagnosing battery energy storage system (BESS) faults are passive and fail to provide early detection of potential hazards, particularly thermal runaway in lithium-ion batteries, leading to potential loss and safety risks.
A method utilizing a BESS fault diagnosis model constructed through multi-information source data input, incorporating temperature, gas, sound, voltage, current, vibration, and pressure detection values, employing a hybrid model-driven and data-driven approach to provide early fault diagnosis.
Enables early detection of BESS faults, reducing hazard and facility loss by integrating multiple sensors and data sources for accurate fault prediction and proactive safety measures.
Smart Images

Figure CN2024115218_05032026_PF_FP_ABST
Abstract
Description
METHOD, DEVICE, SYSTEM, STORAGE MEDIUM AND PROGRAM PRODUCT FOR DIAGNOSING BATTERY ENERGY STORAGE SYSTEM FAULTFIELD
[0001] The present application relates to industrial technologies, and more particularly, to a method, device, system, computer-readable storage medium and computer program product for diagnosing battery energy storage system (BESS) fault.BACKGROUND
[0002] Battery Energy Storage System (BESS) is a complex solution that utilizes rechargeable batteries to store energy for future use. For example, lithium-ion batteries can be used as the rechargeable batteries in BESS, so the safety of the lithium-ion batteries became more and more important. The earlier to detect the failure or abnormality of the battery, the less loss of the facility.
[0003] Due to the high unit density and the chemical characteristic of the lithium-ion battery, the thermal runaway of the lithium-Ion battery happens rapidly, which infers the difficulties of early protection of the Lithium-ion battery.
[0004] At present, some mitigating strategies have been applied to the battery mechanical structure or battery management system (BMS) . For example, a safety vent is set on battery pack to reduce expressive pressure. BMS is used for over-charging / overvoltage protection. A temperature sensor is set to detect internal over-temperature of the battery. However, for the electrical or power distribution system, except some traditional method like fuses, few solutions have been found to improve the battery safety.
[0005] However, most of the traditional methods are passive methods, the passive methods focus on the mitigation when the thermal runaway is about to happen, in another word, the passive methods at most reduce the loss of hazards but do not save the battery or BESS.
[0006] Therefore, those skilled in the art are committed to finding other solutions for diagnosing BESS fault.SUMMARY
[0007] According to embodiments of the present application, a method, device, system, computer-readable storage medium and computer program product for diagnosing BESS fault are provided to early diagnose BESS fault.
[0008] The method for diagnosing BESS fault provided by embodiments of the present application includes: obtaining detection values from multiple different information sources configured for the BESS; inputting the detection values to a BESS fault diagnosis model constructed based on multi-information source data input, the types of the detection values are a subset of the types of the multi-information source data; and receiving a fault diagnosis result outputted by the BESS fault diagnosis model.
[0009] In an example, wherein the detection values comprises any combination of a temperature detection value, a gas detection value, a sound detection value, a voltage detection value, a current detection value, a vibration detection signal and a pressure detection signal; the multi-information source data comprises any combination of temperature data, gas data, sound data, voltage data, current data, vibration data and pressure data.
[0010] In an example, wherein different detection values are obtained from different sensors; or the voltage detection and / or the current detection value are obtained from a power distribution system of the BESS.
[0011] In an example, the BESS fault diagnosis model is constructed adopting a hybrid method of model-driven and data-driven.
[0012] In an example, wherein the BESS fault diagnosis model comprises multiple sub-models and a comprehensive evaluator, different sub-models have the same parameter types and different parameter reference values; the multiple sub-models comprise a normal sub-model and multiple abnormal sub-models, and different abnormal sub-models correspond to different faults; each sub-model is configured to generate parameter prediction values based on received detection values, and calculate and output parameter differences between the parameter prediction values and parameter reference values of the sub-model; the comprehensive evaluator is configured to perform comprehensive evaluation on the parameter differences outputted by all sub-models, and output a fault diagnosis result.
[0013] In an example, the BESS fault diagnosis model is a simplified model of a BESS mechanism model, and the BESS mechanism model is constructed adopting a hybrid method of model-driven and data-driven and based on multi-information source data input.
[0014] In an example, the BESS fault diagnosis model comprises multiple parameter sets, and different parameter sets have the same types of information source data and different value ranges of the information source data; the multiple parameter sets comprises a normal parameter set and multiple abnormal parameter sets, different abnormal parameter sets correspond different faults; each of the multiple parameter sets is generated by simulation using a BESS mechanism model, and the BESS mechanism model is constructed adopting a hybrid method of model-driven and data-driven and based on multi-information source data input; the BESS fault diagnosis model is configured to compare the detection values with each parameter set, if each of the detection values is within corresponding value range of information source data in a parameter set, output a fault diagnosis result corresponding to the parameter set.
[0015] The device for diagnosing BESS fault provided by embodiments of the present application includes: a first module, configured to obtain detection values from multiple different information sources configured for the BESS; and a second module, configured to input the detection values to a BESS fault diagnosis model constructed based on multi-information source data input, the types of the detection values are a subset of the types of the multi-information source data; and receive a fault diagnosis result outputted by the BESS fault diagnosis model.
[0016] The device for diagnosing BESS fault provided by embodiments of the present application includes: at least one memory, to store a computer program; and at least one processor, to call the computer program stored in the at least one memory to perform a method for diagnosing BESS fault mentioned above.
[0017] The system for diagnosing BESS fault provided by embodiments of the present application includes: a data detection system, configured to detect data of multiple information sources; and a device for diagnosing BESS fault mentioned above.
[0018] In an example, the system further includes: a fault processing system, configured to perform corresponding processing based on the fault diagnosis result.
[0019] The non-transitory computer-readable storage medium, on which a computer program is stored, the computer program is to be executed by a processor to implement a method for diagnosing BESS fault mentioned above.
[0020] The computer program product comprising a computer program, the computer program, when executed by a processor, implements the method mentioned above.
[0021] It can be seen from the above technical solutions that by introducing a BESS fault diagnosis model constructed based on multi-information source data input, and obtaining detection values from multiple different information sources configured for the BESS and inputting the detection values into the BESS fault diagnosis model, a fault diagnosis result capable of achieving early diagnosis of BESS fault can be obtained from the BESS fault diagnosis model. Thus the hazard can be avoided and the facility loss can be reduced.BRIEF DESCRIPTION OF THE DRAWINGS
[0022] For a better understanding of the present application, reference should be made to the Detailed Description below, in conjunction with the following drawings in which like reference numerals refer to corresponding parts throughout the figures.
[0023] Figure 1 is a schematic diagram illustrating time comparison of several protection methods.
[0024] Figure 2 is a flow diagram illustrating a method for diagnosing BESS fault according to embodiments of the present application.[0024.1][Corrected under Rule 26, 05.11.2024]Figure 3 is a schematic diagram illustrating a BESS fault diagnosis model according to an example of the present application.
[0025] Figure 4 is a schematic diagram illustrating a method for constructing a BESS fault diagnosis model according to an example of the present application.
[0026] Figure 5 is a schematic diagram illustrating a device for diagnosing BESS fault according to embodiments of the present application.
[0027] Figure 6 is a schematic diagram illustrating a system for diagnosing BESS fault according to an example of the present application.
[0028] Figure 7 is a schematic diagram illustrating another device for diagnosing BESS fault according to embodiments of the present application.
[0029] The reference numerals are as follows: DETAILED DESCRIPTION
[0030] In embodiments of this application, the inventor finds that the temperature-based protection might always be too late due to temperature will rise rapidly when thermal runaway happens. Therefore, the inventor attempts several other protection methods, for example, because short circuit or chemical process inside a battery will generate inorganic gas e.g., hydrogen or carbon dioxide, a gas-based protection method may be feasible. When the inorganic gas generates, it will cause abnormal sound, so a sound-based protection method may be feasible. In addition, when an overcharge fault occurs, abnormal voltage and current signals will appear, so a voltage-based protection method and a current-based protection method are also feasible.
[0031] Figure 1 is a schematic diagram illustrating time comparison of several protection methods. As shown in figure 1, curve 11 represents the un-reversible thermal runaway, the dashed line 10 indicates the latest timing for battery isolation, curve 12 represent a sound signal in a sound-based protection method, curve 13 represent a gas signal in a gas-based protection method, curve 14 represent a voltage signal in a voltage-based protection method. The peak value of each of curves 12-14 indicates that a thermal runaway will happen, and there is a time difference ΔT1, ΔT2, ΔT between two peak values of different curves or between a peak value and the latest timing for battery isolation. In can be seen, these protection methods seem to be able to achieve the early protection of the battery. However, these curves 12-14 are ideal curves. The inventor finds that the gas signal often has large error, the sound signal is easily disturbed, and the voltage signal is sometimes difficult to perceive.
[0032] In order to overcome these shortcomings and improve the accuracy of fault diagnosis, a multi-source information fusion based BESS fault diagnosis scheme is provided in embodiments of the present application.
[0033] Reference will now be made in detail to examples, which are illustrated in the accompanying drawings. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the present application. Also, the figures are illustrations of an example, in which assemblies shown in the figures are not necessarily essential for implementing the present application. In other instances, well-known assemblies, components, and circuits have not been described in detail so as not to unnecessarily obscure aspects of the examples.
[0034] Figure 2 is a flow diagram illustrating a method for diagnosing BESS fault according to embodiments of the present application. As shown in Figure 2, the method can include the following processes.
[0035] At block 201, detection values are obtained from multiple different information sources configured for the BESS.
[0036] At this block 201, the detection values may include any combination of a temperature detection value, a gas detection value, a sound detection value, a voltage detection value, a current detection value, a vibration detection signal, a pressure detection signal, and so on.
[0037] This detection values may be obtained from different sensors, for example, the temperature detection value is obtained from a temperature sensor, the gas detection value is obtained from a gas sensor, the sound detection value is obtained from a sound sensor, the voltage detection value is obtained from a voltage sensor, the current detection value is obtained from a current sensor, the vibration detection value is obtained from a vibration sensor, and the pressure detection value is obtained from a pressure sensor.
[0038] Furthermore, considering that the power distribution system of BESS can obtain voltage and current values, the voltage detection value and the current detection value may be obtained from the power distribution system. In another example, if the power distribution system of BESS can obtain other detection values, such as the temperature value, the gas value, the sound value, etc., which depends on the specific configuration of the power distribution system, other detection values may be obtained from the power distribution system.
[0039] At block 202, the detection values are inputted to a BESS fault diagnosis model constructed based on multi-information source data input, and a fault diagnosis result outputted by the BESS fault diagnosis model is received.
[0040] The multi-information source data may include any combination of temperature data, gas data, sound data, voltage data, current data, vibration data, pressure data, and so on. The types of the detection values are a subset of the types of the multi-information source data. That is to say, if the multi-information source data includes N types of data, then the detection values can include some or all of these N types of data, for that not included in the N types of data, the BESS fault diagnosis model can process it according to a default data. For example, if the multi-information source data includes temperature, gas, sound, voltage and current data, then the detection values can include temperature, gas, sound, voltage and current detection values, or include part of the temperature, gas, sound, voltage and current detection values, for instance, only include temperature, gas, voltage and current detection values, then the BESS fault diagnosis model may take default sound data as a sound detection value.
[0041] Afterwards, corresponding processing can be carried out based on the fault diagnosis result. For example, if there will occur an overcharge or over-discharge fault, a circuit breaker system can be informed to disconnect the charge or discharge circuit; if there will occur an thermal runaway fault, an isolating or blocking system may be informed to isolate or block corresponding battery; if there will occur an overheat fault, a cooling system can be used to cool the battery; if there will occur battery imbalance issue, a battery equalization system may be informed to replace corresponding battery to achieve the battery equalization; and the like.
[0042] In embodiments of the present application, the BESS fault diagnosis model may be achieved by different implementing manners, and the following are some of them.
[0043] The first one:
[0044] The BESS fault diagnosis model may be constructed adopting a hybrid method of model-driven and data-driven and based on multi-information source data input. Figure 3 is a schematic diagram illustrating a BESS fault diagnosis model according to an example of the present application. As shown in figure 3, the BESS fault diagnosis model 31includes multiple sub-models KF0~ KFn and a comprehensive evaluator CE.
[0045] Different sub-models may have the same parameter types and different parameter reference values, and the multiple sub-models include a normal sub-model KF0 and multiple abnormal sub-models KF1~ KFn, and different abnormal sub-models correspond to different faults. For example, the abnormal sub-models may include any combination of an overcharge sub-model, an over-discharge sub-model, a overheat sub-model, a thermal runaway sub-model, an accelerated degradation sub-model, and so on.
[0046] Each sub-model KF0~ KFn is configured to generate parameter prediction values based on received detection values I (v1, v2,..., vn) , and calculate and output parameter differences Δ (0) ~Δ (n) between the parameter prediction values and parameter reference values of the sub-model.
[0047] The comprehensive evaluator is configured to perform comprehensive evaluation on the parameter differences outputted by all sub-models, and output a fault diagnosis result.
[0048] In an example, the fault diagnosis result may include probability values p (0) ~p (n) of each corresponding fault and a possible time from the occurrence of the fault. In another example, the fault diagnosis result may include a result indicating whether there will be a fault and indicating the fault type when there will be a fault. In addition, the fault diagnosis result may further include a possible time from the occurrence of the fault.
[0049] In an example, the BESS fault diagnosis model 31 may be a simplified model of a BESS mechanism model 32, and the BESS mechanism model 32 is also constructed adopting a hybrid method of model-driven and data-driven and based on multi-information source data input (namely base on multi-source information fusion) .
[0050] Figure 4 is a schematic diagram illustrating a method for constructing a BESS fault diagnosis model according to an example of the present application. As shown in figure 4, the method may include the following processes.
[0051] At block 401, a BESS mechanism model is constructed adopting a hybrid method of model-driven and data-driven and based on multi-information source data input. The multi-information source data may include voltage data from a voltage sensor, current data from a current sensor, temperature data from a temperature sensor, gas data from a gas sensor, sound data from a sound sensor, vibration data from a vibration sensor and pressure data from a pressure sensor, and so on.
[0052] At block 402, the BESS mechanism model is used to simulate various fault states to obtain a value range of each of multiple information source data corresponding to each fault, and form parameter sets corresponding to different faults. For example, a parameter set corresponding to overcharge, a parameter set corresponding to over-discharge, a parameter set corresponding to overheat, a parameter set corresponding to thermal runaway, a parameter set corresponding to accelerated degradation, and so on. Different parameter sets correspond to different fault and have different value ranges of the multiple information source data.
[0053] In an example, the value ranges of the multiple information source data can be determined further according to some thresholds.
[0054] At block 403, a BESS fault diagnosis model as shown in figure 3 is constructed based on the BESS mechanism model. The BESS fault diagnosis model is a simplified model of the BESS mechanism model.
[0055] In the example, testing data may be obtained according to each parameter set obtained at block 402, and the testing data may be used to verify the BESS fault diagnosis model. For example, a testing data corresponding to overcharge may be obtained according to the parameter set corresponding to overcharge, and then the testing data can be taken as input data and inputs to the BESS fault diagnosis model, if a fault diagnosis result indicating that there will be a overcharge fault is outputted by the BESS fault diagnosis model, the BESS fault diagnosis model may be taken as usable.
[0056] The second one:
[0057] The multiple parameter sets can be directly used to diagnose BESS fault, namely the BESS fault diagnosis model may include multiple parameter sets obtained at above block 402. Different parameter sets have the same types of information source data and different value ranges of the information source data. The multiple parameter sets comprises a normal parameter set and multiple abnormal parameter sets, different abnormal parameter sets correspond different faults. The BESS fault diagnosis model is configured to compare the detection values with each parameter set, if each of the detection values is within corresponding value range of information source data in a parameter set, output a fault diagnosis result corresponding to the parameter set.
[0058] Regarding the first one and the second one, the fault diagnosis result can be verified by the BESS mechanism model 32.
[0059] The third one:
[0060] The BESS fault diagnosis model is a trained model, for example, the BESS fault diagnosis model is obtained by training a BESS fault training network constructed based on an artificial neural networks (ANN) and domain knowledge using raining sample pairs obtained from collected historical data. Each training sample pair comprises: historical detection values of multiple different information sources as an input example, and corresponding fault diagnosis model as a corresponding output example.
[0061] The method for diagnosing BESS fault in embodiments of the application is described in detail above, and the device for diagnosing BESS fault in embodiments of the application is described in detail below. The device for diagnosing BESS fault in embodiments of the application can be used to implement the method for diagnosing BESS fault in embodiments of the application. For details not disclosed in device embodiments of the application, please refer to the corresponding description in method embodiments of the application.
[0062] Figure 5 is a schematic diagram illustrating a device for diagnosing BESS fault according to embodiments of the present application. As shown in figure 5, the device may include a first module 501 and a second module 502.
[0063] The first module 501 is configured to obtain detection values from multiple different information sources configured for the BESS.
[0064] The second module 502 is configured to input the detection values to a BESS fault diagnosis model constructed based on multi-information source data input, and receive a fault diagnosis result outputted by the BESS fault diagnosis model.
[0065] The detection values may include any combination of a temperature detection value, a gas detection value, a sound detection value, a voltage detection value, a current detection value, a vibration detection signal and a pressure detection signal; the multi-information source data may include any combination of temperature data, gas data, sound data, voltage data, current data, vibration data and pressure data. The types of the detection values are a subset of the types of the multi-information source data.
[0066] The BESS fault diagnosis model may be achieved by different implementing manners, for example the implementing manners described in method embodiments.
[0067] Figure 6 is a schematic diagram illustrating a system for diagnosing BESS fault according to an example of the present application. As shown in figure 6, the device may include a data detection system 610, a fault diagnosis system 620 and a fault processing system 630.
[0068] The data detection system 610 is used to detect data of multiple information sources. For example, the data detection system 610 may include a voltage sensor 611, a current sensor 612, a temperature sensor 613, a gas sensor 614, a sound sensor 615, a vibration sensor 616, a pressure sensor 617, and so on.
[0069] The fault diagnosis system 620 may include a fault diagnosis module 621. In an example, the fault diagnosis system 620 may further include a BESS fault diagnosis model module 622. In another example, the fault diagnosis system 620 may further include a BESS mechanism model module 623, a parameter sets obtaining module 624. In another example, the BESS mechanism model module 623 and the parameter sets obtaining module 624 may be omitted.
[0070] The fault diagnosis module 621 is used to obtain detection values from the data detection system 610, input the detection values to a BESS fault diagnosis model constructed based on multi-information source data input, and receive a fault diagnosis result outputted by the BESS fault diagnosis model. The fault diagnosis module 622 is a specific implementation of the device for diagnosing BESS fault.
[0071] The BESS fault diagnosis model module 622 includes the BESS fault diagnosis model. The BESS fault diagnosis model is constructed based on multi-information source data input.
[0072] The BESS mechanism model module 623 includes a BESS mechanism model which is constructed adopting a hybrid method of model-driven and data-driven and based on multi-information source data input. The multi-information source data may include voltage data, current data, temperature data, gas data, sound data, vibration data, pressure data, and so on.
[0073] The parameter sets obtaining module 624 is used to obtain parameter sets corresponding to different faults. Each parameter set includes a set of value ranges of multiple information source data, and the value ranges of multiple information source data are determined by simulating various fault states using the BESS mechanism model. For example, the parameter sets may include a parameter set corresponding to overcharge 6241, a parameter set corresponding to over-discharge 6242, a parameter set corresponding to overheat 6243, a parameter set corresponding to thermal runaway 6244, a parameter set corresponding to accelerated degradation 6245, and so on. Different parameter sets correspond to different fault and have different value ranges of the multiple information source data. In an example, the parameter sets may be determined further according to some threshold TS1~TSm.
[0074] In the example, the BESS fault diagnosis model may be a simplified model of the BESS mechanism model. In another example, the BESS fault diagnosis model may be a model including the multiple parameter sets.
[0075] The fault processing system 630 is used to perform corresponding processing based on the fault diagnosis result. The fault processing system 630 may include a circuit breaker system 631, an isolating or blocking system 632, a cooling system 633, a battery equalization system 634, and the like.
[0076] In fact, the device for diagnosing BESS fault provided by this embodiment of the present application may be specifically implemented in various manners. For example, the device for diagnosing BESS fault may be compiled, by using an application programming interface that complies with a certain regulation, as a plug-in that is installed in an intelligent terminal, or may be encapsulated into an application program for a user to download and use.
[0077] When compiled as a plug-in, the device for diagnosing BESS fault may be implemented in various plug-in forms such as ocx, dll, and cab. The device for diagnosing BESS fault provided by this embodiment of the present application may also be implemented by using a specific technology, such as a Flash plug-in technology, a RealPlayer plug-in technology, an MMS plug-in technology, a MIDI staff plug-in technology, or an ActiveX plug-in technology.
[0078] The method for diagnosing BESS fault provided by this implementation manner of the present application may be stored in various storage mediums in an instruction storage manner or an instruction set storage manner. These storage mediums include, but are not limited to: a floppy disk, an optical disc, a DVD, a hard disk, a flash memory, a USB flash drive, a CF card, an SD card, an SDHC card, an MMC card, an SM card, a memory stick, and an xD card.
[0079] Moreover, it should be clear that an operating system operated in a computer can be made, not only by executing program code read by the computer from a storage medium, but also by using an instruction based on the program code, to implement some or all actual operations, so as to implement functions of any embodiment in the foregoing embodiments.
[0080] For example, figure 7 is a schematic diagram illustrating another device for diagnosing BESS fault according to embodiments of the present application. The device may be used to perform the method shown in figure 2 or figure 4, or to implement the device shown in figure 5. As shown in figure 7, the device may include at least one memory 71 and at least one processor 72. In addition, some other components may be included, such as communication port, input / output controller, network communication interface, etc. These components communicate through bus 73, etc.
[0081] At least one memory 71 is configured to store a computer program. In one example, the computer program can be understood to include various modules of the device shown in figure 5. In addition, at least one memory 71 may store an operating system or the like. Operating systems include but are not limited to: Android operating system, Symbian operating system, windows operating system, Linux operating system, etc.
[0082] At least one processor 72 is configured to call the computer program stored in at least one memory 71 to perform a method for diagnosing BESS fault described in embodiments of the present application. The processor 72 can be CPU, processing unit / module, ASIC, logic module or programmable gate array, etc. It can receive and send data through the communication port.
[0083] The I / O controller has a display and an input device, which is used to input, output and display relevant data.
[0084] It can be seen from the above technical solutions that by introducing a BESS fault diagnosis model constructed based on multi-information source data input, and obtaining detection values from multiple different information sources configured for the BESS and inputting the detection values into the BESS fault diagnosis model, a fault diagnosis result capable of achieving early diagnosis of BESS fault can be obtained from the BESS fault diagnosis model. Thus the hazard can be avoided and the facility loss can be reduced.
[0085] The technical solutions of the present application achieve the information fusion on different measurements to battery and extend the capability of conventional protection device.
[0086] It should be understood that, as used herein, unless the context clearly supports exceptions, the singular forms "a" ( "a", "an" , "the" ) are intended to include the plural forms. It should also be understood that, "and / or" used herein is intended to include any and all possible combinations of one or more of the associated listed items.
[0087] The number of the embodiments of the present application are only used for description, and do not represent the merits of the implementations.
[0088] Independent of the grammatical term usage, individuals with male, female or other gender identities are included within the term.
[0089] The foregoing description, for purpose of explanation, has been described with reference to specific examples. However, the illustrative discussions above are not intended to be exhaustive or to limit the present application to the precise forms disclosed. Many modifications and variations are possible in view of the above teachings. The examples were chosen and described in order to best explain the principles of the present application and its practical applications, to thereby enable others skilled in the art to best utilize the present application and various examples with various modifications as are suited to the particular use contemplated.
Claims
1.A method for diagnosing battery energy storage system (BESS) fault, characterized in that, comprising:obtaining detection values from multiple different information sources configured for the BESS;inputting the detection values to a BESS fault diagnosis model constructed based on multi-information source data input, the types of the detection values are a subset of the types of the multi-information source data; andreceiving a fault diagnosis result outputted by the BESS fault diagnosis model.2.The method for diagnosing BESS fault according to claim 1, characterized in that, wherein the detection values comprises any combination of a temperature detection value, a gas detection value, a sound detection value, a voltage detection value, a current detection value, a vibration detection signal and a pressure detection signal; the multi-information source data comprises any combination of temperature data, gas data, sound data, voltage data, current data, vibration data and pressure data.3.The method for diagnosing BESS fault according to claim 2, characterized in that, wherein different detection values are obtained from different sensors; orthe voltage detection and / or the current detection value are obtained from a power distribution system of the BESS.4.The method for diagnosing BESS fault according to any one of claims 1 to 3, characterized in that,the BESS fault diagnosis model is constructed adopting a hybrid method of model-driven and data-driven.5.The method for diagnosing BESS fault according to any one of claims 4, characterized in that, wherein the BESS fault diagnosis model comprises multiple sub-models and a comprehensive evaluator, different sub-models have the same parameter types and different parameter reference values; the multiple sub-models comprise a normal sub-model and multiple abnormal sub-models, and different abnormal sub-models correspond to different faults;each sub-model is configured to generate parameter prediction values based on received detection values, and calculate and output parameter differences between the parameter prediction values and parameter reference values of the sub-model;the comprehensive evaluator is configured to perform comprehensive evaluation on the parameter differences outputted by all sub-models, and output a fault diagnosis result.6.The method for diagnosing BESS fault according to claim 5, characterized in that, the BESS fault diagnosis model is a simplified model of a BESS mechanism model, and the BESS mechanism model is constructed adopting a hybrid method of model-driven and data-driven and based on multi-information source data input.7.The method for diagnosing BESS fault according to any one of claims 1 to 3, characterized in that,the BESS fault diagnosis model comprises multiple parameter sets, and different parameter sets have the same types of information source data and different value ranges of the information source data; the multiple parameter sets comprises a normal parameter set and multiple abnormal parameter sets, different abnormal parameter sets correspond different faults; each of the multiple parameter sets is generated by simulation using a BESS mechanism model, and the BESS mechanism model is constructed adopting a hybrid method of model-driven and data-driven and based on multi-information source data input;the BESS fault diagnosis model is configured to compare the detection values with each parameter set, if each of the detection values is within corresponding value range of information source data in a parameter set, output a fault diagnosis result corresponding to the parameter set.8.A device for diagnosing battery energy storage system (BESS) fault, characterized in that, comprising:a first module (501) , configured to obtain detection values from multiple different information sources configured for the BESS; anda second module (502) , configured to input the detection values to a BESS fault diagnosis model constructed based on multi-information source data input, the types of the detection values are a subset of the types of the multi-information source data; and receive a fault diagnosis result outputted by the BESS fault diagnosis model.9.A device for diagnosing battery energy storage system (BESS) fault, characterized in that, comprising:at least one memory, to store a computer program; andat least one processor, to call the computer program stored in the at least one memory to perform a method for diagnosing BESS fault according to any one of claims 1 to 7.10.A system for diagnosing battery energy storage system (BESS) fault, characterized in that, comprising:a data detection system (610) , configured to detect data of multiple information sources; anda device for diagnosing BESS fault according to claim 8 or 9.11.The system for diagnosing BESS fault according to claim 10, characterized in that, further comprising:a fault processing system (630) , configured to perform corresponding processing based on the fault diagnosis result.12.A non-transitory computer-readable storage medium, on which a computer program is stored, characterized in that, the computer program is to be executed by a processor to implement a method for diagnosing BESS fault according to any one of claims 1 to 7.13.A computer program product comprising a computer program, characterized in that, the computer program, when executed by a processor, implements the method for diagnosing BESS fault according to any one of claims 1 to 7.
Citation Information
Patent Citations
Method and apparatus for diagnosing faults of large-capacity battery energy storage system
CN107422266A
Energy storage power station battery operation fault diagnosis method and device, electronic equipment and medium
CN116699413A
Battery energy storage system fault prediction method and device, equipment and storage medium
CN118091423A
Subsystem-level model-based diagnosis
US20230259113A1