Fault diagnosis method and system for energy storage battery cabinet

Abstract

The invention relates to the technical field of energy storage batteries, and provides a fault diagnosis method and system for an energy storage battery cabinet, and the method comprises the steps: obtaining the internal resistance data of each battery string at a plurality of adjacent moments, and obtaining an internal resistance sequence; obtaining a basic voltage difference of each battery string in the energy storage battery cabinet and a real-time voltage difference of a plurality of continuous moments, and calculating a difference value between the real-time voltage difference and the basic voltage difference to obtain a voltage difference value sequence; acquiring temperature values of each battery monomer at a plurality of adjacent moments, and calculating temperature change rates according to the temperature values to obtain a temperature change rate sequence; through a fault diagnosis model, an aging degree index, a connection fault index and a temperature change rate abnormal index of the energy storage battery are obtained, weighted fusion is carried out, and after a fault level of the energy storage cabinet is obtained, an aging condition of each battery string, a connection fault condition of each single battery and a temperature change rate abnormal condition of each single battery are combined to obtain a fault level of the energy storage cabinet. Therefore, the reliability and the accuracy of fault diagnosis of the energy storage battery are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of energy storage batteries, and in particular relates to a fault diagnosis method and system for an energy storage battery cabinet. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] The safety of energy storage battery cabinets has always been the most concerned issue for the majority of users. Usually, energy storage batteries are composed of battery strings connected in series, and the smallest unit of such batteries is called a "single battery". In most cases, the safety of energy storage batteries is determined by these single batteries.

[0004] Therefore, it is very necessary to monitor the status of each single battery and take immediate rescue measures when it is about to be abnormal. Although the existing fault diagnosis methods of energy storage battery cabinets, such as transient voltage detection and ultrasonic detection, can provide certain diagnostic information, the diagnostic accuracy and reliability of these technologies still need to be improved under complex fault conditions, especially because there are many interferences in the energy storage battery cabinet. The existence of interference affects the accuracy and resolution of the sensor, and there are often false fault alarms. Therefore, how to improve the reliability and accuracy of energy storage battery fault diagnosis and timely detect the abnormal status of the energy storage battery cabinet needs to be solved urgently. Summary of the invention

[0005] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides a fault diagnosis method and system for an energy storage battery cabinet. Based on multiple modal data at multiple times, the fault level of the overall energy storage cabinet is diagnosed through a deep learning model. On the basis of the fault level diagnosis of the energy storage cabinet, the fault location is determined in combination with the aging condition of each battery string, the connection fault condition of each single battery and the abnormal temperature change rate of each single battery. False alarms of sensors caused by interference can be effectively avoided, thereby improving the reliability and accuracy of fault diagnosis of energy storage batteries.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] A first aspect of the present invention provides a fault diagnosis method for an energy storage battery cabinet, comprising:

[0008] Obtain the internal resistance data of each battery string at several adjacent moments to obtain an internal resistance sequence; for each battery string, calculate the internal resistance average value according to the internal resistance sequence, and determine the aging condition based on the internal resistance average value;

[0009] Obtain the basic pressure difference of each battery string in the energy storage battery cabinet and the real-time pressure difference at several consecutive moments, and calculate the difference between the real-time pressure difference and the basic pressure difference to obtain a pressure difference difference sequence; for each battery string, determine whether the pressure difference at the current moment is within a preset threshold range. If it is not within the preset threshold range, obtain the voltage of each single cell at the current moment and the previous moment, calculate the voltage change rate, and determine the connection fault status of each single cell based on the voltage change rate;

[0010] Obtain the temperature value of each battery cell at several adjacent moments, and calculate the temperature change rate according to the temperature value to obtain a temperature change rate sequence; for each single battery cell, determine the abnormality of the temperature change rate based on the temperature change rate at the current moment;

[0011] Based on the internal resistance sequence of all battery strings, the voltage difference sequence of all battery strings and the temperature change rate sequence of all battery cells, the aging index, connection fault index and temperature change rate abnormality index of the energy storage battery are obtained through the fault diagnosis model.

[0012] After weighted fusion of the aging index, connection fault index and temperature change rate abnormality index to obtain the fault level of the energy storage cabinet, the fault location is determined based on the aging condition of each battery string, the connection fault condition of each single battery and the temperature change rate abnormality of each single battery.

[0013] Furthermore, if the fault level of the energy storage cabinet is the first level, it is not necessary to determine the fault location;

[0014] If the fault level of the energy storage cabinet is the second level, the fault location is determined and displayed based on the aging condition of each battery string, the connection fault condition of each single battery, and the abnormal temperature change rate of each single battery;

[0015] If the fault level of the energy storage cabinet is the second level, based on the aging condition of each battery string, the connection fault condition of each single battery and the abnormal temperature change rate of each single battery, the preset battery switching process or maintenance process is started after the fault location is determined.

[0016] Furthermore, the method for determining the aging condition is: for each battery string, the average internal resistance is compared with a benchmark internal resistance reference value to obtain a deviation value, and the aging condition is determined according to the size and direction of the deviation value.

[0017] Furthermore, the internal resistance sequence of all battery strings is input into the pre-trained first fault diagnosis model to obtain the aging degree index of the energy storage battery; the voltage difference value sequence of all battery strings is input into the pre-trained second fault diagnosis model to obtain the connection fault index of the energy storage battery; the temperature change rate sequence of all battery cells is input into the pre-trained third fault diagnosis model to obtain the temperature change rate abnormality index.

[0018] A second aspect of the present invention provides a fault diagnosis system for an energy storage battery cabinet, comprising:

[0019] The first evaluation data module is configured to: obtain internal resistance data of each battery string at a number of adjacent moments to obtain an internal resistance sequence; for each battery string, calculate an internal resistance average value according to the internal resistance sequence, and determine an aging condition based on the internal resistance average value;

[0020] The second evaluation data module is configured to: obtain the basic pressure difference of each battery string in the energy storage battery cabinet and the real-time pressure difference at several consecutive moments, and calculate the difference between the real-time pressure difference and the basic pressure difference to obtain a pressure difference difference sequence; for each battery string, determine whether the pressure difference at the current moment is within a preset threshold range, and when it is not within the preset threshold range, obtain the voltage of each single battery at the current moment and the previous moment, calculate the voltage change rate, and determine the connection fault condition of each single battery based on the voltage change rate;

[0021] The third evaluation data module is configured to: obtain the temperature value of each battery cell at a number of adjacent moments, and calculate the temperature change rate according to the temperature value to obtain a temperature change rate sequence; for each single battery, determine the abnormality of the temperature change rate based on the temperature change rate at the current moment;

[0022] A fault diagnosis submodule is configured to obtain an aging index, a connection fault index and an abnormal temperature change rate index of the energy storage battery through a fault diagnosis model based on the internal resistance sequence of all battery strings, the voltage difference difference sequence of all battery strings and the temperature change rate sequence of all battery cells;

[0023] The fault diagnosis result module is configured to: perform weighted fusion of the aging degree index, the connection fault index and the temperature change rate abnormality index to obtain the fault level of the energy storage cabinet, and then determine the fault location by combining the aging condition of each battery string, the connection fault condition of each single battery and the temperature change rate abnormality of each single battery.

[0024] Furthermore, if the fault level of the energy storage cabinet is the first level, it is not necessary to determine the fault location;

[0025] If the fault level of the energy storage cabinet is the second level, the fault location is determined and displayed based on the aging condition of each battery string, the connection fault condition of each single battery, and the abnormal temperature change rate of each single battery;

[0026] If the fault level of the energy storage cabinet is the second level, based on the aging condition of each battery string, the connection fault condition of each single battery and the abnormal temperature change rate of each single battery, the preset battery switching process or maintenance process is started after the fault location is determined.

[0027] Furthermore, the method for determining the aging condition is: for each battery string, the average internal resistance is compared with a benchmark internal resistance reference value to obtain a deviation value, and the aging condition is determined according to the size and direction of the deviation value.

[0028] Furthermore, the fault diagnosis submodule is specifically configured as follows: the internal resistance sequence of all battery strings is input into a pre-trained first fault diagnosis model to obtain an aging index of the energy storage battery; the voltage difference sequence of all battery strings is input into a pre-trained second fault diagnosis model to obtain a connection fault index of the energy storage battery; and the temperature change rate sequence of all battery cells is input into a pre-trained third fault diagnosis model to obtain an abnormal temperature change rate index.

[0029] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the above-mentioned method for diagnosing a fault of an energy storage battery cabinet.

[0030] A fourth aspect of the present invention provides a computer device, comprising a computer-readable storage medium, a processor, and a computer program stored on the computer-readable storage medium and executable on the processor, wherein when the processor executes the program, the steps in the fault diagnosis method for an energy storage battery cabinet as described above are implemented.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] The present invention diagnoses the fault level of the entire energy storage cabinet based on multiple modal data at multiple times through a deep learning model. On the basis of the fault level diagnosis of the energy storage cabinet, the fault location is determined in combination with the aging condition of each battery string, the connection fault condition of each single battery and the abnormal temperature change rate of each single battery. This can effectively avoid sensor false alarms caused by interference and improve the reliability and accuracy of fault diagnosis of energy storage batteries. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0034] Figure 1 It is a flow chart of a fault diagnosis method of an energy storage battery cabinet according to the first embodiment of the present invention;

[0035] Figure 2 is a schematic diagram of a fault diagnosis system for an energy storage battery cabinet according to a second embodiment of the present invention;

[0036] Figure 3 It is a structural diagram of a computer device according to a fourth embodiment of the present invention. DETAILED DESCRIPTION

[0037] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0038] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0039] Embodiment 1

[0040] This embodiment provides a method for diagnosing faults of an energy storage battery cabinet.

[0041] This embodiment provides a method for diagnosing a fault in an energy storage battery cabinet. Figure 1 As shown, steps S10-S50 are included:

[0042] S10, respectively collect the internal resistance data of each battery string in the energy storage battery cabinet during the battery charging process or the battery discharging process at several adjacent moments, obtain the internal resistance sequence, and use the internal resistance sequence as the first evaluation data. The several adjacent moments are tn, tn-1, ..., t-1, t, where t represents the current moment and n represents the number of adjacent moments.

[0043] In S10, after the step of obtaining the first evaluation data, it also includes: for each battery string, calculating the internal resistance average value according to the internal resistance sequence, presetting a benchmark internal resistance reference value, and comparing the internal resistance average value with the benchmark internal resistance reference value to obtain a first deviation value; according to the size and direction of the first deviation value, determining the operating status (aging condition) of each battery string, and then determining the operating status of the energy storage battery.

[0044] In this embodiment, the preset reference internal resistance of the battery string under charging state is 50mΩ, and the preset reference internal resistance under discharging state is 55mΩ. For battery string A, the average internal resistance under charging state is measured to be 52mΩ, and 56mΩ under discharging state, the first deviation value under charging state = 52-50 = 2mΩ, and the first deviation value under discharging state = 56-55 = 1mΩ; for battery string B, the average internal resistance under charging state is measured to be 49mΩ, and 54mΩ under discharging state, the first deviation value under charging state = (49-50) = -1mΩ, and the first deviation value under discharging state = 54-55 = -1mΩ. The operating status of the battery is evaluated based on the size and direction of the first deviation value: the set tolerance range (benchmark internal resistance reference value) is ±5mΩ. For battery string A, the first deviation value in the charging state is +2mΩ, and the first deviation value in the discharging state is +1mΩ. These deviation values ​​are small and within the set tolerance range, indicating that battery string A operates well within the expected range; for battery string B, the first deviation value in the charging state is -1mΩ, and the first deviation value in the discharging state is -1mΩ, which are within the set tolerance range, so the operating status of battery string B is normal.

[0045] S20, respectively collecting the basic pressure difference of each battery string and the real-time pressure difference at several consecutive moments, and calculating the difference between the real-time pressure difference and the basic pressure difference, obtaining the pressure difference difference values ​​at several consecutive moments, forming a pressure difference difference sequence, and obtaining second evaluation data.

[0046] In S20, after the step of obtaining the second evaluation data, it also includes: judging whether the pressure difference value at the current moment is within the preset threshold range; when the pressure difference value at the current moment is not within the preset threshold range, obtaining the voltage data of the single cell at each preset moment (the current moment and the previous moment); calculating the voltage change rate according to the voltage data, and determining the operating state (connection fault condition) of the single cell based on the voltage change rate. That is, comparing the voltage change rate with the set value to judge whether each single cell has a connection fault.

[0047] In one embodiment, the basic pressure difference of the battery string is 50, and the real-time pressure difference collected at the current moment is 55, so the pressure difference value at the current moment is 5. The set threshold range is ±10, and this pressure difference value is within the allowable range.

[0048] In another embodiment, the real-time differential pressure collected at the current moment (t moment) is 62, and the differential pressure difference at the current moment is 12, then this differential pressure difference is not within the allowable range, and the voltage data of the single cell is obtained within the preset time interval. The preset time is to obtain voltage data once every hour. Using the continuously obtained voltage data, the voltage change rate of the single cell is calculated. The voltage of the single cell at the first measurement moment (t-1 moment) is 3.7V, and the voltage at the second measurement moment (t moment) is 3.65V. The voltage change rate is -1.35%. The negative value indicates that the battery voltage is decreasing, indicating that the battery has a certain degree of capacity loss during the discharge process, that is, the single cell may have a connection fault.

[0049] S30, respectively collecting the temperature value of each battery cell at several adjacent moments, and calculating the temperature change rate according to the temperature value, and taking the temperature change rate sequence (including the temperature change rates at several moments) as the third evaluation data.

[0050] In this embodiment, the average temperature of each single cell at a certain preset time is monitored, and the temperature change rate per minute is calculated, and the temperature change rate is used as the third evaluation data. Temperature change rate at time k = (temperature at time k - temperature at time k-1) / temperature at time k-1.

[0051] In S30, after the step of obtaining the third evaluation data, it also includes: judging whether the average temperature change rate of any battery cell exceeds a preset threshold based on the temperature change rate at the current moment, and determining an abnormal temperature change rate; if it is detected that the temperature change rate of the battery cell exceeds the preset threshold, generating a fault diagnosis result (that is, the temperature change rate is abnormal).

[0052] S40, input the first evaluation data of each battery string into the pre-trained first fault diagnosis model so that the first fault diagnosis model outputs a first fault diagnosis result; input the second evaluation data of each battery string into the pre-trained second fault diagnosis model so that the second fault diagnosis model outputs a second fault diagnosis result; input the third evaluation data of each battery cell into the pre-trained third fault diagnosis model so that the third fault diagnosis model outputs a third fault diagnosis result.

[0053] In this embodiment, the first fault diagnosis model, the second fault diagnosis model and the third fault diagnosis model are all based on machine learning algorithms, such as those obtained through neural network training, and are used to identify abnormal conditions or fault modes of battery internal resistance data.

[0054] The first fault diagnosis model: collects internal resistance data of each battery string in the energy storage battery cabinet during the battery charging or discharging process at several adjacent moments to obtain an internal resistance sequence, and calculates the internal resistance average value of each battery string according to the internal resistance sequence to obtain first evaluation data, and inputs the first evaluation data into the pre-trained first fault diagnosis model so that the first fault diagnosis model outputs a first fault diagnosis result, and the first diagnosis result gives an aging degree index of the entire energy storage battery.

[0055] The second fault diagnosis model: collects the basic pressure difference of each battery string and the real-time pressure difference during the current operation process, and calculates the difference between the real-time pressure difference and the basic pressure difference to obtain second evaluation data, and inputs the second evaluation data into the pre-trained second fault diagnosis model so that the second fault diagnosis model outputs a second fault diagnosis result. The second fault diagnosis result gives the connection fault index of the entire energy storage battery.

[0056] The third fault diagnosis model: collect the temperature value of each battery cell at a preset time, and calculate the temperature change rate based on the temperature value to obtain third evaluation data; input the third evaluation data into the pre-trained third fault diagnosis model so that the third fault diagnosis model outputs a third fault diagnosis result, and the third fault diagnosis result gives an abnormal index of the temperature change rate of the entire energy storage battery.

[0057] S50: Based on a pre-built linear weighted fusion model, weighted fusion processing is performed on the first fault diagnosis result, the second fault diagnosis result, and the third fault diagnosis result to obtain a fault diagnosis result (fault level) of the energy storage battery cabinet.

[0058] In one embodiment, the pre-built linear weighted fusion model is as follows:

[0059] D=αD1+βD2+γD3

[0060]

[0061] Wherein, D is the fault diagnosis result of the energy storage battery cabinet (fault level of the energy storage cabinet), α, β and γ are weight values, and satisfy α+β+γ=1, D1 is the first fault diagnosis result, D2 is the second fault diagnosis result, and D3 is the third fault diagnosis result.

[0062] In this embodiment, it is assumed that the aging index of 3 indicates severe aging, the aging index of 2 indicates general aging, 1 indicates slight aging, and 0 indicates completely normal. If the first fault diagnosis result is aging degree = 1.5, it indicates that the energy storage battery has signs of general aging. If the second fault diagnosis result is connection fault index = 1, it indicates that the energy storage battery has a slight connection fault. If the third fault diagnosis result is temperature change rate abnormality index = 2, it indicates that the temperature change rate of the energy storage battery is more serious. These results are calculated based on their respective fault diagnosis models, and now they need to be fused into a comprehensive fault diagnosis result. The pre-built linear weighted fusion model specifies the weights of each fault diagnosis result, or is set according to experience, and the preset weights are as follows: the weight of the first fault diagnosis result is 0.4, the weight of the second fault diagnosis result is 0.3, and the weight of the third fault diagnosis result is 0.3. The sum of these weights is 1, indicating that their sum should be 1 to ensure that the weighted average result is between 0 and 1. Comprehensive fault diagnosis result = (aging degree * 0.4) + (connection fault index * 0.3) + (temperature change rate * 0.3), comprehensive fault diagnosis result = (1.5 * 0.4) + (1 * 0.3) + (2 * 0.3), comprehensive fault diagnosis result = 0.6 + 0.3 + 0.6, comprehensive fault diagnosis result = 1.5, the comprehensive fault diagnosis result is 1.5, this value can be interpreted as the overall fault index. In this example, 1 means that there is no sign of fault, and 3 means that there is a serious fault problem. Therefore, 1.5 means that there are some problems with the energy storage battery cabinet, but they are not very serious. Through this weighted fusion method, multiple different sources and different types of fault diagnosis results are combined to give a more comprehensive assessment. This method can help operation and maintenance personnel diagnose the status of the energy storage battery cabinet more quickly and accurately in actual operation, and take appropriate repair or maintenance measures to ensure the safe operation and performance reliability of the energy storage battery cabinet.

[0063] In this embodiment, after the step of obtaining the fault diagnosis result of the energy storage battery cabinet, it includes: determining the fault diagnosis level result of the fault diagnosis result of the energy storage battery cabinet based on a preset fault diagnosis level classification label; matching the corresponding energy storage battery cabinet fault diagnosis processing suggestion according to the fault diagnosis level result of the energy storage battery cabinet.

[0064] In this embodiment, the fault diagnosis processing suggestions for the corresponding energy storage battery cabinet are matched according to the fault diagnosis level results of the energy storage battery cabinet, specifically including: when the fault diagnosis result level of the energy storage battery cabinet is the first level, no processing is required and regular monitoring is performed; when the fault diagnosis result level of the energy storage battery cabinet is the second level, the fault information and diagnosis results are displayed on the user interface, and the detailed data of the energy storage battery is obtained to confirm the specific location and extent of the fault; when the fault diagnosis result level of the energy storage battery cabinet is the third level, the switching process or maintenance process of the battery cell is executed, and the fault report is sent to the remote monitoring center.

[0065] After the fault level is obtained, based on the fault level of the energy storage cabinet, combined with the aging condition of each battery string given in S10, the connection fault condition of each single battery given in S20, and the abnormal temperature change rate of each single battery given in S30, the fault location is determined and processing suggestions are given.

[0066] In this embodiment, if the fault level is the first level and the temperature change rate of a battery string is abnormal, the processing suggestion is: issue an alarm and conduct regular monitoring, automatically record and alarm, and start regular monitoring of battery temperature changes, such as checking the battery temperature once an hour to ensure that there is no trend of further increase. If the fault level is the second level and a single battery cell connection failure occurs, the processing suggestion is: display the fault information and diagnosis results on the user interface and obtain detailed data. On the monitoring interface, detailed fault information will be displayed. At the same time, collect relevant detailed data, such as the current and voltage curves of the battery cell, to help determine the specific location and impact range of the fault. If the fault level is the third level and a single battery cell connection failure occurs, the processing suggestion is: execute the switching process or maintenance process of the battery cell, and send a fault report to the remote monitoring center, start the preset battery switching process or maintenance process, including rebalancing the voltage of the battery cell, or replacing the damaged battery cell, and automatically send a detailed fault report to the remote monitoring center, including the type of fault, the impact range and the recommended repair steps.

[0067] The present embodiment provides a method for diagnosing a fault of an energy storage battery cabinet, which improves the reliability and accuracy of diagnosing a fault of an energy storage battery and promptly detects abnormal conditions of the energy storage battery.

[0068] Embodiment 2

[0069] This embodiment provides a fault diagnosis system for an energy storage battery cabinet, such as Figure 2 As shown, it specifically includes:

[0070] The energy storage battery includes a battery module, and the battery module includes a battery string formed by connecting battery cells in series.

[0071] The first evaluation data module 10 is configured to: obtain the internal resistance data of each battery string at a number of adjacent moments to obtain an internal resistance sequence; for each battery string, calculate an internal resistance average value according to the internal resistance sequence, and determine the aging condition based on the internal resistance average value;

[0072] The second evaluation data module 20 is configured to: obtain the basic pressure difference of each battery string in the energy storage battery cabinet and the real-time pressure difference at several consecutive moments, and calculate the difference between the real-time pressure difference and the basic pressure difference to obtain a pressure difference difference sequence; for each battery string, determine whether the pressure difference at the current moment is within a preset threshold range, and when it is not within the preset threshold range, obtain the voltage of each single cell at the current moment and the previous moment, calculate the voltage change rate, and determine the connection fault condition of each single cell based on the voltage change rate;

[0073] The third evaluation data module 30 is configured to: obtain the temperature value of each battery cell at a number of adjacent moments, and calculate the temperature change rate according to the temperature value to obtain a temperature change rate sequence; for each single battery, determine the abnormality of the temperature change rate based on the temperature change rate at the current moment;

[0074] The fault diagnosis submodule 40 is configured to obtain the aging index, connection fault index and temperature change rate abnormality index of the energy storage battery through the fault diagnosis model based on the internal resistance sequence of all battery strings, the voltage difference difference sequence of all battery strings and the temperature change rate sequence of all battery cells;

[0075] The fault diagnosis result module 50 is configured to: perform weighted fusion of the aging degree index, the connection fault index and the temperature change rate abnormality index to obtain the fault level of the energy storage cabinet, and then determine the fault location in combination with the aging condition of each battery string, the connection fault condition of each single battery and the temperature change rate abnormality of each single battery.

[0076] If the fault level of the energy storage cabinet is level 1, there is no need to determine the fault location;

[0077] If the fault level of the energy storage cabinet is the second level, the fault location is determined and displayed based on the aging condition of each battery string, the connection fault condition of each single battery, and the abnormal temperature change rate of each single battery;

[0078] If the fault level of the energy storage cabinet is the second level, based on the aging condition of each battery string, the connection fault condition of each single battery and the abnormal temperature change rate of each single battery, the preset battery switching process or maintenance process is started after the fault location is determined.

[0079] The method for determining the aging condition is as follows: for each battery string, the average internal resistance is compared with a benchmark internal resistance reference value to obtain a deviation value, and the aging condition is determined according to the size and direction of the deviation value.

[0080] The fault diagnosis submodule 40 is specifically configured as follows: the internal resistance sequence of all battery strings is input into a pre-trained first fault diagnosis model to obtain an aging index of the energy storage battery; the voltage difference difference sequence of all battery strings is input into a pre-trained second fault diagnosis model to obtain a connection fault index of the energy storage battery; and the temperature change rate sequence of all battery cells is input into a pre-trained third fault diagnosis model to obtain an abnormal temperature change rate index.

[0081] It should be noted here that each module in this embodiment corresponds to each step in Example 1 one by one, and the specific implementation process is the same, which will not be repeated here.

[0082] Embodiment 3

[0083] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps in the fault diagnosis method for an energy storage battery cabinet as described in the first embodiment above are implemented.

[0084] Embodiment 4

[0085] This embodiment provides a computer device, such as Figure 3 As shown, it includes a display device, an input device, a computer-readable storage medium (volatile memory and non-volatile storage medium), a processor, a communication interface (i.e., a network interface), and a computer program stored on the computer-readable storage medium and executable on the processor, wherein the processor, the communication interface, and the computer-readable storage medium can be connected via a bus or other means. The communication interface is used to receive and send data, and when the processor executes the program, the steps in the method for diagnosing a fault of an energy storage battery cabinet as described in the first embodiment above are implemented.

[0086] Among them, any reference to memory, storage, database or other media provided by the present application and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0087] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0088] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0089] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0090] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for diagnosing a fault of an energy storage battery cabinet, characterized in that: include: Obtain the internal resistance data of each battery string at several adjacent moments to obtain an internal resistance sequence; for each battery string, calculate the internal resistance average value according to the internal resistance sequence, and determine the aging condition based on the internal resistance average value; Obtain the basic pressure difference of each battery string in the energy storage battery cabinet and the real-time pressure difference at several consecutive moments, and calculate the difference between the real-time pressure difference and the basic pressure difference to obtain a pressure difference difference sequence; for each battery string, determine whether the pressure difference at the current moment is within a preset threshold range. If it is not within the preset threshold range, obtain the voltage of each single cell at the current moment and the previous moment, calculate the voltage change rate, and determine the connection fault status of each single cell based on the voltage change rate; Obtain the temperature value of each battery cell at several adjacent moments, and calculate the temperature change rate according to the temperature value to obtain a temperature change rate sequence; for each single battery cell, determine the abnormality of the temperature change rate based on the temperature change rate at the current moment; Based on the internal resistance sequence of all battery strings, the voltage difference sequence of all battery strings and the temperature change rate sequence of all battery cells, the aging index, connection fault index and temperature change rate abnormality index of the energy storage battery are obtained through the fault diagnosis model. After weighted fusion of the aging index, connection fault index and temperature change rate abnormality index to obtain the fault level of the energy storage cabinet, the fault location is determined based on the aging condition of each battery string, the connection fault condition of each single battery and the temperature change rate abnormality of each single battery.

2. A method for diagnosing a fault of an energy storage battery cabinet as claimed in claim 1, characterized in that: If the fault level of the energy storage cabinet is level 1, there is no need to determine the fault location; If the fault level of the energy storage cabinet is the second level, the fault location is determined and displayed based on the aging condition of each battery string, the connection fault condition of each single battery, and the abnormal temperature change rate of each single battery; If the fault level of the energy storage cabinet is the second level, based on the aging condition of each battery string, the connection fault condition of each single battery and the abnormal temperature change rate of each single battery, the preset battery switching process or maintenance process is started after the fault location is determined.

3. A method for diagnosing a fault of an energy storage battery cabinet as claimed in claim 1, characterized in that: The method for determining the aging condition is as follows: for each battery string, the average internal resistance is compared with a benchmark internal resistance reference value to obtain a deviation value, and the aging condition is determined according to the size and direction of the deviation value.

4. A method for diagnosing a fault of an energy storage battery cabinet as claimed in claim 1, characterized in that: The internal resistance sequence of all battery strings is input into the pre-trained first fault diagnosis model to obtain the aging degree index of the energy storage battery; the voltage difference difference sequence of all battery strings is input into the pre-trained second fault diagnosis model to obtain the connection fault index of the energy storage battery; the temperature change rate sequence of all battery cells is input into the pre-trained third fault diagnosis model to obtain the temperature change rate abnormality index.

5. A fault diagnosis system for an energy storage battery cabinet, characterized in that: include: The first evaluation data module is configured to: obtain internal resistance data of each battery string at a number of adjacent moments to obtain an internal resistance sequence; for each battery string, calculate an internal resistance average value according to the internal resistance sequence, and determine an aging condition based on the internal resistance average value; The second evaluation data module is configured to: obtain the basic pressure difference of each battery string in the energy storage battery cabinet and the real-time pressure difference at several consecutive moments, and calculate the difference between the real-time pressure difference and the basic pressure difference to obtain a pressure difference difference sequence; for each battery string, determine whether the pressure difference at the current moment is within a preset threshold range, and when it is not within the preset threshold range, obtain the voltage of each single battery at the current moment and the previous moment, calculate the voltage change rate, and determine the connection fault condition of each single battery based on the voltage change rate; The third evaluation data module is configured to: obtain the temperature value of each battery cell at a number of adjacent moments, and calculate the temperature change rate according to the temperature value to obtain a temperature change rate sequence; for each single battery, determine the abnormality of the temperature change rate based on the temperature change rate at the current moment; A fault diagnosis submodule is configured to obtain an aging index, a connection fault index and an abnormal temperature change rate index of the energy storage battery through a fault diagnosis model based on the internal resistance sequence of all battery strings, the voltage difference difference sequence of all battery strings and the temperature change rate sequence of all battery cells; The fault diagnosis result module is configured to: perform weighted fusion of the aging degree index, the connection fault index and the temperature change rate abnormality index to obtain the fault level of the energy storage cabinet, and then determine the fault location by combining the aging condition of each battery string, the connection fault condition of each single battery and the temperature change rate abnormality of each single battery.

6. A fault diagnosis system for an energy storage battery cabinet as claimed in claim 5, characterized in that: If the fault level of the energy storage cabinet is level 1, there is no need to determine the fault location; If the fault level of the energy storage cabinet is the second level, the fault location is determined and displayed based on the aging condition of each battery string, the connection fault condition of each single battery, and the abnormal temperature change rate of each single battery; If the fault level of the energy storage cabinet is the second level, based on the aging condition of each battery string, the connection fault condition of each single battery and the abnormal temperature change rate of each single battery, the preset battery switching process or maintenance process is started after the fault location is determined.

7. A fault diagnosis system for an energy storage battery cabinet as claimed in claim 5, characterized in that: The method for determining the aging condition is as follows: for each battery string, the average internal resistance is compared with a benchmark internal resistance reference value to obtain a deviation value, and the aging condition is determined according to the size and direction of the deviation value.

8. A fault diagnosis system for an energy storage battery cabinet as claimed in claim 5, characterized in that: The fault diagnosis submodule is specifically configured as follows: the internal resistance sequence of all battery strings is input into a pre-trained first fault diagnosis model to obtain an aging index of the energy storage battery; the voltage difference difference sequence of all battery strings is input into a pre-trained second fault diagnosis model to obtain a connection fault index of the energy storage battery; the temperature change rate sequence of all battery cells is input into a pre-trained third fault diagnosis model to obtain an abnormal temperature change rate index.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of a fault diagnosis method for an energy storage battery cabinet as described in any one of claims 1 to 4 are implemented.

10. A computer device comprising a computer-readable storage medium, a processor, and a computer program stored in the computer-readable storage medium and executable on the processor, characterized in that: When the processor executes the program, the steps in the fault diagnosis method of the energy storage battery cabinet as described in any one of claims 1-4 are implemented.

Images