Artificial intelligence-based energy storage battery pack fault monitoring and diagnosis system

Abstract

The present application relates to the technical field of energy storage battery monitoring, and discloses an energy storage battery pack fault monitoring and diagnosis system based on artificial intelligence, which collects the working parameters of the working process of each working energy storage battery pack in real time, collects the environmental parameters of the environment where each working energy storage battery pack is located in real time, calculates the fault diagnosis coefficient of each working energy storage battery pack according to the working parameters and the environmental parameters of each working energy storage battery pack, and performs fault diagnosis on each working energy storage battery pack according to the fault diagnosis coefficient of each working energy storage battery pack. For the working energy storage battery pack that has failed, a standby energy storage battery pack is selected for replacement based on the rated capacity, charging efficiency and discharging efficiency of the energy storage battery pack, real-time monitoring and fault diagnosis of the energy storage battery pack are realized, and the reliability and safety of the energy storage system are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of energy storage battery monitoring, in particular to an energy storage battery pack fault monitoring and diagnosis system based on artificial intelligence. BACKGROUND

[0002] Energy storage battery packs can balance peak and valley power of power systems, improve power grid stability, reduce power grid loss, and reduce energy costs. During power demand peaks, energy storage battery packs can release stored power to supplement power grid power supply shortages. During power demand troughs, they can absorb excess power for storage. In addition, energy storage battery packs can also serve as backup power sources to provide emergency power support for cities and industrial areas in the event of power failure or power outage, ensuring the normal operation of the power system.

[0003] Existing energy storage battery pack fault monitoring and diagnosis systems often rely on manual inspection and professional knowledge, which is not only inefficient, but also difficult to achieve real-time early warning of faults. At the same time, it cannot be switched to the appropriate backup battery pack in time, resulting in power system collapse and causing huge losses. Therefore, the present application provides an energy storage battery pack fault monitoring and diagnosis system based on artificial intelligence. SUMMARY

[0004] The present application aims to provide an energy storage battery pack fault monitoring and diagnosis system based on artificial intelligence to solve the above technical problems.

[0005] The present application can be achieved by the following technical solutions:

[0006] The energy storage battery pack fault monitoring and diagnosis system based on artificial intelligence comprises a data acquisition module, a data processing module, a data analysis module, a fault diagnosis module, and a backup battery selection module.

[0007] The data acquisition module is used to acquire physical parameters during the operation of the energy storage battery pack and environmental parameters of the energy storage battery pack, and transmit them to the data processing module.

[0008] The data processing module is used to receive data transmitted by the data acquisition module, pre-process the data to ensure data accuracy and consistency, and transmit the data to the data analysis module.

[0009] The data analysis module is used to receive processed data transmitted by the data processing module, analyze the data characteristics, and send the analysis results to the fault diagnosis module.

[0010] The fault diagnosis module is used to receive analysis results from the data analysis module, diagnose faults in the operating energy storage battery pack based on the analysis results, and issue real-time warnings based on the diagnosis results.

[0011] The standby battery selection module is used for automatically selecting the most suitable standby energy storage battery pack based on the real-time early warning issued by the fault diagnosis module and performing switching.

[0012] As a further description of the present application, the working process of the data acquisition module includes:

[0013] All working energy storage battery packs are numbered, and the labels are 1, 2, …, n in turn;

[0014] Based on the sensors installed on the energy storage battery packs, the temperature, voltage, and current change data over time of the working process of the working energy storage battery packs are collected in real time;

[0015] Based on the environmental monitoring sensors, the environmental influence parameters of the working energy storage battery packs are collected in real time.

[0016] As a further description of the present application, the working process of the data analysis module includes:

[0017] Based on the temperature, voltage, and current change data over time of the working process of each working energy storage battery pack, the first influence index of each working energy storage battery pack is obtained;

[0018] Based on the environmental influence parameters of the working energy storage battery packs, the second influence index of each working energy storage battery pack is obtained;

[0019] Based on the first influence index and the second influence index of each working energy storage battery pack, the fault diagnosis coefficient of each working energy storage battery pack is obtained, and each working energy storage battery pack is diagnosed for faults according to the fault diagnosis coefficient of each working energy storage battery pack.

[0020] As a further description of the present application, the working process of obtaining the first influence index of each working energy storage battery pack includes:

[0021] According to the actual working conditions of the power system, the working time period of the working energy storage battery pack in the monitoring period is divided into peak and valley sections;

[0022] The temperature, voltage, and current change data over time of the i-th working energy storage battery pack in the peak time period and the valley time period are obtained respectively;

[0023] The state parameter of the i-th working energy storage battery pack in the peak time period is calculated by the following formula:

[0024]

[0025] The state parameter of the i-th working energy storage battery pack in the valley time period is calculated by the following formula:

[0026]

[0027] wherein t1-t2 is the peak time period, t2-t3 is the valley time period, S i1 is the state parameter of the i-th working energy storage battery pack in the peak time period, S i2 is the state parameter of the i-th working energy storage battery pack in the valley time period; U i (t) is the voltage-time change data of the i-th working energy storage battery pack in the monitoring time period, I i (t) is the current-time change data of the i-th working energy storage battery pack in the monitoring time period, T i (t) is the temperature-time change data of the i-th working energy storage battery pack in the monitoring time period; k1, k2 and k3 are the corresponding weight coefficients of the voltage, current and temperature respectively, and i belongs to n;

[0028] based on the state parameter S i1 of the i-th working energy storage battery pack in the peak time period and the state parameter S i2 of the i-th working energy storage battery pack in the valley time period, a first influence index mathematical model of the i-th working energy storage battery pack is constructed:

[0029]

[0030] wherein α and β are the weight coefficients corresponding to the peak time period and the valley time period respectively, and α>β>0, R i1 is the first influence index of the i-th working energy storage battery pack.

[0031] As a further description of the scheme of the present application, the working process of obtaining the second influence index of each working energy storage battery pack comprises:

[0032] obtaining the environmental parameter of the working environment of the i-th working energy storage battery pack, and constructing a second influence index mathematical model of the i-th working energy storage battery pack based on the environmental parameter:

[0033]

[0034] wherein m is the total number of environmental parameters, j belongs to [1, m], E j is the j-th environmental parameter physical quantity, E j0 is the j-th environmental parameter standard value set by the system, ΔE kth is the j-th environmental parameter difference reference value, ε j is the corresponding weight coefficient of the j-th environmental parameter, R i2 is the second influence index of the i-th working energy storage battery pack.

[0035] As a further description of the scheme of the present application, the working process of diagnosing the fault of each working energy storage battery pack comprises:

[0036] The mathematical model of the fault diagnosis coefficient of the ith working energy storage battery pack is constructed, and the expression is:

[0037]

[0038] In the formula, δ and ρ are weight coefficients corresponding to the first influence index and the second influence index respectively, μ i is the fault diagnosis coefficient of the ith working energy storage battery pack;

[0039] The fault diagnosis coefficient μ i of the ith working energy storage battery pack is compared with the fault diagnosis coefficient threshold μ thi of the ith working energy storage battery pack set by the system, if μ i is greater than or equal to μ thi , it indicates that the ith working energy storage battery pack has a fault, and the standby energy storage battery pack needs to be started immediately, and a warning is sent immediately, otherwise, the ith working energy storage battery pack does not have a fault.

[0040] The fault diagnosis coefficients of each working energy storage battery pack are calculated in turn, and the corresponding working energy storage battery pack is diagnosed according to the fault diagnosis coefficient of each working energy storage battery pack.

[0041] As a further description of the scheme of the application, the working process of the standby battery selection module includes:

[0042] When the ith working energy storage battery pack has a fault, the rated capacity Q i , the charging efficiency P ci and the discharging efficiency P di of the ith working energy storage battery pack are obtained.

[0043] The rated capacity Q x , the charging efficiency P cx and the discharging efficiency P dx of the xth standby energy storage battery pack are obtained.

[0044] The replacement coefficient of the xth standby energy storage battery pack relative to the ith working energy storage battery pack is calculated by the following formula:

[0045]

[0046] In the formula, k Q , and are weight coefficients corresponding to the rated capacity, the charging efficiency and the discharging efficiency respectively, σ x-i is the replacement coefficient of the xth standby energy storage battery pack relative to the ith working energy storage battery pack.

[0047] As a further description of the scheme of the application, the working process of the standby battery selection module further comprises:

[0048] sequentially calculate the replacement coefficients of the y standby energy storage battery groups relative to the i th working energy storage battery group, wherein y is the number of standby energy storage battery groups, and wherein x belongs to y;

[0049] arrange the replacement coefficients of the y standby energy storage battery groups relative to the i th working energy storage battery group from small to large, and select the standby energy storage battery group with the smallest replacement coefficient relative to the i th working energy storage battery group for replacement.

[0050] The application has the beneficial effects that the working parameters of the working process of each working energy storage battery group are collected in real time, the environmental parameters of the environment where each working energy storage battery group is located are collected in real time, the first influence index of each working energy storage battery group is calculated according to the working parameters of each working energy storage battery group, the second influence index of each working energy storage battery group is calculated according to the environmental parameters of each working energy storage battery group, the fault diagnosis coefficient of each working energy storage battery group is calculated according to the first influence index and the second influence index of each working energy storage battery group, and each working energy storage battery group is diagnosed for faults according to the fault diagnosis coefficient of each working energy storage battery group, so that the standby energy storage battery group is selected for replacement based on the rated capacity, the charging efficiency and the discharging efficiency of the energy storage battery group for the working energy storage battery group that has a fault, the real-time monitoring and fault diagnosis of the energy storage battery group are realized, and the reliability and safety of the energy storage system are improved. BRIEF DESCRIPTION OF DRAWINGS

[0051] The application will be further described below with reference to the drawings.

[0052] Figure 1 is a partial structure schematic diagram of the energy storage battery group fault monitoring and diagnosis system based on artificial intelligence provided by the application. DETAILED DESCRIPTION

[0053] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor fall within the protection scope of the application.

[0054] Please refer to Figure 1 The application is an energy storage battery group fault monitoring and diagnosis system based on artificial intelligence, which comprises a data collection module, a data processing module, a data analysis module, a fault diagnosis module and a standby battery selection module.

[0055] The data acquisition module is configured to acquire physical parameters in the working process of the energy storage battery pack and environmental parameters of the energy storage battery pack, and transmit the acquired data to the data processing module.

[0056] The data processing module is configured to receive the data transmitted by the data acquisition module, pre-process the data to ensure the accuracy and consistency of the data, and transmit the pre-processed data to the data analysis module.

[0057] The data analysis module is configured to receive the pre-processed data transmitted by the data processing module, analyze the data, and transmit the analysis results to the fault diagnosis module.

[0058] The fault diagnosis module is configured to receive the analysis results from the data analysis module, diagnose the working energy storage battery pack based on the analysis results, and issue a real-time warning based on the diagnosis results.

[0059] The standby battery selection module is configured to automatically select the most suitable standby energy storage battery pack based on the real-time warning issued by the fault diagnosis module, and perform switching.

[0060] According to the above technical solution, the working parameters of each working energy storage battery pack are acquired in real time, the environmental parameters of each working energy storage battery pack are acquired in real time, the first influence index of each working energy storage battery pack is calculated based on the working parameters of each working energy storage battery pack, the second influence index of each working energy storage battery pack is calculated based on the environmental parameters of each working energy storage battery pack, the fault diagnosis coefficient of each working energy storage battery pack is calculated based on the first influence index and the second influence index of each working energy storage battery pack, and the fault diagnosis of each working energy storage battery pack is performed based on the fault diagnosis coefficient of each working energy storage battery pack. For the working energy storage battery pack that has failed, a standby energy storage battery pack is selected based on the rated capacity, charging efficiency and discharging efficiency of the energy storage battery pack to replace the failed working energy storage battery pack.

[0061] As a further description of the present application, the working process of the data acquisition module includes:

[0062] All working energy storage battery packs are numbered, and the labels are 1, 2, …, n in sequence.

[0063] Based on the sensors installed on the energy storage battery pack, the temperature, voltage and current change data of the working energy storage battery pack over time are acquired in real time.

[0064] Based on the environmental monitoring sensor, the environmental influence parameters of the working energy storage battery pack are acquired in real time.

[0065] As a further description of the present application, the working process of the data analysis module includes:

[0066] The first influencing index of each working energy storage battery pack is obtained based on the temperature, voltage, and current changes over time during the operation of each working energy storage battery pack.

[0067] A second impact index is obtained for each working energy storage battery pack based on the environmental impact parameters of each energy storage battery pack.

[0068] The fault diagnosis coefficient of each working energy storage battery pack is obtained based on the first and second influence indicators, and fault diagnosis is performed on each working energy storage battery pack according to the fault diagnosis coefficient of each working energy storage battery pack.

[0069] As a further description of the present invention, the process of obtaining the first influencing index of each working energy storage battery pack includes:

[0070] Based on the actual operating conditions of the power system, the working time periods of the working energy storage battery packs within the monitoring period are divided into peak and off-peak periods.

[0071] Acquire the temperature, voltage, and current changes over time for the i-th working energy storage battery pack during peak and off-peak periods, respectively.

[0072] The state parameters of the i-th working energy storage battery pack during peak hours are calculated using the following formula:

[0073]

[0074] The state parameters of the i-th working energy storage battery pack during the off-peak period are calculated using the following formula:

[0075]

[0076] In the formula, t1-t2 is the peak period, t2-t3 is the trough period, and S i1 Let S be the state parameter of the i-th working energy storage battery pack during the peak period. i2 U represents the state parameters of the i-th working energy storage battery pack during the off-peak period; i (t) represents the voltage change data of the i-th working energy storage battery pack over time during the monitoring period. i (t) represents the current variation of the i-th working energy storage battery pack over time during the monitoring period, where T is the current of the i-th working energy storage battery pack. i (t) represents the temperature change data of the i-th working energy storage battery pack over time during the monitoring period; k1, k2 and k3 are the voltage, current and corresponding weighting coefficients, respectively, and i belongs to n;

[0077] Based on the state parameters S of the i-th working energy storage battery pack during peak hours i1 The state parameters S of the i-th working energy storage battery pack during the off-peak period i2Construct a mathematical model for the first influencing index of the i-th working energy storage battery pack:

[0078]

[0079] In the formula, α and β are the weighting coefficients corresponding to the peak and trough periods, respectively, and α > β > 0, R i1 This is the first impact indicator for the i-th working energy storage battery pack.

[0080] Through the above technical solution, this embodiment provides a method for obtaining the first influencing index of a working energy storage battery pack based on its operating parameters. First, the working process of the energy storage battery pack is divided into peak and off-peak periods. Then, the temperature, voltage, and current changes over time during the peak and off-peak periods are acquired sequentially within the monitoring period. Finally, the acquired data are substituted into the formula... Calculate the state parameters of the i-th working energy storage battery pack during peak and off-peak hours, and then substitute these state parameters into the mathematical model. A mathematical model for calculating the first impact index of the i-th working energy storage battery pack.

[0081] As a further description of the present invention, the process of obtaining the second influencing index of each working energy storage battery pack includes:

[0082] Obtain the environmental parameters of the working environment of the i-th working energy storage battery pack, and construct a mathematical model of the second influencing index of the i-th working energy storage battery pack based on the environmental parameters:

[0083]

[0084] In the formula, m is the total number of environmental parameters, j belongs to [1, m], and E j Let E be the physical quantity of the j-th environmental parameter. j0 The standard value of the j-th environmental parameter set for the system, ΔE kth ε is the reference value for the difference of the j-th environmental parameter. j R represents the weighting coefficient corresponding to the j-th environmental parameter. i2 This is the second impact indicator for the i-th working energy storage battery pack.

[0085] Through the above technical solution, the present invention obtains the environmental parameters of the working environment of each working energy storage battery pack, and uses the formula based on the environmental parameters. A mathematical model for calculating the second impact index of the i-th working energy storage battery pack.

[0086] As a further description of the present invention, the process of fault diagnosis for each working energy storage battery pack includes:

[0087] The mathematical model for the fault diagnosis coefficients of the i-th working energy storage battery pack is constructed, and its expression is:

[0088]

[0089] In the formula, δ and ρ are the weighting coefficients corresponding to the first and second influencing indicators, respectively, and μ i Let be the fault diagnosis coefficient of the i-th working energy storage battery pack;

[0090] The fault diagnosis coefficient μ of the i-th working energy storage battery pack i The fault diagnosis coefficient threshold μ of the i-th working energy storage battery pack set by the system thi Compare, if μ i Greater than or equal to μ thi If the i-th working energy storage battery pack fails, the backup energy storage battery pack must be activated immediately and an early warning must be issued immediately; otherwise, the i-th working energy storage battery pack has not failed.

[0091] The fault diagnosis coefficient of each working energy storage battery pack is calculated sequentially, and the fault diagnosis of the corresponding working energy storage battery pack is performed based on the fault diagnosis coefficient of each working energy storage battery pack.

[0092] Through the above technical solution, the present invention substitutes the first and second influencing indicators into the formula. Calculate the fault diagnosis coefficient of the i-th working energy storage battery pack, and calculate the fault diagnosis coefficient of each working energy storage battery pack in turn. Compare the fault diagnosis coefficient of each working energy storage battery pack with the fault diagnosis coefficient threshold set by the system for each working energy storage battery pack. If the fault diagnosis coefficient of each working energy storage battery pack is greater than or equal to the fault diagnosis coefficient threshold set by the system for each working energy storage battery pack, it indicates that the current working energy storage battery pack has failed, the backup energy storage battery pack needs to be activated immediately, and an early warning should be issued immediately.

[0093] As a further description of the present invention, the operation of the backup battery selection module includes:

[0094] When the i-th working energy storage battery pack fails, obtain the rated capacity Q of the i-th working energy storage battery pack. i Charging efficiency P ci and discharge efficiency P di ;

[0095] Obtain the rated capacity Q of the xth backup energy storage battery pack. x Charging efficiency P cx and discharge efficiency Pdx ;

[0096] The replacement factor of the x-th backup energy storage battery pack relative to the ith working energy storage battery pack is calculated using the following formula:

[0097]

[0098] In the formula, k Q , and These are the weighting coefficients for rated capacity, charging efficiency, and discharging efficiency, respectively, σ x-i is the replacement coefficient of the x-th backup energy storage battery pack relative to the ith working energy storage battery pack.

[0099] As a further description of the present invention, the operation of the backup battery selection module also includes:

[0100] Calculate the replacement coefficients of the y backup energy storage battery packs relative to the i-th working energy storage battery pack in sequence, where y is the number of backup energy storage battery packs, and x belongs to y;

[0101] Arrange the replacement coefficients of the y backup energy storage battery packs relative to the i-th working energy storage battery pack in ascending order, and select the backup energy storage battery pack with the smallest replacement coefficient relative to the i-th working energy storage battery pack for replacement.

[0102] Through the above technical solution, when a working energy storage battery pack fails, the rated capacity, charging efficiency, and discharging efficiency of the current working energy storage battery pack are obtained. The rated capacity, charging efficiency, and discharging efficiency of the backup energy storage battery pack are then obtained sequentially. Based on the physical parameters of the failed working energy storage battery pack and all backup energy storage battery packs, the replacement coefficient of each backup energy storage battery pack relative to the failed working energy storage battery pack is calculated. All backup energy storage battery packs are arranged from smallest to largest replacement coefficient relative to the failed working energy storage battery pack, and the backup energy storage battery pack with the smallest replacement coefficient relative to the failed working energy storage battery pack is selected for replacement.

[0103] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the patent coverage of this invention.

Claims

1. An artificial intelligence-based fault monitoring and diagnosis system for energy storage battery packs, characterized in that, The system includes: a data acquisition module, a data processing module, a data analysis module, a fault diagnosis module, and a backup battery selection module; The data acquisition module is used to collect the physical parameters of the energy storage battery pack during its operation and the environmental parameters of the energy storage battery pack, and send them to the data processing module. The data processing module is used to receive data transmitted by the data acquisition module, perform preprocessing to ensure the accuracy and consistency of the data, and send it to the data analysis module. The data analysis module is used to receive the processed data transmitted by the data processing module, perform feature analysis on the data, and send the analysis results to the fault diagnosis module. The fault diagnosis module is used to receive the analysis results from the data analysis module, perform fault diagnosis on the working energy storage battery pack based on the analysis results, and issue real-time warnings based on the diagnosis results. The backup battery selection module is used to automatically select the most suitable backup energy storage battery pack based on artificial intelligence, and switch it according to the real-time warning issued by the fault diagnosis module. The working process of the data acquisition module includes: All working energy storage battery packs are numbered sequentially as: 1, 2, ..., n; Based on sensors installed on the energy storage battery pack, real-time data on the temperature, voltage, and current changes over time during the operation of the working energy storage battery pack are collected. Based on environmental monitoring sensors, environmental impact parameters of the working energy storage battery pack are collected in real time. The working process of the data analysis module includes: The first influencing index of each working energy storage battery pack is obtained based on the temperature, voltage, and current changes over time during the operation of each working energy storage battery pack. A second impact index is obtained for each working energy storage battery pack based on the environmental impact parameters of each energy storage battery pack. The fault diagnosis coefficient of each working energy storage battery pack is obtained based on the first and second influence indicators of each working energy storage battery pack, and fault diagnosis is performed on each working energy storage battery pack according to the fault diagnosis coefficient of each working energy storage battery pack. The process of obtaining the first impact index for each working energy storage battery pack includes: Based on the actual operating conditions of the power system, the working time periods of the working energy storage battery packs within the monitoring period are divided into peak and off-peak periods. Acquire the temperature, voltage, and current changes over time for the i-th working energy storage battery pack during peak and off-peak periods, respectively. The state parameters of the i-th working energy storage battery pack during peak hours are calculated using the following formula: The state parameters of the i-th working energy storage battery pack during the off-peak period are calculated using the following formula: In the formula, t1-t2 is the peak period, t2-t3 is the trough period, and S i1 Let S be the state parameter of the i-th working energy storage battery pack during the peak period. i2 U represents the state parameters of the i-th working energy storage battery pack during the off-peak period; i (t) represents the voltage change data of the i-th working energy storage battery pack over time during the monitoring period. i (t) represents the current variation of the i-th working energy storage battery pack over time during the monitoring period, where T is the current of the i-th working energy storage battery pack. i (t) represents the temperature change data of the i-th working energy storage battery pack over time during the monitoring period; k1, k2 and k3 are the voltage, current and corresponding weighting coefficients, respectively, and i belongs to n; Based on the state parameters S of the i-th working energy storage battery pack during peak hours i1 The state parameters S of the i-th working energy storage battery pack during the off-peak period i2 Construct a mathematical model for the first influencing index of the i-th working energy storage battery pack: In the formula, α and β are the weighting coefficients corresponding to the peak and trough periods, respectively, and α > β > 0, R i1 The first impact indicator for the i-th working energy storage battery pack; The process of obtaining the second impact index for each working energy storage battery pack includes: Obtain the environmental parameters of the working environment of the i-th working energy storage battery pack, and construct a mathematical model of the second influencing index of the i-th working energy storage battery pack based on the environmental parameters: In the formula, m is the total number of environmental parameters, j belongs to [1, m], and E j Let E be the physical quantity of the j-th environmental parameter. j0 The standard value of the j-th environmental parameter set for the system, ΔE kth ε is the reference value for the difference of the j-th environmental parameter. j R represents the weighting coefficient corresponding to the j-th environmental parameter. i2 This is the second impact indicator for the i-th working energy storage battery pack.

2. The artificial intelligence-based energy storage battery pack fault monitoring and diagnosis system according to claim 1, characterized in that, The process of fault diagnosis for each working energy storage battery pack includes: The mathematical model for the fault diagnosis coefficients of the i-th working energy storage battery pack is constructed, and its expression is: In the formula, δ and ρ are the weighting coefficients corresponding to the first and second influencing indicators, respectively, and μ i Let be the fault diagnosis coefficient of the i-th working energy storage battery pack; The fault diagnosis coefficient μ of the i-th working energy storage battery pack i The fault diagnosis coefficient threshold μ of the i-th working energy storage battery pack set by the system thi Compare, if μ i Greater than or equal to μ thi If the i-th working energy storage battery pack fails, the backup energy storage battery pack must be activated immediately and an early warning must be issued immediately; otherwise, the i-th working energy storage battery pack has not failed. The fault diagnosis coefficient of each working energy storage battery pack is calculated sequentially, and the fault diagnosis of the corresponding working energy storage battery pack is performed based on the fault diagnosis coefficient of each working energy storage battery pack.

3. The artificial intelligence-based energy storage battery pack fault monitoring and diagnosis system according to claim 2, characterized in that, The operation of the backup battery selection module includes: When the i-th working energy storage battery pack fails, obtain the rated capacity Q of the i-th working energy storage battery pack. i Charging efficiency P ci and discharge efficiency P di ; Obtain the rated capacity Q of the xth backup energy storage battery pack. x Charging efficiency P cx and discharge efficiency P dx ; The replacement factor of the x-th backup energy storage battery pack relative to the ith working energy storage battery pack is calculated using the following formula: In the formula, k Q , and These are the weighting coefficients for rated capacity, charging efficiency, and discharging efficiency, respectively, σ x-i is the replacement coefficient of the x-th backup energy storage battery pack relative to the ith working energy storage battery pack.

4. The artificial intelligence-based energy storage battery pack fault monitoring and diagnosis system according to claim 3, characterized in that, The operation of the backup battery selection module also includes: Calculate the replacement coefficients of the y backup energy storage battery packs relative to the i-th working energy storage battery pack in sequence, where y is the number of backup energy storage battery packs, and x belongs to y; Arrange the replacement coefficients of the y backup energy storage battery packs relative to the i-th working energy storage battery pack in ascending order, and select the backup energy storage battery pack with the smallest replacement coefficient relative to the i-th working energy storage battery pack for replacement.

Images