A battery health monitoring method and system based on an energy storage platform

Abstract

The application discloses a kind of battery health monitoring method and system based on energy storage platform, specifically relates to battery health monitoring technical field;It is through the real-time acquisition of energy storage platform in battery system single battery cell's electric quantity characteristic parameter, state characteristic parameter and operating environment parameter, establishes basic data information base, and calculates the charging energy achievement rate of battery system, identifies current operating state;Again, the potential failure risk is determined by charging energy achievement rate determination potential failure level;According to potential failure level and current operating state, the cumulative charge-discharge capacity of single battery cell is periodically sampled, and the actual energy of battery system is calculated;While combining historical failure data to predict failure trend, determine periodic fault type;Finally, based on actual energy and periodic fault type analysis energy attenuation trend, generate corresponding maintenance strategy and alarm information, improve the security and operation intelligent level of battery system under energy storage platform.

Description

Technical Field

[0001] This invention relates to the field of battery health monitoring technology, and more specifically, to a battery health monitoring method and system based on an energy storage platform. Background Technology

[0002] Energy storage platforms are widely used in the field of power energy storage as an important means of monitoring and managing the operation of battery systems.

[0003] Existing energy storage platforms can typically collect basic operating data and display simple status of battery systems, but they cannot reflect the true health status of the battery system. This makes it impossible for energy storage platforms to perform targeted proactive maintenance and fault warnings, thus limiting the safe and stable operation of the battery system. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a battery health monitoring method and system based on an energy storage platform to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A battery health monitoring method based on an energy storage platform includes the following steps:

[0007] By collecting the energy characteristic parameters, state characteristic parameters and operating environment parameters of individual cells in the battery system in real time through the energy storage platform, a basic data information database of the battery system is established.

[0008] Based on the battery system's basic data information database, the charging energy achievement rate of the battery system is calculated, and the current operating status of the battery system is identified.

[0009] Fault prediction is based on the charging energy achievement rate of the battery system. When the charging energy achievement rate of the battery system is lower than a predetermined threshold, it is determined that there is a potential fault risk in the battery system, and the potential fault level of the battery system is determined.

[0010] Based on the potential fault level and current operating status of the battery system, the cumulative charge and discharge amount of the individual cells in the battery system is periodically sampled, and the actual energy of the battery system is calculated based on the full charge and discharge state data of adjacent cells.

[0011] Based on historical fault data of the battery system, the fault trend of the battery system is predicted, and the periodic fault types of the battery system are determined.

[0012] Based on the actual energy and periodic fault types of the battery system, the energy decay trend of the battery system is analyzed, and maintenance strategies and alarm information for the battery system are generated.

[0013] In a preferred embodiment, the energy storage platform collects the energy characteristic parameters, state characteristic parameters, and operating environment parameters of individual cells in the battery system in real time to establish a basic data information database for the battery system, specifically:

[0014] The energy storage platform collects the energy characteristic parameters, state characteristic parameters, and operating environment parameters of each individual cell in the battery system in real time.

[0015] A basic data information database for battery systems is constructed based on energy characteristic parameters, state characteristic parameters, and operating environment parameters.

[0016] In a preferred embodiment, the power characteristic parameters include the cumulative charge, cumulative discharge, and maximum charge of each individual cell in the battery system; the state characteristic parameters include the state of charge of each individual cell in the battery system; and the operating environment parameters include the cell voltage and cell temperature of each individual cell in the battery system.

[0017] In a preferred embodiment, the charging energy achievement rate of the battery system is calculated based on the battery system basic data information database, and the current operating state of the battery system is identified, specifically as follows:

[0018] Based on the battery system basic data information database, calculate the maximum charge of each individual cell in the battery system during the daily operating cycle.

[0019] Based on the power load requirements of the battery system and the battery charging and discharging operation strategy, the calendar energy of the battery system is preset;

[0020] The battery system's charging energy achievement rate is obtained by calculating the ratio of the battery system's maximum daily charging amount to the pre-set calendar energy of the battery system.

[0021] The current operating status of the battery system is determined based on the charging energy achievement rate of the battery system.

[0022] In a preferred embodiment, fault prediction is performed based on the battery system's charging energy achievement rate. When the battery system's charging energy achievement rate is lower than a predetermined threshold, it is determined that the battery system has a potential fault risk, and the potential fault level of the battery system is determined, specifically as follows:

[0023] The charging energy achievement rate of the battery system is compared with the charging energy achievement rate threshold preset by the energy storage platform in real time.

[0024] When the charging energy achievement rate of the battery system is lower than the charging energy achievement rate threshold preset by the energy storage platform, it is determined that there is a potential risk of failure in the battery system.

[0025] When a potential fault risk is identified in the battery system, the potential fault level of the battery system is determined based on the operating environment parameters in the battery system basic data information database.

[0026] In a preferred embodiment, based on the potential fault level and current operating state of the battery system, the cumulative charge and discharge quantities of individual cells in the battery system are periodically sampled, and the actual energy of the battery system is calculated based on the full charge and discharge state data of adjacent cells, specifically:

[0027] The sampling period is set based on the potential fault level and current operating status of the battery system;

[0028] Within each sampling period, the cumulative charge and discharge amounts of each individual cell in the battery system under fully discharged and fully charged states are extracted from the battery system basic data information database.

[0029] The actual energy of the battery system is calculated based on the cumulative charge and discharge of each individual cell in the fully discharged and fully charged states.

[0030] In a preferred embodiment, based on historical fault data of the battery system, the fault trend of the battery system is predicted to determine the periodic fault type of the battery system, specifically:

[0031] Based on historical fault data of battery systems, a fault trend prediction model is established using regression analysis.

[0032] Input the power characteristic parameters, status characteristic parameters and operating environment parameters obtained in the current sampling period into the fault trend prediction model, and output the fault trend prediction results;

[0033] Based on the fault occurrence time interval and fault type identifier in the fault trend prediction results, the periodic characteristics of the prediction results are analyzed to determine the periodic fault types of the battery system.

[0034] In a preferred embodiment, based on the actual energy of the battery system and the type of periodic faults, the energy decay trend of the battery system is analyzed to generate a maintenance strategy and alarm information for the battery system, specifically:

[0035] Obtain the actual energy and rated energy of the battery system;

[0036] Calculate the energy retention rate between actual energy and rated energy;

[0037] The energy retention rate is compared with the energy decay threshold table to generate an energy decay level;

[0038] The energy degradation level is correlated and matched with the periodic failure type of the battery system to form a set of maintenance requirement data;

[0039] Based on the maintenance requirement data set, the maintenance rule base is invoked to generate a maintenance strategy;

[0040] Alarm information is generated based on the energy decay level and the periodic fault type of the battery system.

[0041] On the other hand, the present invention provides a battery health monitoring system based on an energy storage platform, comprising:

[0042] Data acquisition module: Collects the energy characteristic parameters, state characteristic parameters and operating environment parameters of individual cells in the battery system in real time through the energy storage platform, and establishes a basic data information database for the battery system;

[0043] Operation identification module: Based on the battery system basic data information database, calculate the charging energy achievement rate of the battery system and identify the current operating status of the battery system;

[0044] Fault prediction module: Based on the charging energy achievement rate of the battery system, fault prediction is performed. When the charging energy achievement rate of the battery system is lower than a predetermined threshold, it is determined that there is a potential fault risk in the battery system and the potential fault level of the battery system is determined.

[0045] Energy Calculation Module: Based on the potential fault level and current operating status of the battery system, the module periodically samples the cumulative charge and discharge amount of individual cells in the battery system, and calculates the actual energy of the battery system based on the full charge and discharge status data of adjacent cells.

[0046] Fault prediction module: Based on historical fault data of the battery system, predict the fault trend of the battery system and determine the periodic fault types of the battery system;

[0047] Strategy generation module: Based on the actual energy of the battery system and the types of periodic faults, it analyzes the energy decay trend of the battery system and generates maintenance strategies and alarm information for the battery system.

[0048] The technical effects and advantages of the battery health monitoring method and system based on an energy storage platform of the present invention are as follows:

[0049] By collecting real-time energy characteristic parameters, state characteristic parameters, and operating environment parameters of individual battery cells through the energy storage platform, a comprehensive time-series basic data information database is formed, enabling refined monitoring of the battery system's health status. Based on the basic data information database, the charging energy achievement rate is calculated and the operating status is identified, effectively reflecting fluctuations in charge and discharge performance. Potential fault risks are determined and classified by comparing the charging energy achievement rate with predetermined thresholds, enabling early warning. The cumulative charge and discharge volume is periodically sampled and the actual energy is calculated by combining potential fault levels and operating status, accurately quantifying energy decay. A fault trend prediction model is built based on historical fault data to determine the types of periodic faults, realizing the mining of periodic fault patterns. Finally, maintenance strategies and alarm information are generated based on the analysis of actual energy decay trends and periodic fault types, realizing the transformation from passive detection to proactive operation and maintenance, improving the operational safety and maintenance efficiency of the battery system. Attached Figure Description

[0050] Figure 1 This is a schematic diagram of a battery health monitoring method based on an energy storage platform according to the present invention;

[0051] Figure 2 This is a schematic diagram of the structure of a battery health monitoring system based on an energy storage platform according to the present invention. Detailed Implementation

[0052] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0053] Example 1

[0054] Figure 1 This invention provides a battery health monitoring method based on an energy storage platform, which includes the following steps:

[0055] By collecting the energy characteristic parameters, state characteristic parameters and operating environment parameters of individual cells in the battery system in real time through the energy storage platform, a basic data information database of the battery system is established.

[0056] Based on the battery system's basic data information database, the charging energy achievement rate of the battery system is calculated, and the current operating status of the battery system is identified.

[0057] Fault prediction is based on the charging energy achievement rate of the battery system. When the charging energy achievement rate of the battery system is lower than a predetermined threshold, it is determined that there is a potential fault risk in the battery system, and the potential fault level of the battery system is determined.

[0058] Based on the potential fault level and current operating status of the battery system, the cumulative charge and discharge amount of the individual cells in the battery system is periodically sampled, and the actual energy of the battery system is calculated based on the full charge and discharge state data of adjacent cells.

[0059] Based on historical fault data of the battery system, the fault trend of the battery system is predicted, and the periodic fault types of the battery system are determined.

[0060] Based on the actual energy and periodic fault types of the battery system, the energy decay trend of the battery system is analyzed, and maintenance strategies and alarm information for the battery system are generated.

[0061] By collecting real-time energy characteristic parameters, state characteristic parameters, and operating environment parameters of individual cells in the battery system through an energy storage platform, a basic data information database for the battery system is established, including:

[0062] The energy storage platform collects the energy characteristic parameters, state characteristic parameters, and operating environment parameters of each individual cell in the battery system in real time.

[0063] A basic data information database for battery systems is constructed based on energy characteristic parameters, state characteristic parameters, and operating environment parameters.

[0064] Specifically, the energy storage platform collects the energy characteristic parameters, state characteristic parameters, and operating environment parameters of each individual cell in the battery system in real time at a pre-set data acquisition frequency. The data acquisition frequency is determined based on the operating strategy requirements of the energy storage platform and the acquisition interval recommended by the battery system manufacturer. For example, for energy storage platform application scenarios, a reasonable data acquisition frequency range can be determined by statistically analyzing the rate of change of historical data during battery system operation and using the relationship curve between the rate of change and the acquisition frequency. When the operating environment parameters of individual cells in the battery system change rapidly per unit time, a higher data acquisition frequency is set, such as once every 1 second; when the operating environment parameters of individual cells in the battery system change slowly, a relatively lower data acquisition frequency is set, such as once every 10 seconds.

[0065] After determining the data acquisition frequency, the energy storage platform performs real-time data acquisition and transmission according to the data communication protocol between the battery system and the energy storage platform. The energy storage platform collects the charge characteristic parameters, state characteristic parameters, and operating environment parameters of each individual battery cell in real time through data acquisition sensors deployed near the individual battery cells. These data acquisition sensors include, but are not limited to, voltage sensors, temperature sensors, current sensors, and state monitoring sensors. The data acquisition sensors convert analog signals into digital signals and upload the collected charge characteristic parameters, state characteristic parameters, and operating environment parameters to the energy storage platform's data server via the battery management system. For example, the selection criteria for voltage sensors are: based on the voltage range of the cell type, the range and measurement accuracy of the voltage sensor are determined. If the voltage of a single battery cell varies within the range of 3.0 to 4.2 volts, a voltage sensor with a measurement range of 0 to 5 volts is selected to ensure the accuracy of the measurement data. Temperature sensors are placed at predetermined locations on the surface of the individual battery cell. The location is determined based on the heat dissipation distribution characteristics of the cell, for example, placed in the center of the cell casing to obtain temperature data representing the overall temperature state of the cell.

[0066] The collected energy characteristic parameters include the cumulative charge, cumulative discharge, and maximum charge of each individual cell in the battery system. The cumulative charge refers to the total amount of energy accumulated by each individual cell from installation and commissioning to the current time of data collection; the cumulative discharge refers to the total amount of energy accumulated by each individual cell from installation and commissioning to the current time of data collection. The cumulative charge and discharge are obtained by measuring the current flowing through the cell in real time using a current sensor and integrating the current value over time. The maximum charge is defined as the amount of energy that each individual cell can actually receive and store during its most recent complete full discharge to full charge cycle.

[0067] The state characteristic parameter is the state of charge (SOC) of each individual cell in the battery system. The SOC is defined as the ratio of the actual amount of energy stored in each individual cell at the time of data acquisition to its rated energy: the actual amount of energy stored is calculated based on the difference between the cumulative charge and cumulative discharge, and then compared with the rated energy recorded when the individual cell of the battery system was initially put into operation to obtain the SOC parameter.

[0068] Operating environment parameters include the cell voltage and cell temperature of each individual cell in the battery system. The cell voltage refers to the actual voltage measured at the positive and negative terminals of each individual cell at the time of data acquisition, measured in real-time by a voltage sensor. The cell temperature refers to the actual surface temperature of the individual cell measured at the location of a temperature sensor at the time of data acquisition.

[0069] Data cleaning and verification are performed on power characteristic parameters, state characteristic parameters, and operating environment parameters. Data cleaning includes anomaly identification and processing. For example, for cell voltage data collected from individual cells, if the cell voltage exceeds the normal operating range, it is identified as anomaly data. This anomaly data is then processed using linear interpolation or the average of preceding and following valid data to generate processed valid data. Data verification refers to confirming the rationality of the data through data verification rules (such as the correspondence between voltage and state of charge) set in the energy storage platform server, ensuring the validity of the data.

[0070] The battery system's basic data information database is constructed as follows: independent data records are created for each individual battery cell. Each data record is indexed by a timestamp and includes the current energy characteristic parameters, state characteristic parameters, and operating environment parameters at the time of collection, forming a time-series data structure. The data records are continuously updated within each sampling period.

[0071] Based on the battery system's basic data database, the charging energy achievement rate of the battery system is calculated, and the current operating status of the battery system is identified, including:

[0072] Based on the battery system basic data information database, calculate the maximum charge of each individual cell in the battery system during the daily operating cycle.

[0073] Specifically, based on the predefined operating cycle of the energy storage platform, the cumulative charging data of each individual cell recorded in the battery system's basic data information database is sorted by timestamp within the operating cycle. The cumulative charging data at the start and end times of each day's operating cycle is extracted to determine the daily cumulative charging change value within the operating cycle. The method for determining the start and end times of the daily operating cycle is as follows: based on the preset power load characteristics and battery charging and discharging operation strategy requirements of the energy storage platform. For example, if the energy storage platform where the battery system is located uses a once-a-day charge-discharge cycle strategy, the operating cycle is set to 24 hours, starting at midnight each day and ending at midnight the following day. If it uses a multiple-charge-discharge cycle strategy, multiple charge-discharge cycles are set according to the operating strategy, and calculations are performed for each cycle separately. For example, under a 1.5-cycle strategy, each day has two operating cycles: midnight to 4 PM and 4 PM to midnight the following day. The cumulative charging change values ​​within each of these two cycles are extracted and calculated to determine the cumulative charging amount for the corresponding operating cycle.

[0074] After determining the operating cycle, the cumulative charge at the start of each operating cycle is used as the baseline data, and the cumulative charge at the end of the operating cycle is extracted. The difference between the two is the actual charge within the operating cycle. The charge data from multiple operating cycles are compared, and the largest charge is selected as the maximum charge for each individual cell in the battery system within the day's operating cycle. The process of determining the maximum charge requires traversing the cumulative charge data for each individual cell across all operating cycles in the battery system's basic data database for that day, sorting the calculated charge for all operating cycles, and selecting the largest charge among the sorted results. For example, under a 1.5-cycle-per-day strategy, if the calculated charge for the first operating cycle is 95 amp-hours and the calculated charge for the second operating cycle is 60 amp-hours, then the 95 amp-hours calculated in the first operating cycle is determined as the maximum charge for that day.

[0075] Based on the power load requirements of the battery system and the battery charging and discharging operation strategy, the calendar energy of the battery system is preset;

[0076] Specifically, the method for determining calendar energy is as follows: It is pre-set based on the power load requirements of the energy storage platform where the battery system resides and the battery charging / discharging operation strategy. Power load requirements refer to the power demand parameters of the energy storage platform corresponding to the battery system's operation, such as the load type, load power, and load duration. The battery charging / discharging operation strategy refers to the charging / discharging cycle frequency, discharge depth, and charging limitations set by the energy storage platform for the battery system. The setting process is as follows: The daily power demand is obtained through analysis of historical operating data from the energy storage platform; the charge / discharge cycle multiple is determined based on the number of charge / discharge cycles set by the energy storage platform for the battery system. For example, if the energy storage platform adopts a strategy of one full charge / discharge cycle per day, the charge / discharge cycle multiple is set to 1; if the energy storage platform adopts a strategy of 1.5 charge / discharge cycles per day, the charge / discharge cycle multiple is set to 1.5; then, the daily power demand is multiplied by the determined charge / discharge cycle multiple to finally obtain the calendar energy of the battery system. For example, if the daily electricity demand of the energy storage platform is 1000 kWh and the daily charge-discharge cycle strategy is determined to be 1 cycle, then the calendar energy is set to 1000 kWh; if the daily cycle strategy is 1.5 cycles, then the calendar energy is determined to be 1500 kWh.

[0077] The battery system's charging energy achievement rate is obtained by calculating the ratio of the battery system's maximum daily charging amount to the pre-set calendar energy of the battery system.

[0078] Specifically, the maximum daily charging amount and calendar energy are obtained to calculate the charging energy achievement rate. The charging energy achievement rate is defined as the ratio of the maximum daily charging amount to the calendar energy, used to indicate the degree to which the planned charging target for the day has been achieved. The preset qualified threshold for the charging energy achievement rate is determined as follows: based on historical operating data, the correlation between the achievement rate and battery health is analyzed to determine a suitable threshold to ensure safe operation, for example, it can be set to 90%. It is then determined whether the charging energy achievement rate has reached the preset qualified threshold. If the charging energy achievement rate has reached the preset qualified threshold, the assessment for the day ends; if the charging energy achievement rate has not reached the preset qualified threshold, transformer energy matching analysis, load power utilization analysis, battery energy analysis, and cell data analysis are performed.

[0079] The transformer energy matching degree analysis is specifically as follows: the ratio of the average charging power during the charging period to the transformer energy is calculated and then multiplied by a safety factor. The safety factor is determined based on the statistical analysis of historical operating data. For example, if the safety factor is set to 0.9, and the transformer energy matching degree is lower than the safety factor, a prompt indicating that the transformer energy is too low will be output.

[0080] The load power utilization analysis specifically involves calculating the ratio of the average discharge power during the discharge period to the load demand power. If the ratio is less than the historical stable operating threshold, for example, if the historical stable operating threshold is set to 0.8, then an insufficient load power prompt will be output.

[0081] Battery energy analysis specifically involves the following steps: If the battery energy achievement rate remains below a set threshold for an extended period, cell data analysis is initiated; if the energy achievement rate is normal but fluctuations are abnormal, energy degradation verification is performed. The energy degradation verification method involves calculating the actual charge-discharge energy difference for the day and comparing it with historical adjacent full-charge-discharge energies. If the difference exceeds an error threshold (e.g., a 5% error threshold), the data collection period and state-of-charge threshold are rechecked; otherwise, a normal energy degradation trend is confirmed.

[0082] Cell data analysis uses time-series data of individual cells as input to calculate the voltage and temperature ranges of individual cells at the same time point, denoted as voltage range A and temperature range B, respectively. A smoothed reference value for the voltage and temperature ranges is obtained using a moving window averaging method to eliminate short-term spike interference. In cell data analysis, graded handling is implemented based on trigger conditions such as abnormal terminal voltage, widening energy differences between individual cells, and deviations in state-of-charge estimation. Battery balancing is initiated when the balancing conditions are met; if balancing fails to restore consistency and the anomaly is concentrated in a sub-cluster, battery pack replacement is performed; if the anomaly is chain-like and affects branches, the entire cluster is replaced.

[0083] The current operating status of the battery system is determined based on the charging energy achievement rate of the battery system.

[0084] Specifically, by statistically analyzing historical operational data of the energy storage platform, a threshold table for classifying battery system operating status levels is constructed. This table includes a mapping relationship between multiple charging energy achievement rate ranges and their corresponding operating status levels. The currently calculated charging energy achievement rate of the battery system is compared with this threshold table to determine the current operating status level of the battery system. For example, the threshold table is set as follows: when the charging energy achievement rate is greater than or equal to 95%, the operating status level is defined as normal; when the charging energy achievement rate is between 85% and 95%, the operating status level is defined as slightly abnormal; when the charging energy achievement rate is between 70% and 85%, the operating status level is defined as abnormal; and when the charging energy achievement rate is less than 70%, the operating status level is defined as severely abnormal. Therefore, if the current charging energy achievement rate of the battery system is calculated to be 96.67%, the current operating status of the battery system is determined to be normal.

[0085] Fault prediction is based on the battery system's charging energy achievement rate. When the battery system's charging energy achievement rate is lower than a predetermined threshold, it is determined that the battery system has a potential fault risk, and the potential fault level of the battery system is determined, including:

[0086] The charging energy achievement rate of the battery system is compared with the charging energy achievement rate threshold preset by the energy storage platform in real time.

[0087] When the charging energy achievement rate of the battery system is lower than the charging energy achievement rate threshold preset by the energy storage platform, it is determined that there is a potential risk of failure in the battery system.

[0088] Specifically, the charging energy achievement rate of the battery system obtained in each sampling period is compared in real time with the charging energy achievement rate threshold preset by the energy storage platform. The method for setting the charging energy achievement rate threshold includes statistical analysis of a large amount of sample data in the early stage of battery system operation, combined with the standard charging volume requirements under different operating environments, to establish a correlation mapping curve between the charging energy achievement rate and the actual operating health status, and selecting the inflection point region where accuracy and recall are maximized as the recommended threshold range. For example, the charging energy achievement rate threshold is set separately according to different battery types, different energy specifications and energy storage platform operation strategies. For battery systems with energy in the range of 100 kWh to 1000 kWh, the charging energy achievement rate threshold is set to 90% to 95% through big data training and comprehensive adjustment based on expert experience, and 92% is used as the initial application threshold in actual settings.

[0089] If the calculated charging energy achievement rate of the battery system in the current cycle is 88%, which is less than the charging energy achievement rate threshold of 92%, then the battery system is considered not to have reached its ideal charging capacity, and there is a potential risk of failure. If the charging energy achievement rate of the battery system is greater than or equal to the charging energy achievement rate threshold, then the battery system is considered to be in a healthy or normal operating state.

[0090] When the charging energy achievement rate is lower than the pre-set threshold of the energy storage platform, the battery system is deemed to have a potential fault risk. To prevent misjudgment based on occasional abnormal data, a multi-cycle superposition judgment method is adopted. That is, a potential fault risk judgment is only triggered when the charging energy achievement rate is lower than the threshold for multiple consecutive cycles (e.g., 3 consecutive sampling cycles). The number of cycles is set by the energy storage platform parameters and optimized according to actual application needs. For example, by statistically analyzing historical operation case data, the number of cycles with the lowest misjudgment rate is selected for application configuration.

[0091] When a potential fault risk is identified in the battery system, the potential fault level of the battery system is determined based on the operating environment parameters in the battery system basic data information database.

[0092] Specifically, the operating environment parameters include the real-time cell voltage and cell temperature of each individual battery cell. The grading of cell voltage and temperature is based on: statistically analyzing the typical distribution ranges of each parameter during the charging and discharging processes of historical healthy and faulty battery systems, and using box plots or standard deviation statistics to define safe operating ranges and risk ranges. The typical safe operating range for cell voltage can be set to 2.8 to 4.2 volts, and the typical safe operating range for cell temperature can be set to 10 to 40 degrees Celsius. For example, if, within the potential fault assessment period, the cell voltage of an individual battery cell in the battery system continuously deviates from the normal range, and the cell temperature abnormally rises by more than 45 degrees Celsius, the potential fault level of the battery system is determined to be high-risk; if the cell voltage of an individual battery cell in the battery system is within the normal range, the potential fault level of the battery system is determined to be low-risk; otherwise, the potential fault level of the battery system is determined to be medium-risk.

[0093] Based on the potential fault level and current operating state of the battery system, the cumulative charge and discharge capacity of individual cells in the battery system is periodically sampled, and the actual energy of the battery system is calculated based on the full charge and discharge state data of adjacent cells, including:

[0094] The sampling period is set based on the potential fault level and current operating status of the battery system;

[0095] Specifically, the sampling period is determined as follows: By statistically analyzing the changes in the cumulative charge and discharge of individual cells under different potential fault levels in historical operating data, a Discrete Fourier Transform is used to extract the significant change periods of the energy characteristic parameters at different time scales, which serve as a reference for setting the sampling period. For example, if the potential fault level of the battery system is high-risk, indicating drastic changes in cell parameters, a shorter sampling period is set to be used to accurately monitor the energy changes of the battery system in real time, such as 1 to 2 hours. If the potential fault level of the battery system is medium-risk, the sampling period is appropriately extended, such as 4 to 8 hours. If the potential fault level of the battery system is low-risk, the sampling period is further extended, such as 12 to 24 hours.

[0096] Within each sampling period, the cumulative charge and discharge amounts of each individual cell in the battery system under fully discharged and fully charged states are extracted from the battery system basic data information database.

[0097] Specifically, within each sampling period, the energy storage platform's data server extracts the cumulative charge and discharge data for each individual battery cell, using the start and end times of the sampling period as time windows. The cumulative charge data for each individual cell represents the total amount of electricity charged since the battery system was installed and put into operation until the sampling time, while the cumulative discharge data represents the total amount of electricity discharged since the battery system was installed and put into operation until the sampling time. Both are recorded in the battery system's basic data information database.

[0098] After extracting the cumulative charge and discharge data, the full charge and full discharge states at the time of the sampling are accurately determined based on the battery system state of charge (SOC) data in the battery system basic data information database. A full charge state is defined as the SOC value of a single cell reaching the preset full charge threshold of the energy storage platform; for example, a SOC of 95% to 100% is considered a full charge state. A full discharge state is defined as the SOC value of a single cell dropping to the preset full discharge threshold of the energy storage platform; for example, a SOC below 5% to 10% is considered a full discharge state. The determination method for the full charge and full discharge thresholds is as follows: based on the cell characteristic curve data provided by the battery system manufacturer, combined with the actual operating conditions of the battery system on the energy storage platform (including temperature conditions, charge / discharge rate requirements, etc.), the threshold range that maximizes the battery system's lifespan and meets the operational requirements of the energy storage platform is determined through experiments or historical data statistics.

[0099] Based on the above determination method, a pair of data points is established for the fully discharged state within two consecutive sampling periods and the subsequent fully charged state. For example, in one sampling period, if the state of charge of a single cell drops from 95% to 5%, the cumulative charge and discharge data at the end of the sampling period are the fully discharged state data; in the next sampling period, if the state of charge of a single cell rises back from 5% to above 95%, the cumulative charge and discharge data at the end of the sampling period are the fully charged state data.

[0100] The actual energy of the battery system is calculated based on the cumulative charge and discharge of each individual cell in the fully discharged and fully charged states.

[0101] Specifically, the actual energy of the battery system is calculated based on the full charge and discharge state data of adjacent cells: Actual energy of the battery system = Cumulative charge at full charge state - Cumulative charge at full discharge state - Cumulative discharge at full charge state + Cumulative discharge at full discharge state.

[0102] To obtain the overall actual energy data, the actual energy of each individual cell is calculated separately, and then the actual energy data of all individual cells are summed or averaged to obtain the overall actual energy of the battery system. For example, if the battery system consists of multiple individual cells with the same energy, the actual energy is obtained by averaging; if the battery system consists of multiple individual cells with different energy, the actual energy of the individual cells is weighted according to the rated energy of each cell, ensuring that the calculated actual energy accurately reflects the overall usable energy of the battery system.

[0103] Meanwhile, in order to improve the accuracy and stability of the calculation, an energy calculation data verification is designed in the energy storage platform data server to verify the rationality of the calculated actual energy: the calculated actual energy is compared with the historical energy data calculated by the battery system. If the difference between the newly calculated actual energy and the previous actual energy exceeds the set threshold range, such as the difference exceeding 15%, a secondary data verification is automatically triggered. The verification includes reconfirmation of the sampled data and re-verification of the accuracy of the full charge and discharge status determination.

[0104] Based on historical failure data of the battery system, the failure trend of the battery system is predicted, and the types of periodic failures of the battery system are determined, including:

[0105] Based on historical fault data of battery systems, a fault trend prediction model is established using regression analysis.

[0106] Specifically, the selection process for historical fault data is as follows: Since the battery system was put into operation, the energy storage platform has recorded each fault event. Each record includes the time of the fault occurrence, the corresponding energy characteristic parameters, state characteristic parameters, operating environment parameters, and the identified fault type. To ensure the effectiveness and representativeness of the prediction model, the historical fault data is screened as follows: First, random fault events caused by external factors are excluded, and fault events with inherent correlation characteristics are included in the analysis scope. For example, fault events caused by a single cell being exposed to a high-temperature environment for a long time, a cell voltage deviating from the standard range for a long time, or abnormal charge-discharge cycles of a single cell are included. This ensures that the selected dataset can accurately reflect the inherent laws of battery system fault trends.

[0107] Historical fault data undergoes preprocessing, including data normalization, missing data interpolation, and outlier detection and handling. Data normalization specifically involves normalizing the power characteristic parameters (cumulative charging, cumulative discharging, maximum battery charging), state characteristic parameters (state of charge), and operating environment parameters (cell voltage, cell temperature) according to their maximum and minimum values ​​to unify the units and value ranges. For example, all parameters are normalized to the range of 0 to 1. Missing data interpolation involves filling in missing data records using interpolation methods, such as linear interpolation or interpolation based on the average of adjacent time periods, to ensure the integrity of the dataset. Outlier detection and handling involves using the standard deviation method to detect outliers. Data points deviating from the dataset mean by more than a set threshold (e.g., three standard deviations) are identified as outliers and removed. After preprocessing, a high-quality historical fault dataset for regression analysis is obtained.

[0108] Regression analysis methods include, but are not limited to, linear regression, multinomial regression, and ridge regression. The method is determined based on the model's accuracy and computational efficiency requirements. A nonlinear correlation exists between battery system failure trends and cell voltage, cell temperature, cumulative charge, cumulative discharge, and state of charge. Therefore, multinomial regression, which effectively describes this nonlinear relationship, is chosen for model construction. Specifically, the multinomial regression analysis involves: first, determining the relationship between each input parameter (charge characteristic parameters, state characteristic parameters, and operating environment parameters) and the failure type. By statistically analyzing historical failure data, the Pearson correlation coefficient method is used to analyze the significant relationship between each input parameter and the failure type, identifying parameters with strong correlations as model input features. Using the selected input parameters as independent variables and the historical failure occurrence time and failure type as dependent variables, the coefficients of the multinomial regression equation are determined using the least squares method. The coefficients are determined by dividing historical data into training and validation datasets, and using cross-validation to determine the optimal model parameter values. The optimal coefficient combination exhibits the minimum prediction error on the validation dataset. The mean squared error (MSE) index is used to evaluate the model error.

[0109] Input the power characteristic parameters, status characteristic parameters and operating environment parameters obtained in the current sampling period into the fault trend prediction model, and output the fault trend prediction results;

[0110] Specifically, after receiving the input parameters, the fault trend prediction model outputs the prediction results, including the fault occurrence time interval and the fault type identifier. The fault occurrence time interval is the time difference between the predicted time of the next possible fault, based on historical fault trends, and the current time, expressed in hours. The fault type identifier is the type of fault predicted by the fault trend prediction model, such as cell overheating, abnormal cell voltage, or battery energy degradation.

[0111] Based on the fault occurrence time interval and fault type identifier in the fault trend prediction results, the periodic characteristics of the prediction results are analyzed to determine the periodic fault types of the battery system.

[0112] Specifically, the periodic characteristic analysis method is as follows: Using historical fault event records, the recurrence intervals of similar fault events during historical operation are statistically analyzed. Fourier spectrum analysis is then used to determine the dominant and secondary frequencies of this type of fault event, thereby confirming the fault cycle. For example, if the dominant frequency of the same type of fault event in historical data is once every 7 days, and the secondary frequency is once every 14 days, then this fault type can be identified as having periodic characteristics, and the cycle can be determined to be 7 days or 14 days. The final cycle value is determined based on the significance of the fault occurrence frequency, and the cycle value is confirmed by comparing the peak intensity of the power spectral density curve. Based on the results of the periodic characteristic analysis, the periodic fault type of the battery system is determined and recorded in the periodic fault type field of the battery system basic data information database.

[0113] Based on the actual energy level and cyclical fault types of the battery system, the energy degradation trend of the battery system is analyzed, and maintenance strategies and alarm information for the battery system are generated, including:

[0114] Obtain the actual energy and rated energy of the battery system;

[0115] Calculate the energy retention rate between actual energy and rated energy;

[0116] The energy retention rate is compared with the energy decay threshold table to generate an energy decay level;

[0117] The energy degradation level is correlated and matched with the periodic failure type of the battery system to form a set of maintenance requirement data;

[0118] Based on the maintenance requirement data set, the maintenance rule base is invoked to generate a maintenance strategy;

[0119] Alarm information is generated based on the energy decay level and the periodic fault type of the battery system.

[0120] Specifically, the rated energy data of the battery system comes from the initial energy stored in the energy storage platform database when the battery system is initially put into operation. It is determined and provided by the battery system manufacturer based on the initial delivery energy of the battery system under standard test conditions. The unit is either ampere-hour or kilowatt-hour, depending on the requirements of the energy storage platform for the battery energy representation method. For example, the rated energy of the battery system is 1000 kilowatt-hours.

[0121] After obtaining the rated energy data of the battery system, the energy retention rate between the actual energy and the rated energy is calculated. The energy retention rate is calculated by dividing the actual energy obtained in each sampling period by the rated energy of the battery system. For example, if the calculated actual energy of the battery system in the current sampling period is 900 kWh and the rated energy is 1000 kWh, then the energy retention rate is 90%.

[0122] The calculated energy retention rate is compared with a pre-defined energy degradation threshold table to generate an energy degradation level. The energy degradation threshold table is constructed as follows: based on actual operating experience of the battery system, the energy degradation risk level of the battery system corresponding to different energy retention rates is statistically analyzed, and the degradation risk level is divided into different levels using the energy retention rate as an indicator. For example, the degradation level is divided into four levels: normal energy (energy retention rate ≥ 95%), slight degradation (energy retention rate between 85% and 95%), moderate degradation (energy retention rate between 70% and 85%), and severe degradation (energy retention rate < 70%). When the energy retention rate is 90%, the battery system's energy degradation level is determined to be slight degradation by comparing it with the energy degradation threshold table.

[0123] After determining the energy degradation level, it is correlated and matched with the periodic fault types of the battery system to form a maintenance requirement dataset. A rule base for associating energy degradation levels and periodic fault types is pre-established. This rule base determines the correlation through correlation analysis of historical operating data. For example, based on statistical analysis of historical operating data, when the battery system's energy degradation level reaches a moderate level, the frequency of abnormal cell voltage occurrences (a periodic fault type) increases, indicating a strong correlation. Therefore, in the maintenance requirement dataset, maintenance requirements for periodic fault types corresponding to a slight degradation level might include increasing the monitoring frequency of cell voltage parameters and checking the accuracy of battery voltage sensors in advance. Through this correlation matching operation, a maintenance requirement dataset is formed, recording the energy degradation level, the associated periodic fault type, and a list of corresponding maintenance requirement measures.

[0124] Based on the maintenance requirement data set, the energy storage platform's built-in maintenance rule library is used to generate battery system maintenance strategies. The maintenance rule library is constructed as follows: based on battery system maintenance experience and maintenance specifications provided by battery manufacturers, domain experts develop standardized maintenance rules. Each rule describes maintenance operation procedures, maintenance cycle recommendations, and a list of parts to be inspected or replaced under different energy degradation levels and fault types. For example, for cell voltage anomaly faults at the minor degradation level, maintenance rules in the rule library might include increasing the cell voltage sampling frequency to once every 30 minutes, scheduling maintenance personnel to verify the accuracy of voltage sensors on-site within the next 7 days, and visually inspecting or replacing cell connection lines. The energy storage platform uses the maintenance rule library to generate maintenance strategies based on the maintenance requirement data set. These strategies are recorded in the energy storage platform's database as maintenance task work orders, which include maintenance measures, maintenance operation methods, recommended maintenance time cycles, and responsible maintenance personnel.

[0125] Alarm information is generated based on the energy degradation level and the periodic fault type of the battery system. The alarm information generation method specifically involves matching corresponding alarm rules from a pre-set alarm rule base within the energy storage platform, based on the battery system's energy degradation level and periodic fault type. The alarm rule base is developed by determining the alarm level and triggering conditions based on the severity analysis of historical fault data and maintenance experience. For example, for the periodic fault type of severe battery energy degradation corresponding to the severe degradation level, the alarm level is high, and the alarm content is immediate on-site maintenance; for the cell voltage abnormality type of fault corresponding to the minor degradation level, the alarm level is low, and the alarm content is a recommendation to check the cell voltage in the short term. The alarm information includes the alarm level (e.g., high, medium, and low), the alarm cause (e.g., energy decay to 90%, abnormal cell voltage trend), suggested maintenance measures (e.g., checking cell voltage sensors, increasing monitoring frequency), and the time the alarm was generated. The energy storage platform stores the alarm information in the battery system basic data information database as data records and simultaneously notifies the designated maintenance personnel via message push to ensure that the alarm information can be processed in a timely manner.

[0126] Example 2

[0127] The difference between Embodiment 2 and Embodiment 1 is that this embodiment introduces a battery health monitoring system based on an energy storage platform.

[0128] Figure 2 A schematic diagram of a battery health monitoring system based on an energy storage platform is provided according to the present invention. The battery health monitoring system based on an energy storage platform includes:

[0129] Data acquisition module: Collects the energy characteristic parameters, state characteristic parameters and operating environment parameters of individual cells in the battery system in real time through the energy storage platform, and establishes a basic data information database for the battery system;

[0130] Operation identification module: Based on the battery system basic data information database, calculate the charging energy achievement rate of the battery system and identify the current operating status of the battery system;

[0131] Fault prediction module: Based on the charging energy achievement rate of the battery system, fault prediction is performed. When the charging energy achievement rate of the battery system is lower than a predetermined threshold, it is determined that there is a potential fault risk in the battery system and the potential fault level of the battery system is determined.

[0132] Energy Calculation Module: Based on the potential fault level and current operating status of the battery system, the module periodically samples the cumulative charge and discharge amount of individual cells in the battery system, and calculates the actual energy of the battery system based on the full charge and discharge status data of adjacent cells.

[0133] Fault prediction module: Based on historical fault data of the battery system, predict the fault trend of the battery system and determine the periodic fault types of the battery system;

[0134] Strategy generation module: Based on the actual energy of the battery system and the types of periodic faults, it analyzes the energy decay trend of the battery system and generates maintenance strategies and alarm information for the battery system.

[0135] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0136] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0137] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0138] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0139] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0140] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0141] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0142] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0143] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0144] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A battery health monitoring method based on an energy storage platform, characterized in that, Includes the following steps: By collecting the energy characteristic parameters, state characteristic parameters and operating environment parameters of individual cells in the battery system in real time through the energy storage platform, a basic data information database of the battery system is established. Based on the battery system's basic data database, the charging energy achievement rate of the battery system is calculated, and the current operating state of the battery system is identified, specifically: Based on the battery system basic data information database, calculate the maximum charge of each individual cell in the battery system during the daily operating cycle. Based on the power load requirements of the battery system and the battery charging and discharging operation strategy, the calendar energy of the battery system is preset; The battery system's charging energy achievement rate is obtained by calculating the ratio of the battery system's maximum daily charging amount to the pre-set calendar energy of the battery system. The current operating status of the battery system is determined based on the charging energy achievement rate of the battery system. Fault prediction is based on the charging energy achievement rate of the battery system. When the charging energy achievement rate of the battery system is lower than a predetermined threshold, it is determined that there is a potential fault risk in the battery system, and the potential fault level of the battery system is determined. Based on the potential fault level and current operating state of the battery system, the cumulative charge and discharge capacity of individual cells in the battery system is periodically sampled, and the actual energy of the battery system is calculated based on the full charge and discharge state data of adjacent cells. Specifically: The sampling period is set based on the potential fault level and current operating status of the battery system; Within each sampling period, the cumulative charge and discharge amounts of each individual cell in the battery system under fully discharged and fully charged states are extracted from the battery system basic data information database. The actual energy of the battery system is calculated based on the cumulative charge and discharge of each individual cell in the fully discharged and fully charged states. Based on historical fault data of the battery system, the fault trend of the battery system is predicted, and the periodic fault types of the battery system are determined. Based on the actual energy and periodic fault types of the battery system, the energy decay trend of the battery system is analyzed, and maintenance strategies and alarm information for the battery system are generated.

2. The battery health monitoring method based on an energy storage platform according to claim 1, characterized in that, By collecting real-time energy characteristic parameters, state characteristic parameters, and operating environment parameters of individual cells in the battery system through the energy storage platform, a basic data information database for the battery system is established, specifically: The energy storage platform collects the energy characteristic parameters, state characteristic parameters, and operating environment parameters of each individual cell in the battery system in real time. A basic data information database for battery systems is constructed based on energy characteristic parameters, state characteristic parameters, and operating environment parameters.

3. The battery health monitoring method based on an energy storage platform according to claim 1, characterized in that, The power characteristic parameters include the cumulative charge, cumulative discharge, and maximum charge of each individual cell in the battery system; the state characteristic parameters include the state of charge of each individual cell in the battery system; and the operating environment parameters include the cell voltage and cell temperature of each individual cell in the battery system.

4. The battery health monitoring method based on an energy storage platform according to claim 1, characterized in that, Fault prediction is based on the battery system's charging energy achievement rate. When the battery system's charging energy achievement rate is lower than a predetermined threshold, it is determined that the battery system has a potential fault risk, and the potential fault level of the battery system is determined, specifically: The charging energy achievement rate of the battery system is compared with the charging energy achievement rate threshold preset by the energy storage platform in real time. When the charging energy achievement rate of the battery system is lower than the charging energy achievement rate threshold preset by the energy storage platform, it is determined that there is a potential risk of failure in the battery system. When a potential fault risk is identified in the battery system, the potential fault level of the battery system is determined based on the operating environment parameters in the battery system basic data information database.

5. The battery health monitoring method based on an energy storage platform according to claim 1, characterized in that, Based on historical fault data of the battery system, the fault trend of the battery system is predicted, and the cyclical fault types of the battery system are determined, specifically: Based on historical fault data of battery systems, a fault trend prediction model is established using regression analysis. Input the power characteristic parameters, status characteristic parameters and operating environment parameters obtained in the current sampling period into the fault trend prediction model, and output the fault trend prediction results; Based on the fault occurrence time interval and fault type identifier in the fault trend prediction results, the periodic characteristics of the prediction results are analyzed to determine the periodic fault types of the battery system.

6. The battery health monitoring method based on an energy storage platform according to claim 1, characterized in that, Based on the actual energy level and cyclical fault types of the battery system, the energy degradation trend of the battery system is analyzed, and maintenance strategies and alarm information for the battery system are generated, specifically: Obtain the actual energy and rated energy of the battery system; Calculate the energy retention rate between actual energy and rated energy; The energy retention rate is compared with the energy decay threshold table to generate an energy decay level; The energy degradation level is correlated and matched with the periodic failure type of the battery system to form a set of maintenance requirement data; Based on the maintenance requirement data set, the maintenance rule base is invoked to generate a maintenance strategy; Alarm information is generated based on the energy decay level and the periodic fault type of the battery system.

7. A battery health monitoring system based on an energy storage platform, used to implement the battery health monitoring method based on an energy storage platform as described in any one of claims 1-6, characterized in that, include: Data acquisition module: Collects the energy characteristic parameters, state characteristic parameters and operating environment parameters of individual cells in the battery system in real time through the energy storage platform, and establishes a basic data information database for the battery system; Operation identification module: Based on the battery system basic data information database, calculate the charging energy achievement rate of the battery system and identify the current operating status of the battery system; Fault prediction module: Based on the charging energy achievement rate of the battery system, fault prediction is performed. When the charging energy achievement rate of the battery system is lower than a predetermined threshold, it is determined that there is a potential fault risk in the battery system and the potential fault level of the battery system is determined. Energy Calculation Module: Based on the potential fault level and current operating status of the battery system, the module periodically samples the cumulative charge and discharge amount of individual cells in the battery system, and calculates the actual energy of the battery system based on the full charge and discharge status data of adjacent cells. Fault prediction module: Based on historical fault data of the battery system, predict the fault trend of the battery system and determine the periodic fault types of the battery system; Strategy generation module: Based on the actual energy of the battery system and the types of periodic faults, it analyzes the energy decay trend of the battery system and generates maintenance strategies and alarm information for the battery system.

Images