A Health Management Method and System for Energy Storage Power Stations Based on a Multi-Level Assessment Framework

Abstract

This application provides a health management method and system for energy storage power stations based on a multi-level evaluation system, relating to the field of power and energy technology. The method includes: extracting features from raw monitoring data to obtain feature data; calculating health scores for multiple preset cell health indicators and a total health score based on cell feature data; calculating health scores for multiple preset battery cluster health indicators and a total health score based on battery cluster feature data and the health scores of each individual cell; calculating health scores for multiple preset battery stack health indicators and a total health score based on battery pile feature data and the health scores of each battery cluster; calculating health scores for multiple preset power station health indicators and a total health score based on power station feature data and the health scores of each battery stack; and issuing an alarm when the health score at any level and / or the total health score falls below a threshold. This application enables comprehensive health monitoring of energy storage power stations.

Description

Technical Field

[0001] This application relates to the field of power and energy technology, and in particular to a health management method and system for energy storage power stations based on a multi-level assessment system. Background Technology

[0002] Energy storage power stations often manage tens of thousands of battery cells, with data stored at the second level. Maintenance personnel typically monitor real-time data changes such as temperature, voltage, and current to assess the station's health, but comprehensive, long-term monitoring is lacking. Existing patents and literature largely focus on single indicators and dimensions, such as cell SOH (State of Health), SOC (State of Charge), and battery cluster consistency. These only reflect the situation of individual cells and cannot reflect the overall situation of the entire energy storage power station, making comprehensive monitoring of the entire system impossible. Furthermore, energy storage power stations have a large number of batteries—typically tens of thousands—resulting in massive amounts of data. Performing full monitoring of the raw data would consume enormous resources and make it difficult to guarantee real-time performance.

[0003] Therefore, how to achieve comprehensive health monitoring of energy storage power stations is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0004] To address the aforementioned technical problems, this application provides a health management method for energy storage power stations based on a multi-level assessment system, enabling comprehensive health monitoring of energy storage power stations. This application also provides a health management system for energy storage power stations based on a multi-level assessment system, achieving the same technical effects.

[0005] The first objective of this application is to provide a health management method for energy storage power stations based on a multi-level assessment system.

[0006] The aforementioned objective of this application is achieved through the following technical solution: A health management method for energy storage power stations based on a multi-level assessment system includes: Feature extraction is performed on the raw monitoring data of the energy storage power station to obtain feature data, which includes cell feature data of individual cells, battery cluster feature data of battery clusters, battery stack feature data of battery piles, and power station feature data of the energy storage power station. Based on the cell characteristic data, the health scores of multiple preset cell health indicators for each individual cell are calculated, and the total health score of each individual cell is calculated using a weighted average method. Based on the battery cluster feature data and the health score of each individual cell, the health scores of multiple preset battery cluster health indicators for each battery cluster are calculated, and the total health score of each battery cluster is calculated using a weighted average method. The preset battery cluster health indicators include the average cell health index, and the health score of the average cell health index is the average of the health scores of all preset cell health indicators of all individual cells in each battery cluster. Based on the battery stack feature data and the health score of each battery cluster, the health scores of multiple preset battery stack health indicators for each battery stack are calculated, and the total health score of each battery stack is calculated using a weighted average method. The preset battery stack health indicators include the average health index of the battery cluster, and the health score of the average health index of the battery cluster is the average of the health scores of all preset battery cluster health indicators of all battery clusters in each battery stack. Based on the power station characteristic data and the health scores of each battery stack, the health scores of multiple preset power station health indicators of the energy storage power station are calculated, and the total health score of the energy storage power station is calculated by using a weighted average method. The preset power station health indicators include the battery stack health average indicator, and the health score of the battery stack health average indicator is the average of the health scores of all preset battery stack health indicators of all battery stacks in the energy storage power station. An alarm will be triggered when the health score and / or total health score at any level of a single cell, battery cluster, battery stack, or energy storage power station falls below a preset score threshold.

[0007] Preferably, in the energy storage power station health management method based on a multi-level evaluation system, the step of extracting features from the original monitoring data of the energy storage power station to obtain feature data includes: The raw monitoring data of the energy storage power station is processed according to the three states of the battery: charging, discharging, and resting, and feature extraction is performed to obtain feature data for each of the three states.

[0008] Preferably, in the energy storage power station health management method based on a multi-level evaluation system, the multiple preset cell health indicators include cell temperature, cell voltage, cell internal resistance, cell energy efficiency, and equivalent cycle life. The step of calculating the health score of each individual cell based on the cell characteristic data for the multiple preset cell health indicators includes: Based on the cell characteristic data, the values ​​of various parameters in the cell temperature index, cell voltage index, cell internal resistance index, cell energy efficiency index, and equivalent cycle life index of each individual cell are obtained. The values ​​of each parameter are compared with the set standards to obtain the score of each parameter. The scores are then mapped to obtain the health score of the cell temperature index, the cell voltage index, the cell internal resistance index, the cell energy efficiency index, and the equivalent cycle life index of each individual cell.

[0009] Preferably, in the energy storage power station health management method based on a multi-level evaluation system, the cell internal resistance index includes the cell internal resistance parameter, and the calculation formula is as follows: ; In the formula, Indicates the internal resistance of the battery cell. The voltage at the end of the charging state of a single battery cell. The current representing the end of the charging state of a single battery cell, or... The voltage at the end of the discharge state of a single battery cell. This represents the current at the end of the discharge state of a single battery cell. This indicates the voltage at the start of the next resting phase of a single battery cell.

[0010] Preferably, in the energy storage power station health management method based on a multi-level evaluation system, the cell energy efficiency index includes the battery's energy efficiency parameter, calculated using the following formula: ; In the formula, This indicates the battery's energy efficiency.

[0011] Preferably, in the energy storage power station health management method based on a multi-level evaluation system, the multiple preset battery cluster health indicators further include insulation evaluation indicators, connection impedance indicators, battery cluster energy efficiency indicators, voltage consistency indicators, and temperature consistency indicators. The calculation of the health score of each battery cluster's multiple preset battery cluster health indicators based on the battery cluster characteristic data and the health score of each individual cell includes: Based on the battery cluster characteristic data, the values ​​of each parameter in the insulation evaluation index, connection impedance index, battery cluster energy efficiency index, voltage consistency index, and temperature consistency index of each battery cluster are obtained. The values ​​of each parameter are compared with the set standards to obtain the score of each parameter. The scores are then mapped to obtain the health score of each battery cluster's insulation evaluation index, connection impedance index, battery cluster energy efficiency index, voltage consistency index, and temperature consistency index. Calculate the average health score of all preset cell health indicators for all individual cells within each battery cluster to obtain the average health score of the cell health indicators for each battery cluster.

[0012] Preferably, in the energy storage power station health management method based on a multi-level evaluation system, the voltage consistency index includes the voltage standard deviation parameter, calculated using the following formula: ; In the formula, SD represents the voltage standard deviation, and n represents the number of individual cells in the battery cluster. This represents the voltage of the individual battery cell numbered i. This represents the average voltage of all individual cells within the battery cluster.

[0013] Preferably, in the energy storage power station health management method based on a multi-level evaluation system, the multiple preset battery stack health indicators further include current consistency indicators, stack humidity indicators, SOC consistency indicators, stack internal temperature consistency indicators, and stack energy efficiency indicators. The calculation of the health scores of the multiple preset battery stack health indicators for each battery stack based on the battery stack characteristic data and the health scores of each battery cluster includes: Based on the battery stack characteristic data, the values ​​of various parameters in the current consistency index, stack humidity index, SOC consistency index, stack internal temperature consistency index, and stack energy efficiency index of each battery stack are obtained. The values ​​of each parameter are compared with the set standards to obtain the scores of each parameter. The scores are then mapped to obtain the health scores of the current consistency index, stack humidity index, SOC consistency index, stack internal temperature consistency index, and stack energy efficiency index of each battery stack. Calculate the average health score of all preset battery cluster health indicators for all battery clusters within each battery stack to obtain the average health score of the battery cluster health indicator for each battery stack.

[0014] Preferably, in the energy storage power station health management method based on a multi-level evaluation system, the multiple preset power station health indicators also include a station energy indicator. The calculation of the health scores of the multiple preset power station health indicators based on the power station characteristic data and the health scores of each battery stack includes: Based on the power station characteristic data, the values ​​of the parameters in the station energy index of the energy storage power station are obtained. The parameter values ​​are compared with the set standards to obtain the parameter scores. The scores are mapped to obtain the health score of the station energy index of the energy storage power station. Calculate the average health score of all preset battery stack health indicators for all battery stacks in the energy storage power station to obtain the average health score of the battery stack health indicators of the energy storage power station.

[0015] The second objective of this application is to provide a health management system for energy storage power stations based on a multi-level assessment system.

[0016] The second objective of this application is achieved through the following technical solution: A health management system for energy storage power stations based on a multi-level assessment system includes: The extraction unit is used to extract features from the raw monitoring data of the energy storage power station to obtain feature data, wherein the feature data includes cell feature data of individual cells, battery cluster feature data of battery clusters, battery stack feature data of battery piles, and power station feature data of the energy storage power station. The first calculation unit is used to calculate the health score of multiple preset cell health indicators for each individual cell based on the cell characteristic data, and to calculate the total health score of each individual cell using a weighted average method. The second calculation unit is used to calculate the health score of multiple preset battery cluster health indicators for each battery cluster based on the battery cluster feature data and the health score of each individual cell, and to calculate the total health score of each battery cluster using a weighted average method. The preset battery cluster health indicators include the average cell health indicator, and the health score of the average cell health indicator is the average of the health scores of all preset cell health indicators of all individual cells in each battery cluster. The third calculation unit is used to calculate the health score of multiple preset battery stack health indicators for each battery stack based on the battery stack feature data and the health score of each battery cluster, and to calculate the total health score of each battery stack using a weighted average method. The preset battery stack health indicators include the average health index of the battery cluster, and the health score of the average health index of the battery cluster is the average of the health scores of all preset battery cluster health indicators of all battery clusters in each battery stack. The fourth calculation unit is used to calculate the health scores of multiple preset power station health indicators of the energy storage power station based on the power station characteristic data and the health scores of each battery stack, and to calculate the total health score of the energy storage power station using a weighted average method. The preset power station health indicators include the average health index of the battery stack, and the health score of the average health index of the battery stack is the average of the health scores of all preset battery stack health indicators of all battery stacks in the energy storage power station. The alarm unit is used to issue an alarm when the health score and / or total health score of any level in the individual cell, battery cluster, battery stack, and energy storage power station are lower than a preset score threshold.

[0017] The above technical solution extracts features from the raw monitoring data of the energy storage power station, greatly reducing the dimensionality of the data, saving computational resources, and facilitating subsequent health assessments. Based on the cell feature data, it calculates health scores for multiple preset cell health indicators for each individual cell, and uses a weighted average method to calculate the total health score for each individual cell. Similarly, based on the battery cluster feature data and the health scores of each individual cell, it calculates health scores for multiple preset battery cluster health indicators for each battery cluster, and uses a weighted average method to calculate the total health score for each battery cluster. Likewise, based on the battery stack feature data and the health scores of each battery cluster, it calculates health scores for multiple preset battery stack health indicators for each battery stack, and uses a weighted average method to calculate the total health score for each battery stack. Finally, based on the power station feature data and the health scores of each battery stack, it calculates health scores for multiple preset power station health indicators for the energy storage power station, and uses a weighted average method to calculate the total health score for the energy storage power station. An alarm is triggered when the health score and / or total health score at any level—whether it's an individual cell, battery cluster, battery stack, or energy storage power station—falls below a preset threshold. This constructs a comprehensive multi-level health assessment mechanism for energy storage power stations, using health scores to represent the health status of individual units. This facilitates operation and maintenance personnel in understanding the health status of the station, stack, cluster, and core, identifying abnormal units, and accurately locating anomalies. When the health score at any level and / or the total health score falls below a preset threshold, an alarm mechanism is immediately triggered to promptly notify operation and maintenance personnel. This facilitates rapid response and handling of potential problems, effectively prevents faults, and ensures the safe and stable operation of energy storage power stations.

[0018] Furthermore, the above technical solution introduces the average health index of cells, the average health index of battery clusters, and the average health index of battery stacks. By using the average health score of all individuals within the cell level, cluster level, and stack level as one of the evaluation indicators for the next higher level, it can more comprehensively reflect the overall health status of the next higher level. This allows the health assessment to not only focus on individuals but also take into account the whole, thus improving the accuracy and comprehensiveness of the health assessment.

[0019] In summary, the above technical solutions enable comprehensive health monitoring of energy storage power stations. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart illustrating a health management method for an energy storage power station provided in an embodiment of this application. Figure 2 This is a schematic diagram of the topology of the energy storage power station provided in the embodiments of this application; Figure 3 This is a schematic diagram of the calculation of the cell internal resistance provided in the embodiments of this application; Figure 4 This is a schematic diagram of the health management system of an energy storage power station provided in the embodiments of this application. Detailed Implementation

[0022] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] In the embodiments provided in this application, it should be understood that the disclosed methods and systems can be implemented in other ways. The system embodiments described below are merely illustrative. For example, the division of units and modules is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or modules can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, and can be electrical, mechanical, or other forms.

[0024] In addition, each functional unit in the various embodiments of this application can be integrated into a single processor, or each unit can be a separate device, or two or more units can be integrated into a single device; each functional unit in the various embodiments of this application can be implemented in hardware or in the form of hardware plus software functional units.

[0025] Those skilled in the art will understand that all or part of the steps of the following method embodiments can be implemented by program instructions and related hardware. The aforementioned program instructions can be stored in a computer-readable storage medium. When the program instructions are executed, they perform the steps of the following method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks.

[0026] It should be understood that the use of terms such as "system," "device," "unit," and / or "module" in this application is merely one method of distinguishing different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0027] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "a plurality of" or "several" means two or more, unless otherwise explicitly specified.

[0028] If a flowchart is used in this application, it is used to illustrate the operations performed by the system according to embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0029] It should also be noted that, in this document, terms such as “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase “comprising one…” does not exclude the presence of other identical elements in the article or device that includes the aforementioned element.

[0030] The embodiments in this application are written in a progressive manner.

[0031] like Figure 1 As shown in the figure, this application provides a health management method for an energy storage power station, including: S101. Extract features from the raw monitoring data of the energy storage power station to obtain feature data; Specifically, in S101, raw monitoring data can be obtained from the Battery Management System (BMS) of the energy storage power station. The energy storage power station has a four-layer structure: station, stack, cluster, and core. Figure 2 As shown, energy storage power stations often require monitoring and management of tens of thousands of battery cells. A single energy storage power station comprises multiple battery stacks, each stack includes multiple battery clusters, and each cluster consists of multiple cells (typically hundreds) connected in series. Correspondingly, the raw monitoring data includes monitoring data at four levels: station, stack, cluster, and cell. Due to the sheer volume of data from individual cells, storing real-time data from tens of thousands of cells places high demands on hardware. Directly analyzing the raw monitoring data would consume enormous server computing resources, making it difficult to guarantee real-time performance. Therefore, in this step, feature extraction is performed on the raw monitoring data of the energy storage power station to obtain feature data. This feature data includes cell feature data for individual cells, battery cluster feature data, battery stack feature data, and power station feature data. This significantly reduces the dimensionality of the data, saves computing resources, and facilitates subsequent health assessments.

[0032] In some embodiments, one implementation of this step specifically includes: extracting features from the raw monitoring data of the energy storage power station according to the three states of the battery: charging, discharging, and resting, to obtain feature data for each of the three states. The feature data calculation at each level is divided into the three states of charging, discharging, and resting, effectively reducing data dimensionality while retaining the key features of the battery cell. In a specific embodiment, the battery is divided into three states: charging, discharging, and resting, and the feature data extracted for each state is as follows: Cell characteristic data, including but not limited to: state name (one of charging, discharging, and stationary), start time, intermediate time, end time, start time voltage, intermediate time voltage, end time voltage, start time temperature, intermediate time temperature, end time temperature, energy change, charge change, highest temperature, lowest temperature, maximum voltage, minimum voltage, etc. Battery cluster characteristic data, including but not limited to: state name, start time, intermediate time, end time, start time voltage, intermediate time voltage, end time voltage, start time temperature, intermediate time temperature, end time temperature, start time current, intermediate time current, end time current, start time insulation, intermediate time insulation, end time insulation, start time SOC, intermediate time SOC, end time SOC, maximum cell voltage, maximum voltage cell number, minimum cell voltage, minimum voltage cell number, average cell temperature, maximum voltage difference, average voltage difference, maximum cell temperature, maximum temperature cell number, maximum temperature difference, average temperature difference, energy change, charge change, etc. Battery stack characteristic data, including but not limited to: state name, start time, intermediate time, end time, start time voltage, intermediate time voltage, end time voltage, start time current, intermediate time current, end time current, start time insulation, intermediate time insulation, end time insulation, maximum current difference, stack current at maximum current difference, maximum temperature difference, maximum SOC difference, energy change, charge change, etc. Power plant characteristic data, including but not limited to: status name, energy change, and power change.

[0033] The following is data on the charging process of a certain battery cell. The extractable features are shown in Table 1 below: Table 1. Characteristic data of battery cells during charging

[0034] If the battery was charged between 0:00 and 2:00, the start time would be 2025-10-01 00:00:00, the middle time would be 2025-10-01 01:00:00, and the end time would be 2025-10-01 02:00:00. The voltages at the start, middle, and end times would be 3291, 3345, and 3367, respectively. Other characteristics follow the same pattern. Changes in charge and energy are calculated using the ampere-hour integral method, with the following formula: ; ; In the formula, Indicates changes in electricity level. Indicates energy change. Represents current. Indicates voltage. Indicates the start time. Indicates the end time.

[0035] In other embodiments, the cell feature data also includes cell charging cycle features, and the battery cluster feature data also includes battery cluster charging cycle features. The charging cycle features are calculated by defining a charging cycle as the period from the start of one charge to the start of the next charge. Typically, in an energy storage station, after a battery is charged, it will discharge once or multiple times. The extractable features are as follows: Battery cell charging cycle characteristics: cycle start time, charging end time, cycle end time, charging energy, discharging energy, charging capacity, discharging capacity, charging start SOC, charging end SOC, discharging end SOC; Battery cluster charging cycle characteristics: cycle start time, charging end time, cycle end time, charging energy, discharging energy, charging capacity, discharging capacity, charging start SOC, charging end SOC, discharging end SOC.

[0036] The original monitoring data of the energy storage power station can be extracted at a fixed frequency, such as according to the three states of battery charging, discharging, and resting, after each state ends or at a fixed time every day. Then, the health status of the energy storage power station can be assessed using the feature data. This application is not limited to this.

[0037] S102. Based on the cell characteristic data, calculate the health scores of multiple preset cell health indicators for each individual cell, and use the weighted average method to calculate the total health score of each individual cell. In step S102, specifically, multiple preset cell health indicators can be pre-set based on actual needs. Then, based on cell characteristic data, the values ​​of each parameter in the multiple preset cell health indicators are obtained. Following preset scoring rules, the health score of each individual cell for the multiple preset cell health indicators is calculated. Next, a weighted average method is used to calculate the total health score of each individual cell based on its health score and preset indicator weights. The preset indicator weights can be pre-set by industry experts or power plant operation and maintenance personnel based on actual needs; this application does not impose specific restrictions on this. This step not only accurately quantifies the health score of each individual cell but also allows for differentiated evaluation based on the importance of different indicators, making the health score more scientific and practical.

[0038] S103. Based on the battery cluster characteristic data and the health score of each individual cell, calculate the health score of multiple preset battery cluster health indicators for each battery cluster, and use the weighted average method to calculate the total health score of each battery cluster. The preset battery cluster health indicators include the average cell health index. In step S103, specifically, multiple preset battery cluster health indicators can be pre-set based on actual needs. Then, based on battery cluster feature data, the values ​​of each parameter in the preset battery cluster health indicators (excluding the average cell health indicator) are obtained. Following preset scoring rules, the health score of each battery cluster's preset battery cluster health indicators (excluding the average cell health indicator) is calculated. The average cell health indicator's health score is the average of the health scores of all preset cell health indicators for all individual cells within each battery cluster. By calculating the average of the health scores of all preset cell health indicators for all individual cells within each battery cluster, the average cell health indicator's health score can be obtained. Next, a weighted average method is used to calculate the total health score of each battery cluster based on the health scores of the multiple preset battery cluster health indicators and the preset indicator weights. The preset indicator weights can be pre-set based on actual needs.

[0039] In this step, by introducing the average health index of individual cells, the impact of the health status of individual cells on the overall health of the battery cluster is quantified. This allows the health assessment of the battery cluster to consider not only its own direct monitoring data, but also the health status of the individual cells within it, thereby improving the accuracy and comprehensiveness of the battery cluster health assessment.

[0040] S104. Based on the battery stack characteristic data and the health score of each battery cluster, calculate the health score of multiple preset battery stack health indicators for each battery stack, and use the weighted average method to calculate the total health score of each battery stack. The preset battery stack health indicators include the average health index of the battery cluster. In S104, specifically, multiple preset battery stack health indicators can be pre-set based on actual needs. Then, based on battery stack characteristic data, the values ​​of each parameter in the preset battery stack health indicators (excluding the average battery cluster health indicator) are obtained. Then, according to preset scoring rules, the health score of each battery stack's preset battery stack health indicators (excluding the average battery cluster health indicator) is calculated. The health score of the average battery cluster health indicator is the average of the health scores of all preset battery cluster health indicators for all battery clusters within each battery stack. By calculating the average of the health scores of all preset battery cluster health indicators for all battery clusters within each battery stack, the health score of the average battery cluster health indicator can be obtained. Next, a weighted average method is used to calculate the total health score of each battery stack based on the health scores of the multiple preset battery stack health indicators and the preset indicator weights. The preset indicator weights can be pre-set based on actual needs.

[0041] In this step, by introducing the average health index of battery clusters, the impact of the health status of battery clusters on the overall health of the battery stack is quantified. This allows the health assessment of the battery stack to not only consider its own direct monitoring data, but also the health status of the internal battery clusters, thereby improving the accuracy and completeness of the battery stack health assessment.

[0042] S105. Based on the power station characteristic data and the health scores of each battery stack, calculate the health scores of multiple preset power station health indicators of the energy storage power station, and use the weighted average method to calculate the total health score of the energy storage power station. Among them, the preset power station health indicators include the average health index of the battery stack. Specifically, in S105, multiple preset power station health indicators can be pre-set based on actual needs. Then, based on power station characteristic data, the values ​​of each parameter in the preset power station health indicators (excluding the average health indicator of the battery stack) are obtained. Following preset scoring rules, the health score of each power station's preset power station health indicators (excluding the average health indicator of the battery stack) is calculated. The health score of the average health indicator of the battery stack is the average of the health scores of all preset battery stack health indicators for all battery stacks within the energy storage power station. The average health score of the average battery stack health indicator is obtained by calculating the average of the health scores of all preset battery stack health indicators for all battery stacks within the energy storage power station. Next, a weighted average method is used to calculate the total health score of the energy storage power station based on the health scores of the multiple preset power station health indicators for each power station and the preset indicator weights. The preset indicator weights can be pre-set based on actual needs.

[0043] In this step, by introducing the average health index of the battery stack, the impact of the battery stack's health status on the overall health of the energy storage power station is quantified. This ensures that the health assessment of the energy storage power station not only considers its own direct monitoring data but also comprehensively considers the health status of the internal battery stack, thereby ensuring the reliability and systematic nature of the energy storage power station's health assessment.

[0044] By establishing the aforementioned multi-level, progressive evaluation mechanism, the health status of energy storage power stations can be comprehensively grasped from the micro to the macro level, providing operation and maintenance personnel with accurate and comprehensive health assessment results. Considering the strong correlation between each level of an energy storage power station—for example, when the temperature of a certain cell is abnormal, the battery cluster will be in a state of temperature inconsistency, the battery stack will also be in a state of temperature inconsistency between clusters, and the power station will be in a state of temperature inconsistency between stacks—this embodiment introduces the average health index of cells, the average health index of battery clusters, and the average health index of battery stacks. The average health score of all individuals within the cell level, cluster level, and stack level is used as one of the evaluation indicators for the next higher level. This can more comprehensively reflect the overall health status of the next higher level, making the health assessment not only focus on individuals but also take into account the whole, thus improving the accuracy and comprehensiveness of the assessment.

[0045] S106. An alarm is triggered when the health score and / or total health score of any level in the individual cell, battery cluster, battery stack, and energy storage power station are lower than the preset score threshold.

[0046] Specifically, in S106, corresponding preset score thresholds can be pre-set for the health score and / or total health score of any level in individual cells, battery clusters, battery stacks, and energy storage power stations. When a certain health score and / or total health score is lower than the corresponding preset score threshold, an alarm is triggered to notify the operation and maintenance personnel in a timely manner, so as to facilitate rapid response and handling of potential problems, effectively prevent failures, and ensure the safe and stable operation of the energy storage power station.

[0047] In some embodiments, the range of health score and total health score is [0, 100]. The higher the score, the better the health. The following scoring criteria can be defined, but this application is not limited to them: Table 2 Scoring Standards

[0048] In other embodiments, the health scores and / or total health scores of any level in the individual cell, battery cluster, battery stack, and energy storage power station can be visualized, so that operation and maintenance personnel can intuitively and clearly understand the health status of each level and the whole of the energy storage power station, thereby taking timely measures to ensure the safe and stable operation of the energy storage power station and achieve effective health management.

[0049] Existing patents and literature mostly focus on research on single indicators and single dimensions, such as cell SOH, SOC, and battery cluster consistency. These can only reflect the situation of a single individual or single dimension, and cannot reflect the overall situation of the energy storage power station, nor can they provide comprehensive monitoring of the entire energy storage power station. In addition, energy storage power stations have a large number of batteries, typically tens of thousands of cells, resulting in a large amount of data. Performing full monitoring of the raw data would consume a lot of resources and make it difficult to guarantee real-time performance.

[0050] The above embodiments extract features from the raw monitoring data of the energy storage power station to obtain feature data, which greatly reduces the dimensionality of the data, saves computing resources, and facilitates subsequent health assessments. Based on the cell feature data, the health scores of multiple preset cell health indicators for each individual cell are calculated, and a weighted average method is used to calculate the total health score of each individual cell. Based on the battery cluster feature data and the health scores of each individual cell, the health scores of multiple preset battery cluster health indicators for each battery cluster are calculated, and a weighted average method is used to calculate the total health score of each battery cluster. Based on the battery stack feature data and the health scores of each battery cluster, the health scores of multiple preset battery stack health indicators for each battery stack are calculated, and a weighted average method is used to calculate the total health score of each battery stack. Based on the power station feature data and the health scores of each battery stack, the health scores of multiple preset power station health indicators for the energy storage power station are calculated, and a weighted average method is used to calculate the total health score of the energy storage power station. When the health score and / or total health score at any level of individual cell, battery cluster, battery stack, or energy storage power station is lower than a preset score threshold, an alarm is triggered. This constructs a comprehensive, multi-level health assessment mechanism for energy storage power stations. Health scores represent the health status of individual cells, facilitating maintenance personnel's understanding of the health status of the station, stack, cluster, and core cells, identifying abnormal individuals, and accurately locating anomalies. When the health score at any level and / or the total health score falls below a preset threshold, an alarm mechanism is immediately triggered, promptly notifying maintenance personnel for rapid response and handling of potential problems, effectively preventing faults and ensuring the safe and stable operation of the energy storage power station. Furthermore, the above embodiments introduce average cell health, average battery cluster health, and average battery stack health indicators. The average health score of all individuals within the core, cluster, and stack levels is used as one of the evaluation indicators for the next higher level, providing a more comprehensive reflection of the overall health status of that level. This ensures that health assessment not only focuses on individuals but also considers the overall health, improving the accuracy and comprehensiveness of the health assessment. In summary, the above embodiments achieve comprehensive health monitoring of energy storage power stations.

[0051] In other embodiments of this application, the multiple preset cell health indicators include cell temperature, cell voltage, cell internal resistance, cell energy efficiency, and equivalent cycle life. One implementation of the step of calculating the health score of each individual cell based on cell characteristic data for the multiple preset cell health indicators specifically includes: S201. Based on the cell characteristic data, obtain the values ​​of various parameters in the cell temperature index, cell voltage index, cell internal resistance index, cell energy efficiency index, and equivalent cycle life index for each individual cell. Compare the values ​​of each parameter with the set standards to obtain the score of each parameter. Perform score mapping to obtain the health score of the cell temperature index, cell voltage index, cell internal resistance index, cell energy efficiency index, and equivalent cycle life index for each individual cell.

[0052] In some embodiments, the parameters in the cell temperature index may include the start temperature, the middle temperature, the end temperature, the highest temperature, and the lowest temperature data. The values ​​of each parameter are compared with the temperature alarm thresholds in the battery standard, such as the highest temperature threshold and the lowest temperature threshold, and each parameter is scored. For example, if a temperature greater than T1 and less than T2 is defined as a normal temperature, the score is A; if the temperature exceeds T2, it is a general alarm, the score is B; and if the temperature exceeds T3, it is a serious alarm, the score is C. The scores of each parameter are then linearly mapped to the interval [0, 100] to obtain the health score of the cell temperature index of each individual cell. This application is not limited to this.

[0053] In some embodiments, the parameters in the cell voltage index may include the voltage at the start time, the voltage at the middle time, the voltage at the end time, the maximum voltage, the minimum voltage, etc. The values ​​of each parameter are compared with the voltage alarm threshold in the battery standard to obtain the score of each parameter. Then, a linear mapping is performed to obtain the health score of the cell voltage index of each individual cell. This application is not limited to this.

[0054] In some embodiments, the cell internal resistance index includes the cell internal resistance parameter, and the calculation formula is as follows: ; In the formula, Indicates the internal resistance of the battery cell. The voltage at the end of the charging state of a single battery cell. The current representing the end of the charging state of a single battery cell, or... The voltage at the end of the discharge state of a single battery cell. This represents the current at the end of the discharge state of a single battery cell. This indicates the voltage at the start of the next resting phase of a single battery cell.

[0055] Specifically, referring to local standards, a simplified measurement of the cell's internal resistance is performed. In each charge / discharge cycle, the cell's charging / discharging and subsequent resting phases are measured. The end time of charging / discharging is recorded as A, and the start time of resting is recorded as B. Figure 3As shown, the data can come from cell characteristic data. After calculating the cell internal resistance value, it is compared with the standard internal resistance. For example, multiple alarm thresholds are set, and scores are given by comparing the alarm thresholds. The scores are linearly mapped to obtain the health score of the cell internal resistance index of each individual cell. This application is not limited to this.

[0056] In some embodiments, the cell energy efficiency index includes the battery's energy efficiency parameter, calculated using the following formula: ; In the formula, This indicates the battery's energy efficiency.

[0057] Specifically, charging energy, discharging energy, start-of-charge SOC, end-of-charge SOC, and end-of-discharge SOC can be extracted from the cell charging cycle characteristics in the cell feature data. Then, the battery energy efficiency can be calculated using the formula mentioned above. According to the preset corresponding standards, two standards are set: good energy (parameter 1) and average energy (parameter 2). The initial score of the battery energy efficiency parameter is score = energy efficiency * 100. The score is normalized, and the linear transformation rule is: score = parameter 2, corresponding to 60 points; score = parameter 1, corresponding to 90 points. These scores serve as the health score of the cell energy efficiency index for each individual cell. This application is not limited to this.

[0058] In some embodiments, the equivalent cycle life index includes the battery used life parameter. Charging energy data can be extracted from the cell charging cycle characteristics in the cell characteristic data. The number of battery charging times is represented by the charging energy / battery rated capacity. The data of each charging is recorded and accumulated to obtain the cumulative number of battery cycles. The battery used life can be obtained by multiplying the cumulative number of cycles / rated number of cycles by 100%. The battery is then scored by comparing it with the national standard. For example, more than 80% corresponds to 60 points, 80% to 90% corresponds to 60 to 90 points, and 90% to 100% corresponds to 90 to 100 points. This score mapping is used to obtain the health score of the equivalent cycle life index of each individual cell. This application is not limited to this.

[0059] In the above embodiments, by introducing cell temperature, cell voltage, cell internal resistance, cell energy efficiency, and equivalent cycle life indicators, a comprehensive and detailed assessment of the health status of individual cells is conducted from multiple dimensions. These indicators not only cover the basic operating parameters of the cell, such as temperature and voltage, but also involve the cell's performance parameters, such as internal resistance and energy efficiency, as well as lifespan parameters, such as equivalent cycle life. By comprehensively considering these indicators, the health status of the cells can be more accurately reflected, providing a solid foundation for subsequent health assessments of battery clusters, battery stacks, and even the entire energy storage power station.

[0060] In other embodiments of this application, the multiple preset battery cluster health indicators further include insulation assessment indicators, connection impedance indicators, battery cluster energy efficiency indicators, voltage consistency indicators, and temperature consistency indicators. One implementation of the step of calculating the health score of each battery cluster's multiple preset battery cluster health indicators based on battery cluster characteristic data and the health score of each individual cell specifically includes: S301. Based on the characteristic data of the battery cluster, obtain the values ​​of each parameter in the insulation evaluation index, connection impedance index, battery cluster energy efficiency index, voltage consistency index and temperature consistency index of each battery cluster. Compare the values ​​of each parameter with the set standards to obtain the score of each parameter. Perform score mapping to obtain the health score of the insulation evaluation index, connection impedance index, battery cluster energy efficiency index, voltage consistency index and temperature consistency index of each battery cluster. In some embodiments, the parameters in the insulation evaluation index may include insulation at the start time, insulation at the middle time, and insulation at the end time. The values ​​of each parameter are compared with the insulation threshold in the battery standard to obtain a first score for each parameter, and a linear mapping is performed on the first score. Simultaneously, a set time period is defined as a cycle, and all the above insulation data are acquired. A linear regression method is used to detect whether there is a corresponding downward trend in insulation, the magnitude of the trend is defined and scored, and a second score is obtained for each parameter. A linear mapping is also performed on the second score. Combining the two linear mappings, a health score for the insulation evaluation index of each battery cluster is obtained; this application is not limited to this.

[0061] In some embodiments, the connection impedance index includes connection impedance parameters. Since the cells within a battery cluster are connected in series, due to factors such as connection line losses, the battery cluster voltage should be greater than or equal to the sum of the voltages of all cells within the cluster. During charging and discharging, the connection impedance is represented by (cluster voltage - sum of cell voltages) / cluster current. The magnitude of the connection impedance is analyzed, and a threshold can be defined with reference to historical data. Scoring is performed by comparing thresholds, and a score mapping is performed based on the scores to obtain a health score for the connection impedance index of each battery cluster. This application is not limited to this.

[0062] In some embodiments, the battery cluster energy efficiency index includes the battery cluster energy efficiency parameter. The charging energy, discharging energy, starting SOC, ending SOC, and ending SOC can be extracted from the battery cluster charging cycle characteristics in the battery cluster feature data. Then, referring to the battery energy efficiency calculation formula mentioned above, the energy efficiency of the battery cluster is calculated. According to preset standards, two standards are set: good energy (parameter 1) and average energy (parameter 2). The initial score of the battery cluster energy efficiency parameter is score = energy efficiency * 100. The score is normalized, and the linear transformation rule is: score = parameter 2, corresponding to 60 points; score = parameter 1, corresponding to 90 points. This score serves as the health score of the battery cluster energy efficiency index for each battery cluster. This application is not limited to this.

[0063] In some embodiments, the voltage consistency index includes a voltage standard deviation parameter, calculated using the following formula: ; In the formula, SD represents the voltage standard deviation, and n represents the number of individual cells in the battery cluster. This represents the voltage of the individual battery cell numbered i. This represents the average voltage of all individual cells within the battery cluster.

[0064] Specifically, the cell voltage data of all cells within a cluster at the same time, such as the voltage at the start, middle, and end times, is obtained. The voltage standard deviation (SD) is calculated. Based on historical data, the voltage standard deviation (SD) can be mapped to a score, such as 100 points for values ​​less than 0.2, 90 to 100 points for values ​​between 0.2 and 0.4, 60 to 90 points for values ​​between 0.4 and 0.6, 0 to 60 points for values ​​between 0.6 and 1, and 0 points for values ​​greater than 1. This score serves as a health score for the voltage consistency indicator of each battery cluster. This application is not limited to this.

[0065] In other embodiments, multiple indicators may be referenced, such as obtaining the maximum pressure difference when the battery is stationary. According to national standards, the pressure difference when stationary must not exceed a certain value as a threshold of 90 points. A certain value is defined as a threshold of 60 points. Then, a linear mapping is performed to obtain the health score of the voltage consistency index of each battery cluster. This application is not limited to this.

[0066] In some embodiments, the temperature consistency index includes the maximum temperature difference parameter within a cluster within a stage. The maximum temperature difference within a cluster within a stage can be obtained, and a score mapping can be performed with reference to the threshold range specified by the battery manufacturer to obtain the health score of the temperature consistency index of each battery cluster. This application is not limited to this.

[0067] S302. Calculate the average health score of all preset cell health indicators for all individual cells in each battery cluster, and obtain the average health score of the cell health indicators for each battery cluster.

[0068] In some embodiments, the average health scores of cell temperature, cell voltage, cell internal resistance, cell energy efficiency, and equivalent cycle life of all individual cells in each battery cluster can be calculated to obtain the average health score of the cell health of each battery cluster. This application is not limited thereto.

[0069] In the above embodiments, by introducing insulation assessment indicators, connection impedance indicators, battery cluster energy efficiency indicators, voltage consistency indicators, and temperature consistency indicators, the health status of the battery cluster is assessed in depth and accurately from multiple key aspects. The comprehensive application of these indicators makes the health assessment of the battery cluster more comprehensive and accurate, providing strong support for the subsequent health management of battery stacks and energy storage power stations.

[0070] In other embodiments of this application, the multiple preset battery stack health indicators further include current consistency indicators, stack humidity indicators, SOC consistency indicators, stack internal temperature consistency indicators, and stack energy efficiency indicators. One implementation of the step of calculating the health scores of the multiple preset battery stack health indicators for each battery stack based on battery stack characteristic data and the health scores of each battery cluster includes: S401. Based on the battery stack characteristic data, obtain the values ​​of various parameters in the current consistency index, stack humidity index, SOC consistency index, stack internal temperature consistency index and stack energy efficiency index of each battery stack. Compare the values ​​of each parameter with the set standards to obtain the score of each parameter. Perform score mapping to obtain the health score of the current consistency index, stack humidity index, SOC consistency index, stack internal temperature consistency index and stack energy efficiency index of each battery stack. In some embodiments, the current consistency index includes a relative maximum current difference parameter, where the relative maximum current difference = maximum current difference / stack current at maximum current difference. The score is determined based on the value of the relative maximum current difference and defined according to historical data and relevant standards. For example, 0 to 5% is mapped to 90 to 100 points, and so on, to obtain the health score of the current consistency index for each battery stack. This application is not limited to this.

[0071] In some embodiments, the stack humidity index includes the maximum humidity parameter of the stack. Scoring is performed based on the maximum humidity of the stack and a set threshold. The scores are then mapped to obtain a health score for the stack humidity index of each battery stack. This application is not limited to this.

[0072] In some embodiments, the SOC consistency index includes a maximum SOC difference parameter. By obtaining the maximum SOC difference, scoring is performed based on the maximum SOC difference and a set threshold. The scores are then mapped to obtain a health score for the SOC consistency index of each battery stack. This application is not limited to this.

[0073] In some embodiments, the in-pile temperature consistency index includes temperature range and maximum temperature difference. It can be calculated by obtaining the average temperature of all battery clusters in the battery stack, and calculating the temperature range = max(average cluster temperature) - min(average cluster temperature), denoted as t1; obtaining the maximum temperature difference data of the battery stack characteristic data, denoted as t2; and mapping scores according to the values ​​of t1 and t2 with reference to relevant standards, denoted as s1 and s2 respectively. Weights w1 and w2 are set according to historical experience, such that w1 + w2 = 1, and w1 and w2 both belong to (0,1). Then, the total score is score = s1 * w1 + s2 * w2, which is used as the health score of the in-pile temperature consistency index of each battery stack. This application is not limited to this.

[0074] In some embodiments, the stack energy efficiency index includes the energy efficiency parameter of the battery stack. The energy efficiency of all battery clusters in the battery stack is calculated, and the average value is taken as the energy efficiency of the battery stack. Then, with reference to the above threshold setting, a score mapping is performed to obtain the health score of the stack energy efficiency index of each battery stack. This application is not limited to this.

[0075] S402. Calculate the average health score of all preset battery cluster health indicators for all battery clusters in each battery stack, and obtain the average health score of the battery cluster health indicator for each battery stack.

[0076] In some embodiments, the average of the health scores of the insulation evaluation index, the connection impedance index, the energy efficiency index, the voltage consistency index, the temperature consistency index, and the average health score of the cell health index of all cell clusters in each battery stack can be calculated to obtain the health score of the average health index of the cell clusters of each battery stack. This application is not limited thereto.

[0077] In the above embodiments, by introducing current consistency index, stack humidity index, SOC consistency index, stack temperature consistency index and stack energy efficiency index, a comprehensive and accurate health assessment of the battery stack is carried out from multiple important dimensions. Through the comprehensive analysis of these indicators, potential problems of the battery stack can be identified in a timely manner, providing a more accurate basis for the subsequent health assessment of energy storage power stations.

[0078] In other embodiments of this application, the multiple preset power station health indicators also include station energy indicators. One implementation of the step of calculating the health scores of the multiple preset power station health indicators of the energy storage power station based on power station characteristic data and the health scores of each battery stack specifically includes: S501. Based on the power station characteristic data, obtain the values ​​of the parameters in the station energy index of the energy storage power station, compare the parameter values ​​with the set standards, obtain the parameter scores, perform score mapping, and obtain the health score of the station energy index of the energy storage power station. S502. Calculate the average health score of all preset battery stack health indicators for all battery stacks in the energy storage power station, and obtain the average health score of the battery stack health indicators of the energy storage power station.

[0079] In some embodiments, the station energy efficiency index includes the energy efficiency parameters of the energy storage station. By calculating the energy efficiency of all battery stacks in the energy storage station, taking the average value as the energy efficiency of the energy storage station, and then referring to the above-mentioned threshold setting, a score mapping is performed to obtain the health score of the station energy efficiency index of the energy storage station. This application is not limited to this.

[0080] In some embodiments, the average of the health scores of the current consistency index, the stack humidity index, the SOC consistency index, the stack temperature consistency index, the stack energy efficiency index, and the average health score of the cell health index of all battery stacks in the energy storage power station can be calculated to obtain the health score of the average health index of the battery stack of the energy storage power station. This application is not limited thereto.

[0081] In the above embodiments, by introducing the station energy efficiency index, the energy utilization efficiency of the energy storage station is evaluated from an overall perspective. Combined with the previous comprehensive evaluation of individual cells, battery clusters, and battery stacks, a complete and detailed multi-level health assessment system is constructed. Through comprehensive analysis and calculation of these different levels of indicators, the health status of the energy storage station can be evaluated in a comprehensive and accurate manner, potential problems and hidden dangers can be discovered in a timely manner, and the operational reliability and economy of the energy storage station can be effectively improved.

[0082] like Figure 4 As shown, in another embodiment of this application, a health management system for an energy storage power station is provided, comprising: Extraction unit 10 is used to extract features from the raw monitoring data of the energy storage power station to obtain feature data, including cell feature data of individual cells, battery cluster feature data of battery clusters, battery stack feature data of battery piles, and power station feature data of the energy storage power station. The first calculation unit 11 is used to calculate the health score of multiple preset cell health indicators for each individual cell based on cell characteristic data, and to calculate the total health score of each individual cell using a weighted average method. The second calculation unit 12 is used to calculate the health score of multiple preset battery cluster health indicators for each battery cluster based on the battery cluster feature data and the health score of each individual cell, and to calculate the total health score of each battery cluster using a weighted average method. The preset battery cluster health indicators include the average cell health indicator, and the health score of the average cell health indicator is the average of the health scores of all preset cell health indicators of all individual cells in each battery cluster. The third calculation unit 13 is used to calculate the health scores of multiple preset battery stack health indicators for each battery stack based on the battery stack feature data and the health scores of each battery cluster, and to calculate the total health score of each battery stack using a weighted average method. The preset battery stack health indicators include the average health index of the battery cluster, and the health score of the average health index of the battery cluster is the average of the health scores of all preset battery cluster health indicators of all battery clusters in each battery stack. The fourth calculation unit 14 is used to calculate the health scores of multiple preset power station health indicators of the energy storage power station based on the power station characteristic data and the health scores of each battery stack, and to calculate the total health score of the energy storage power station using a weighted average method. The preset power station health indicators include the average health index of the battery stack, and the health score of the average health index of the battery stack is the average of the health scores of all preset battery stack health indicators of all battery stacks in the energy storage power station. Alarm unit 15 is used to issue an alarm when the health score and / or total health score of any level in the individual cell, battery cluster, battery stack and energy storage power station are lower than a preset score threshold.

[0083] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A health management method for energy storage power stations based on a multi-level assessment system, characterized in that, include: Feature extraction is performed on the raw monitoring data of the energy storage power station to obtain feature data, which includes cell feature data of individual cells, battery cluster feature data of battery clusters, battery stack feature data of battery piles, and power station feature data of the energy storage power station. Based on the cell characteristic data, the health scores of multiple preset cell health indicators for each individual cell are calculated, and the total health score of each individual cell is calculated using a weighted average method. Based on the battery cluster feature data and the health score of each individual cell, the health scores of multiple preset battery cluster health indicators for each battery cluster are calculated, and the total health score of each battery cluster is calculated using a weighted average method. The preset battery cluster health indicators include the average cell health index, and the health score of the average cell health index is the average of the health scores of all preset cell health indicators of all individual cells in each battery cluster. Based on the battery stack feature data and the health score of each battery cluster, the health scores of multiple preset battery stack health indicators for each battery stack are calculated, and the total health score of each battery stack is calculated using a weighted average method. The preset battery stack health indicators include the average health index of the battery cluster, and the health score of the average health index of the battery cluster is the average of the health scores of all preset battery cluster health indicators of all battery clusters in each battery stack. Based on the power station characteristic data and the health scores of each battery stack, the health scores of multiple preset power station health indicators of the energy storage power station are calculated, and the total health score of the energy storage power station is calculated by using a weighted average method. The preset power station health indicators include the battery stack health average indicator, and the health score of the battery stack health average indicator is the average of the health scores of all preset battery stack health indicators of all battery stacks in the energy storage power station. An alarm will be triggered when the health score and / or total health score at any level of a single cell, battery cluster, battery stack, or energy storage power station falls below a preset score threshold.

2. The method as described in claim 1, characterized in that, The raw monitoring data of the energy storage power station is subjected to feature extraction to obtain feature data, including: The raw monitoring data of the energy storage power station is processed according to the three states of the battery: charging, discharging, and resting, and feature extraction is performed to obtain feature data for each of the three states.

3. The method as described in claim 1, characterized in that, The preset cell health indicators include cell temperature, cell voltage, cell internal resistance, cell energy efficiency, and equivalent cycle life. Based on the cell characteristic data, a health score for each individual cell is calculated for these preset cell health indicators, including: Based on the cell characteristic data, the values ​​of various parameters in the cell temperature index, cell voltage index, cell internal resistance index, cell energy efficiency index, and equivalent cycle life index of each individual cell are obtained. The values ​​of each parameter are compared with the set standards to obtain the score of each parameter. The scores are then mapped to obtain the health score of the cell temperature index, the cell voltage index, the cell internal resistance index, the cell energy efficiency index, and the equivalent cycle life index of each individual cell.

4. The method as described in claim 3, characterized in that, The cell internal resistance index includes the cell internal resistance parameter, and the calculation formula is as follows: ； In the formula, Indicates the internal resistance of the battery cell. The voltage at the end of the charging state of a single battery cell. The current representing the end of the charging state of a single battery cell, or... The voltage at the end of the discharge state of a single battery cell. This represents the current at the end of the discharge state of a single battery cell. This indicates the voltage at the start of the next resting phase of a single battery cell.

5. The method as described in claim 3, characterized in that, The cell energy efficiency index includes the battery's energy efficiency parameters, calculated using the following formula: ； In the formula, This indicates the battery's energy efficiency.

6. The method as described in claim 1, characterized in that, The preset battery cluster health indicators also include insulation assessment indicators, connection impedance indicators, battery cluster energy efficiency indicators, voltage consistency indicators, and temperature consistency indicators. The health score of each battery cluster is calculated based on the battery cluster characteristic data and the health score of each individual cell, including: Based on the battery cluster characteristic data, the values ​​of each parameter in the insulation evaluation index, connection impedance index, battery cluster energy efficiency index, voltage consistency index, and temperature consistency index of each battery cluster are obtained. The values ​​of each parameter are compared with the set standards to obtain the score of each parameter. The scores are then mapped to obtain the health score of each battery cluster's insulation evaluation index, connection impedance index, battery cluster energy efficiency index, voltage consistency index, and temperature consistency index. Calculate the average health score of all preset cell health indicators for all individual cells within each battery cluster to obtain the average health score of the cell health indicators for each battery cluster.

7. The method as described in claim 6, characterized in that, The voltage consistency index includes the voltage standard deviation parameter, which is calculated using the following formula: ； In the formula, SD represents the voltage standard deviation, and n represents the number of individual cells in the battery cluster. This represents the voltage of the individual battery cell numbered i. This represents the average voltage of all individual cells within the battery cluster.

8. The method as described in claim 1, characterized in that, The preset battery stack health indicators also include current consistency indicators, stack humidity indicators, SOC consistency indicators, stack internal temperature consistency indicators, and stack energy efficiency indicators. The health score of each battery stack is calculated based on the battery stack characteristic data and the health score of each battery cluster, including: Based on the battery stack characteristic data, the values ​​of various parameters in the current consistency index, stack humidity index, SOC consistency index, stack internal temperature consistency index, and stack energy efficiency index of each battery stack are obtained. The values ​​of each parameter are compared with the set standards to obtain the scores of each parameter. The scores are then mapped to obtain the health scores of the current consistency index, stack humidity index, SOC consistency index, stack internal temperature consistency index, and stack energy efficiency index of each battery stack. Calculate the average health score of all preset battery cluster health indicators for all battery clusters within each battery stack to obtain the average health score of the battery cluster health indicator for each battery stack.

9. The method as described in claim 1, characterized in that, The preset power station health indicators also include station energy indicators. The calculation of health scores for the preset power station health indicators of the energy storage power station based on the power station characteristic data and the health scores of each battery stack includes: Based on the power station characteristic data, the values ​​of the parameters in the station energy index of the energy storage power station are obtained. The parameter values ​​are compared with the set standards to obtain the parameter scores. The scores are mapped to obtain the health score of the station energy index of the energy storage power station. Calculate the average health score of all preset battery stack health indicators for all battery stacks in the energy storage power station to obtain the average health score of the battery stack health indicators of the energy storage power station.

10. A health management system for energy storage power stations based on a multi-level assessment system, characterized in that, include: The extraction unit is used to extract features from the raw monitoring data of the energy storage power station to obtain feature data, wherein the feature data includes cell feature data of individual cells, battery cluster feature data of battery clusters, battery stack feature data of battery piles, and power station feature data of the energy storage power station. The first calculation unit is used to calculate the health score of multiple preset cell health indicators for each individual cell based on the cell characteristic data, and to calculate the total health score of each individual cell using a weighted average method. The second calculation unit is used to calculate the health score of multiple preset battery cluster health indicators for each battery cluster based on the battery cluster feature data and the health score of each individual cell, and to calculate the total health score of each battery cluster using a weighted average method. The preset battery cluster health indicators include the average cell health indicator, and the health score of the average cell health indicator is the average of the health scores of all preset cell health indicators of all individual cells in each battery cluster. The third calculation unit is used to calculate the health score of multiple preset battery stack health indicators for each battery stack based on the battery stack feature data and the health score of each battery cluster, and to calculate the total health score of each battery stack using a weighted average method. The preset battery stack health indicators include the average health index of the battery cluster, and the health score of the average health index of the battery cluster is the average of the health scores of all preset battery cluster health indicators of all battery clusters in each battery stack. The fourth calculation unit is used to calculate the health scores of multiple preset power station health indicators of the energy storage power station based on the power station characteristic data and the health scores of each battery stack, and to calculate the total health score of the energy storage power station using a weighted average method. The preset power station health indicators include the average health index of the battery stack, and the health score of the average health index of the battery stack is the average of the health scores of all preset battery stack health indicators of all battery stacks in the energy storage power station. The alarm unit is used to issue an alarm when the health score and / or total health score of any level in the individual cell, battery cluster, battery stack, and energy storage power station are lower than a preset score threshold.

Images