Energy storage equipment health management method and system, electronic equipment and storage medium

Abstract

The invention provides an energy storage equipment health management method and system, electronic equipment and a storage medium, and belongs to the technical field of energy storage management.The method comprises the steps that multiple health feature vectors of management data of energy storage equipment are fused, and a comprehensive health index is obtained; obtaining a first health state of the energy storage equipment based on the comprehensive health index and the internal resistance of the energy storage equipment, obtaining a second health state of the energy storage equipment based on the comprehensive health index and a change trend of a current preset number of historical comprehensive health indexes, and fusing the first health state and the second health state, obtaining a target health state of the energy storage equipment; calculating a risk index of the energy storage equipment based on the target health state; and determining a management strategy of the energy storage equipment based on the risk index, and managing the energy storage equipment based on the management strategy. According to the energy storage equipment health management method and system, the electronic equipment and the storage medium provided by the invention, the management reliability of the energy storage equipment can be improved.

Description

Technical Field

[0001] The present application belongs to the field of energy storage management technology, and more specifically, relates to a health management method and system for energy storage equipment, electronic equipment, and storage medium. Background Art

[0002] With the increasing adoption of renewable energy and the advancement of grid modernization, energy storage devices are playing an increasingly important role in improving energy efficiency and ensuring grid stability. However, the performance of energy storage devices (especially electrochemical energy storage devices such as lithium-ion batteries and flow batteries) degrades with use and over time. Accurate assessment and effective management of their state of health (SOH) are directly related to the safety, reliability, and economic efficiency of energy storage systems.

[0003] Traditional health management methods often rely on a single indicator or simple threshold judgment, resulting in inaccurate judgment of the health status of energy storage equipment, and thus unable to achieve reliable management of energy storage equipment. Summary of the Invention

[0004] The purpose of this application is to provide a method and system for managing the health of energy storage equipment, an electronic device, and a storage medium to improve the reliability of energy storage equipment management.

[0005] In a first aspect of an embodiment of the present application, a method for managing the health of an energy storage device is provided, comprising: extracting features from a management data set of the energy storage device to obtain multiple health feature vectors of a current cycle; the management data set is a standardized data set collected on a cycle basis after preprocessing the original management data of the energy storage device; a cycle is a complete charge and discharge cycle completed by the energy storage device; the original management data is data generated by the energy storage device during the charge and discharge process; The multiple health feature vectors of the current cycle are fused to obtain a comprehensive health index; Determining a first health state of the energy storage device based on the comprehensive health index and the internal resistance of the energy storage device, determining a second health state of the energy storage device based on the comprehensive health index and the historical comprehensive health index, and fusing the first health state and the second health state to obtain a target health state of the energy storage device; Calculate the risk index of energy storage equipment based on the target health status; A management strategy for energy storage equipment is determined based on the risk index, and the energy storage equipment is managed based on the management strategy.

[0006] A second aspect of an embodiment of the present application provides an energy storage device health management system, including: The feature extraction module is used to extract features from the management data set of the energy storage device to obtain multiple health feature vectors of the current cycle. The management data set is a standardized data set collected by cycle after preprocessing the original management data of the energy storage device. A cycle is a complete charge and discharge cycle completed by the energy storage device. The original management data is the data generated by the energy storage device during the charge and discharge process. The first fusion module is used to fuse multiple health feature vectors of the current cycle to obtain a comprehensive health index; a second fusion module, configured to determine a first health state of the energy storage device based on the comprehensive health index and the internal resistance of the energy storage device, determine a second health state of the energy storage device based on the comprehensive health index and the historical comprehensive health index, and fuse the first health state and the second health state to obtain a target health state of the energy storage device; A risk calculation module is used to calculate the risk index of the energy storage device based on the target health status; The management module is used to determine a management strategy for the energy storage device based on the risk index and manage the energy storage device based on the management strategy.

[0007] According to a third aspect of an embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above-mentioned energy storage device health management method when executing the computer program.

[0008] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned energy storage device health management method are implemented.

[0009] The beneficial effects of the energy storage equipment health management method and system, electronic device, and storage medium provided in the embodiments of the present application are: the present application pre-processes the original data and extracts health features to ensure data quality and feature comprehensiveness, laying the foundation for health assessment. Secondly, the comprehensive health index comprehensively evaluates multi-dimensional features to make the health status intuitive. Combining the dual health status assessment of internal resistance and historical comprehensive health index, it takes into account the current health level and degradation trend, avoiding the one-sidedness of single-dimensional assessment. The risk index integrates the target health status and its changing trend to quantify potential risks. Finally, differentiated management strategies are formulated based on risk levels to achieve closed-loop management from monitoring to control, which can provide early warning of equipment failures, optimize operation and maintenance strategies, and extend equipment life, thereby achieving reliable management of energy storage equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0011] Figure 1 A flow chart of a method for managing the health of an energy storage device according to an embodiment of the present application; Figure 2 A structural block diagram of the energy storage device health management system provided in one embodiment of the present application; Figure 3 A schematic block diagram of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0012] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, systems, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0013] In order to make the purpose, technical solutions and advantages of this application clearer, specific embodiments will be described below with reference to the accompanying drawings.

[0014] Please refer to Figure 1 , Figure 1 A flowchart of a method for managing the health of an energy storage device provided in one embodiment of the present application, which may be executed by an electronic device, may include: S101: Feature extraction is performed on the management data set of the energy storage device to obtain multiple health feature vectors of the current cycle. The management data set is a standardized data set collected by cycle after preprocessing the original management data of the energy storage device. A cycle is a complete charge and discharge cycle completed by the energy storage device. The original management data is the data generated by the energy storage device during the charging and discharging process.

[0015] In this embodiment, the energy storage device is a device for storing electrical energy, such as a lithium battery, a lead-acid battery, a flow battery, etc.

[0016] A health feature vector is a multidimensional indicator (such as internal resistance growth rate, capacity retention rate, and charge / discharge efficiency) extracted from single-cycle data, characterizing the health status of the energy storage device. Each one-dimensional indicator corresponds to a health feature vector. For example, the multiple health feature vectors in S101 may include a health feature vector corresponding to the internal resistance growth rate, a health feature vector corresponding to the capacity retention rate, and a health feature vector corresponding to the charge / discharge efficiency.

[0017] In this embodiment, the collected raw data (such as voltage fluctuations and temperature changes) is preprocessed, including: removing sensor outliers (such as voltage jumps and temperature changes); normalizing multi-source data (voltage, current, and temperature) to a unified dimension; and identifying complete charge and discharge cycles based on current direction (charging: current > 0 and the energy storage device's state of charge increases; discharging: current < 0 and the energy storage device's state of charge decreases). In this embodiment of the present application, preprocessing the collected raw data ensures data quality and eliminates interference such as sensor noise and communication anomalies, thereby improving the accuracy of subsequent determinations of the energy storage device's health status.

[0018] Extract key features from each cycle, such as capacity characteristics, internal resistance characteristics, voltage characteristics, temperature characteristics, etc. of the energy storage device.

[0019] S102: Fusing multiple health feature vectors of the current cycle to obtain a comprehensive health index.

[0020] In this embodiment, multiple health feature vectors contain health information of different dimensions, making it complex to directly use these high-dimensional features for decision making. The comprehensive health index generates a comprehensive health metric by weightedly integrating multiple health features, making the expression of health status more intuitive and concise.

[0021] The comprehensive health index is a quantitative representation of the current circulatory health status, and the higher the value, the better the health status.

[0022] This embodiment can fuse multiple health feature vectors of the cycle through a weighted average algorithm. The weight of each feature vector is determined based on feature importance analysis, and then the comprehensive health index is obtained by calculating the weighted sum. The calculation formula is:

[0023] in, Indicates the comprehensive health index of the current cycle, represents the normalized value of the jth healthy feature vector in the current cycle, represents the weight of the jth health feature vector, and n represents the number of health features.

[0024] The closer the comprehensive health index value is to 1, the better the health status is, and the closer it is to 0, the worse the health status is.

[0025] S103: Determine a first health state of the energy storage device based on the comprehensive health index and the internal resistance of the energy storage device, determine a second health state of the energy storage device based on the comprehensive health index and the historical comprehensive health index, and fuse the first health state and the second health state to obtain a target health state of the energy storage device.

[0026] In this embodiment, the first health state of the energy storage device can be calculated using a comprehensive health index and the internal resistance value measured during the current cycle. Internal resistance is a key indicator of aging in energy storage devices (e.g., lithium batteries). Increased internal resistance can lead to decreased energy efficiency and increased heat generation risk. In this embodiment, the internal resistance of the energy storage device can include: the initial internal resistance of the energy storage device, the current internal resistance of the energy storage device, and the internal resistance at the end of the energy storage device's life.

[0027] This embodiment can combine the comprehensive health index and internal resistance to obtain a first health status (such as "good", "general", or "warning") through a mapping relationship (such as a table lookup or formula calculation). In this embodiment of the present application, the first health status can be characterized by the first health index. For example, if the first health index is greater than 0.7, the first health status is characterized as good; if the first health index is greater than 0.5 and not greater than 0.7, the first health status is characterized as general; and if the first health index is not greater than 0.5, the first health status is characterized as warning.

[0028] In this embodiment, the change trend (such as slope and difference value) of the current comprehensive health index and a preset number of historical comprehensive health indices can be calculated. The change trend reflects the deterioration trend of the health state. Furthermore, the second health state is calculated based on the historical comprehensive health index change trend and the comprehensive health index itself. For example, if the historical comprehensive health index change trend reflects a rapid decline in the comprehensive health index, and the comprehensive health index value corresponding to the current cycle is low, then the second health state is also relatively low. This reflects the dynamic health trend of the energy storage device, that is, the evolution rate of the health state. This embodiment takes into account the time dimension of device degradation and can detect possible signs of accelerated aging. Furthermore, the second health state can also be characterized by the second health index. For example, if the second health index is greater than 0.7, it indicates that the second health state is good; if the second health index is greater than 0.5 and not greater than 0.7, it indicates that the second health state is fair; if the second health index is not greater than 0.5, it indicates that the second health state is a warning.

[0029] In this embodiment, the first health state and the second health state can be combined using a weighted fusion method to obtain a target health state. This state integrates the current health level, the historical degradation trend of the energy storage device, and the impact of internal resistance changes on the health state of the energy storage device, more comprehensively reflecting the actual health status of the device and avoiding the one-sidedness of single-dimensional assessment.

[0030] For example: If the first health status is 0.6, it indicates that the first health status is "general"; the second health status is 0.3, it indicates that the second health status is "warning". If the weights corresponding to the first health status and the second health status are 0.5 respectively, the fused health index is 0.45, which indicates that the target health status after fusion is "warning".

[0031] S104: Calculate a risk index of the energy storage device based on the target health status.

[0032] In this embodiment, the risk index is a comprehensive risk quantification indicator used to evaluate the current overall risk level of the energy storage device, and can be obtained from the target health status.

[0033] Specifically, the calculation of the risk index is based on the target health status, and the calculation formula of the risk index is:

[0034] in, The risk index of energy storage equipment is a quantitative result of the comprehensive health status and its changing trend. The larger the value, the higher the risk. Indicates the target health state, which is obtained by fusing the first health state and the second health state, reflecting the current comprehensive health level of the device; The weight coefficient representing the change trend is used to adjust the impact of historical change trends on risks. When >0, the greater the change trend, the greater the risk increase; Indicates the number of time window periods used to calculate historical change trends; Indicates the target health status value of the current cycle; Indicates the target health status value of the cycle history m cycles away from the current cycle (for example, m=5, Indicates the historical target health status value corresponding to the cycle 5 cycles away from the current cycle), used to calculate the historical change trend; A nonlinear adjustment parameter representing the changing trend, used to control the nonlinear impact of the absolute value of the changing trend on the risk. For example, when γ=1, it is a linear relationship, and when γ>1, the impact of rapid changes is amplified.

[0035] Represents the basic risk item, which is based on the basic risk of the current health status. The closer it is to 0 (the worse the health status), the larger the value is and the higher the risk is.

[0036] It represents the risk term of changing trend, reflecting the superimposed impact of the decline rate of health status on risk. It is the average absolute value of the change trend within m cycles, which measures the speed of health status decline.

[0037] Through the risk index, system managers can clearly understand the current risk status of energy storage equipment and take corresponding management measures accordingly.

[0038] S105: Determine a management strategy for the energy storage device based on the risk index, and manage the energy storage device based on the management strategy.

[0039] In this embodiment, referring to the management strategy comparison table in Table 1, a corresponding management strategy can be automatically selected or adjusted according to the calculated risk index.

[0040] Table 1 Management strategy comparison table

[0041] In this embodiment, control signals based on the management strategy can be sent to the control system of the energy storage device (such as BMS, PCS, and temperature control system) to achieve actual management and control of the energy storage device, thereby maximizing its economic value and service life while ensuring the safety of the equipment.

[0042] From the above, it can be concluded that, first, this embodiment preprocesses the raw data and extracts health features to ensure data quality and feature comprehensiveness, laying the foundation for health assessment. Secondly, the comprehensive health index comprehensively evaluates multi-dimensional features to make the health status intuitive. Combining the dual health status assessment of internal resistance and historical comprehensive health index change trends, it takes into account both the current health level and the degradation trend, avoiding the one-sidedness of a single-dimensional assessment. The risk index integrates the target health status and its changing trends to quantify potential risks. Finally, differentiated management strategies are formulated based on risk levels to achieve closed-loop management from monitoring to control, which can provide early warning of equipment failures, optimize operation and maintenance strategies, and extend equipment life.

[0043] In one embodiment of the present application, a method for acquiring a management data set includes: Preprocess the original management data of the energy storage device to obtain initial management data. The preprocessing includes data cleaning and noise filtering. The initial management data is cyclically identified based on the direction of the current during the charge and discharge process of the energy storage device to obtain different types of initial management data within the current cycle; the categories include voltage, current and temperature; Based on a preset time interval, time series alignment is performed on different types of initial management data in the current cycle to obtain a management data set for the energy storage device.

[0044] In this embodiment, the original management data includes electrical parameters (voltage, current, SOC), physical parameters (temperature, pressure), environmental parameters (humidity, ambient temperature), etc. during the operation of the energy storage device, which can be collected in real time through corresponding sensors.

[0045] This embodiment uses the interquartile range method to identify and delete data points that significantly deviate from the normal range (e.g., voltage jumps, temperature spikes). Short-term missing data is filled using linear interpolation and sliding averages; long-term missing data segments are marked as invalid data segments. High-frequency electromagnetic interference is then eliminated using a low-pass filter (e.g., a Butterworth filter). After this processing, initial management data is obtained.

[0046] In this embodiment, a complete charging (from the start of charging to the end of charging) and discharging (from the start of discharging to the end of discharging) cycle can be identified based on the current direction and the change in the state of charge.

[0047] The mapping relationship between current direction and charge and discharge state is: In the charging state, the current direction is positive (flowing into the energy storage device), and the state of charge continues to rise; In the discharge state, the current direction is negative (flowing out of the energy storage device), and the state of charge continues to decrease.

[0048] When the current turns from negative to positive and the rate of increase of the state of charge exceeds a threshold (e.g., 0.5% / min), it is marked as the start of a charging cycle. When the current drops to near zero (e.g., <5% of the rated current) and the state of charge no longer changes, it is marked as the end of a charging cycle. A complete cycle is a continuous data segment from the start of charging to the end of charging, or from the start of discharging to the end of discharging. In this embodiment of the present application, based on the current direction of the energy storage device during the charging and discharging process, the initial management data (voltage data, current data, and temperature data) of each type of charging state stage in the current cycle is identified from the initial management data, as well as the initial management data (voltage data, current data, and temperature data) of each type of discharging state stage in the current cycle is identified.

[0049] In this embodiment, different sensors (e.g., voltage sensor, temperature sensor) have different sampling frequencies (e.g., 10 Hz for voltage, 1 Hz for temperature), resulting in data timing asynchrony. To address this issue, in this embodiment, the time series of different types of initial management data in the current cycle are aligned. Specifically, this may include: aligning the various types of management data in the charging phase (e.g., aligning the voltage data, current data, and temperature data in the charging phase), and aligning the various types of management data in the discharging phase (e.g., aligning the voltage data, current data, and temperature data in the discharging phase).

[0050] Specifically, this embodiment can use the lowest common multiple frequency (e.g., 1 Hz) as a benchmark, downsampling high-frequency data (e.g., taking the average value per second for voltage data) and upsampling low-frequency data (e.g., linear interpolation for temperature data). Sensor clock bias can be eliminated through hardware clock synchronization (e.g., GPS timing) or software timestamp correction.

[0051] From the above, it can be concluded that this embodiment solves the problems of "high noise, disordered timing, and fuzzy cycles" in the energy storage device operating data by preprocessing the original management data and identifying cycles, thereby providing high-quality input data for the health management algorithm.

[0052] In one embodiment of the present application, multiple health feature vectors of the current cycle are fused to obtain a comprehensive health index, including: Normalizing the multiple health feature vectors respectively to obtain multiple target health feature vectors; assigning weights to the multiple target health feature vectors based on the degree of influence of each of the multiple target health feature vectors on the health status of the energy storage device; Based on multiple health feature vectors and their corresponding weights, a weighted fusion is performed to obtain a comprehensive health index.

[0053] In this embodiment, different health feature vectors have different dimensions, such as voltage, current, and temperature. In order to eliminate the dimensional differences of different health features and make the features comparable, this embodiment normalizes multiple health feature vectors to obtain multiple target health feature vectors.

[0054] In this embodiment, multiple health feature vectors can be mapped to a uniform interval (such as [0, 1]) through mathematical transformation, such as through minimum-maximum normalization:

[0055] in, represents the value of the target health feature vector, represents the value of the health feature vector, represents the maximum value of the health feature vector, Represents the minimum value of the healthy feature vector.

[0056] For example, if the value of a health feature vector is 200 mV, the minimum value of the health feature vector is 100 mV and the maximum value is 300 mV. After minimum-maximum normalization, it is (200-100) / (300-100)=0.5, that is, it is mapped to 0.5.

[0057] In this embodiment, different health characteristics have different degrees of influence on the health status of the energy storage device (for example, internal resistance growth may be more critical than temperature fluctuation), and their importance needs to be quantified through weights.

[0058] In this embodiment, weights can be assigned to multiple target health feature vectors through principal component analysis, that is, principal components are extracted through dimensionality reduction, and weights are determined according to variance contribution rates.

[0059] Assume that k target health feature vectors are V = [v1, v2, ..., v k ], corresponding weight ,satisfy .

[0060] In this embodiment, the normalized eigenvectors are linearly combined with the weights to obtain a comprehensive health index.

[0061]

[0062] in, Indicates the comprehensive health index of the current cycle, represents the normalized value of the jth healthy feature vector in the current cycle, represents the weight of the jth health feature vector, and k represents the number of health features.

[0063] For example, if there are three eigenvectors v1=0.6 (voltage), v2=0.8 (internal resistance), and v3=0.4 (temperature), the corresponding weights are =0.25, =0.4, =0.35, then: CHI=0.6×0.25+0.8×0.4+0.4×0.35=0.63.

[0064] The comprehensive health index converts multi-dimensional features into a numerical value in the range of 0-1 through weighted fusion. The higher the value, the better the health status of the energy storage equipment, and vice versa.

[0065] From the above, it can be concluded that this embodiment normalizes the health feature vectors to eliminate dimensional differences and make the features comparable; assigns weights based on the degree of influence of the features on the health status of the equipment to highlight key indicators; and generates a comprehensive health index through weighted fusion, quantifying multi-dimensional health information into a single indicator to make the expression of health status more intuitive.

[0066] In one embodiment of the present application, determining a first health state of the energy storage device based on the comprehensive health index and the internal resistance of the energy storage device includes: Determining a first health state of the energy storage device based on the comprehensive health index and the internal resistance of the energy storage device and using a first formula; Among them, the first formula is:

[0067] in, Indicates the first health status of the energy storage device, represents the initial internal resistance of the energy storage device, Indicates the current internal resistance of the energy storage device, Indicates the internal resistance of the energy storage device at the end of its life. Indicates the comprehensive health index of the current cycle, Indicates the current actual capacity of the energy storage device, Indicates the nominal capacity of the energy storage device.

[0068] In this embodiment, It represents the internal resistance degradation term, reflecting the degree of degradation of the internal resistance of the energy storage device over the usage cycle. Indicates the internal resistance of the energy storage device at the end of its life. If near When the ratio approaches 1, it indicates that the health status is deteriorating.

[0069] It represents the capacity attenuation term, which reflects the ratio of actual capacity to nominal capacity. When the energy storage device ages, Decreases, the ratio decreases, and the health status decreases.

[0070] In this embodiment, the health status of the energy storage device can be determined by internal resistance growth and capacity decay, but the correlation between the two varies at different aging stages. For example, initial capacity decay may dominate health degradation, while later internal resistance growth is more significant.

[0071] In this embodiment, both the internal resistance degradation term and the capacity attenuation term are converted into dimensionless values ​​in the interval [0, 1] through normalization processing, ensuring that indicators of different dimensions can be directly weighted and summed.

[0072] For example: If , the internal resistance degradation term is close to 0 (optimal health state); if , the internal resistance degradation term is 1 (end of life); if , the capacity attenuation term is 1; if , the capacity decay term is 0.8.

[0073] The final calculation The value range is [0, 1], and the lower the value, the better the health status.

[0074] As can be seen from the above, this embodiment integrates the internal resistance degradation and capacity attenuation indicators and uses the comprehensive health index (CHI) to dynamically adjust weights to achieve a multi-dimensional assessment of the health status of energy storage equipment. This can adapt to the dominant failure modes at different aging stages, avoid the one-sidedness of a single indicator, and improve the accuracy of health assessment and adaptability to operating conditions.

[0075] In one embodiment of the present application, determining a second health state of the energy storage device based on the comprehensive health index and the historical comprehensive health index includes: Determining a second health state of the energy storage device based on the comprehensive health index and the historical comprehensive health index and using a second formula; Among them, the second formula is:

[0076] in, Indicates the second health state of the energy storage device, Indicates the comprehensive health index of the current cycle, Indicates the changing trend of the comprehensive health index from the mn cycle to the m cycle period, represents the historical comprehensive health index, represents the weight coefficient, Indicates the current actual capacity of the energy storage device, Indicates the nominal capacity of the energy storage device.

[0077] In this embodiment, The LSTM network captures the temporal variation of the comprehensive health index from time mn to time m. Using memory cells to process long-term dependencies, it reflects the degradation trend of the energy storage device's health (e.g., accelerated decay or stable aging). The LSTM network outputs values ​​reflecting the dynamic trend of health status changes from time mn to the current time m, which can be used to predict future health status evolution.

[0078] Weight coefficient The weight used to balance the historical trend and the current status. When the energy storage device is in the stable aging stage, It can be set to a smaller value to focus on the current health indicators; when the equipment is nearing the end of its life or the working conditions fluctuate greatly, increase It can enhance the impact of trend analysis and capture accelerated degradation characteristics in advance.

[0079] and Complement each other. When it increases, the weight of trend analysis increases, and vice versa, more emphasis is placed on the current capacity and the immediate status of the comprehensive health index.

[0080] In this embodiment, the full life cycle data of the energy storage device (such as charge and discharge cycles, CHI changes, and actual health status values) can be used to construct an optimization objective function and solve the problem of minimizing the objective function. Value. Specifically expressed as:

[0081] in, represents the second health status prediction value calculated by the second formula for the i-th cycle sample, represents the measured value of the second health state of the i-th cycle sample (which can be a real value directly obtained through experiments or sensors), and N represents the total number of cycle samples.

[0082] It can be concluded from the above that this embodiment Dynamically adjust the weights of LSTM time series trends and capacity status, integrate historical CHI change trends with current capacity attenuation characteristics, capture the dynamic trend of health degradation, and combine with real-time capacity status to improve the foresight and accuracy of health assessment under complex working conditions.

[0083] In one embodiment of the present application, the first health state and the second health state are integrated to obtain a target health state of the energy storage device, including: Calculate the basic weights corresponding to the first health state and the second health state respectively based on the confidence levels of the first health state and the second health state; Calculating the operating condition matching factors of the first health state and the second health state based on the correlation between the current operating condition characteristics of the energy storage device and the first health state and the second health state, respectively; the operating condition characteristics represent the current operating conditions of the energy storage device; the correlation between the current operating condition characteristics of the energy storage device and the first health state is the degree of correlation between the current operating conditions of the energy storage device and the first health state, and the correlation between the current operating condition characteristics of the energy storage device and the second health state is the degree of correlation between the current operating conditions of the energy storage device and the second health state; Calculating average errors of the historical first health state and the historical second health state of the energy storage device, and normalizing them based on the average errors to obtain historical performance factors corresponding to the first health state and the second health state; The fusion weight corresponding to the first health state is obtained by fusing the basic weight, the working condition matching factor, and the historical performance factor corresponding to the first health state, and the fusion weight corresponding to the second health state is obtained by fusing the basic weight, the working condition matching factor, and the historical performance factor corresponding to the second health state; A weighted fusion is performed based on the first health state, the second health state, and their corresponding fusion weights to obtain a target health state of the energy storage device.

[0084] In this embodiment, the confidence level reflects the reliability of each health status assessment method and can be determined based on the theoretical basis or data source of the assessment model. For example, a first health status can be derived using a first model, and a second health status can be derived using a second model. The confidence level can reflect the confidence of the first and second models in predicting the health status.

[0085] Specifically, the basic weight formula in this embodiment is expressed as:

[0086]

[0087] in, represents the basic weight corresponding to the first health state, Indicates the basic weight corresponding to the second health state, represents the confidence of the first health state, Indicates the confidence level of the second health state.

[0088] In this embodiment, the operating condition characteristics represent the current operating conditions of the energy storage device, such as temperature, charge / discharge rate, state of charge, etc. The correlation degree represents the correlation between the operating condition characteristics and each health status assessment method.

[0089] For example: Under high temperature conditions, the change of internal resistance The impact is significant. The correlation is high; under frequent charge and discharge conditions, the CHI trend is The impact is significant. The correlation is high.

[0090] In this embodiment, the correlation between the current operating condition characteristics of the energy storage device and the first health state and the second health state can be calculated by cosine similarity.

[0091] In this embodiment, the average error represents the deviation between the historical evaluation results and the true value, reflecting the long-term stability of the health status judgment. The calculation formula of the average error is:

[0092]

[0093] in, Indicates the average error of the historical first health state of the energy storage device, Represents the average error of the historical second health state of the energy storage device, It represents the first health status prediction value of the i-th cycle sample calculated by the first formula.

[0094] The formula for calculating the historical performance factor is:

[0095]

[0096] in, The historical performance factor representing the first health state, A historical performance factor representing the second health state.

[0097] In this embodiment, the fusion weight corresponding to the first health state is obtained by fusing the basic weight, the working condition matching factor, and the historical performance factor corresponding to the first health state, including: multiplying the basic weight, the working condition matching factor, and the historical performance factor corresponding to the first health state and normalizing them to obtain the fusion weight corresponding to the first health state. The fusion weight corresponding to the first health state is expressed as:

[0098] in, represents the fusion weight corresponding to the first health state, Indicates the working condition matching factor of the first health state, Indicates the operating condition matching factor of the second health state.

[0099]

[0100] in, Indicates the fusion weight corresponding to the second health state.

[0101] Based on the first health state and the second health state and their corresponding fusion weights, a weighted fusion is performed to obtain the target health state of the energy storage device. Specifically expressed as:

[0102] From the above, it can be concluded that this embodiment calculates the fusion weight by comprehensively considering the confidence, working condition matching and historical performance, and dynamically adjusts the influence of the first health state and the second health state to make the target health state assessment more accurate.

[0103] In one embodiment of the present application, the method further includes: Based on the target health state and multiple health eigenvectors, the health decay cost for the next cycle and the current dynamic power envelope of the energy storage device are obtained. The health decay cost is the loss cost caused by aging of the energy storage device during each charge and discharge cycle. The dynamic power envelope is the maximum charge and discharge power limit allowed by the current energy storage device in a healthy state. The charge and discharge power corresponding to each future cycle of the energy storage device is predicted based on the health decay cost and dynamic power envelope.

[0104] In this embodiment, the worse the health status, the higher the aging loss per cycle (e.g., accelerated capacity decay). A mathematical model is used to convert health indicators into economic costs (e.g., capacity loss per cycle converted to replacement costs). For example, if the target health status shows 80% remaining capacity, combined with historical decay data, the cost of capacity loss due to aging in the next cycle can be estimated.

[0105] In this embodiment, the deterioration of the health status may result in a decrease in the ability of the energy storage device to withstand high current charging and discharging (eg, increased internal resistance and easy heating).

[0106] This embodiment can establish a mapping relationship between the health state and the maximum allowable power through historical data or physical models (such as equivalent circuit models). For example, when the health state is below a threshold, the dynamic power envelope will shrink, limiting the charge and discharge power to avoid accelerated aging.

[0107] In this embodiment, to reduce aging costs, power planning needs to avoid excessive loss of health status (eg, reducing the number of high-power charge and discharge times).

[0108] The power forecast must be within the power boundary allowed by the current health status (for example, the maximum charging power does not exceed the upper limit of the dynamic envelope).

[0109] In this embodiment, historical operating patterns and future load demands can be combined to generate a charge and discharge power that balances economy and safety under cost and power constraints through optimization algorithms (such as model predictive control). For example, during periods of high health decay costs, low power charging and discharging is preferred, while when the dynamic power envelope is loose, the power can be appropriately increased to meet load demand. Model predictive control can be expressed as:

[0110] in, Indicates the predicted charge and discharge power of future cycles (positive values ​​indicate charging, negative values ​​indicate discharging), Indicates the number of predicted future cycles; represents the health decay cost of the future i-th cycle, and is the dynamic power envelope function; The weight coefficient that weighs the health attenuation cost and the power tracking error can be determined empirically. The larger it is, the higher the priority is for meeting the reference power requirement; The smaller it is, the higher the priority is to reduce aging costs; represents the reference power of the future i-th cycle.

[0111] During the application process, the dynamic power envelope constraints must be met, namely:

[0112] in, Indicates the maximum discharge power allowed based on the current health status at time t; Represents the maximum charging power allowed based on the current health status at time t.

[0113] As can be concluded from the above, this embodiment calculates the health decay cost and dynamic power envelope through the target health state and health eigenvector, and combines the two to predict future charge and discharge power. This can minimize aging losses while meeting power requirements, dynamically adjust power boundaries, achieve a balance between the lifespan and economic efficiency of energy storage equipment, and improve operational safety and scientific management.

[0114] Corresponding to the energy storage device health management method of the above embodiment, Figure 2 This is a structural block diagram of the energy storage device health management system provided in one embodiment of the present application. For ease of explanation, only the parts related to the embodiment of the present application are shown. Figure 2 The energy storage equipment health management system 20 includes: a feature extraction module 21 , a first fusion module 22 , a second fusion module 23 , a risk calculation module 24 , and a management module 25 .

[0115] The feature extraction module 21 is used to extract features from the management data set of the energy storage device to obtain multiple health feature vectors of the current cycle. The management data set is a standardized data set collected by cycle after preprocessing the original management data of the energy storage device. A cycle is a complete charge and discharge cycle completed by the energy storage device. The original management data is the data generated by the energy storage device during the charge and discharge process. A first fusion module 22 is used to fuse multiple health feature vectors of the current cycle to obtain a comprehensive health index; A second fusion module 23 is configured to determine a first health state of the energy storage device based on the comprehensive health index and the internal resistance of the energy storage device, determine a second health state of the energy storage device based on the comprehensive health index and the historical comprehensive health index, and fuse the first health state and the second health state to obtain a target health state of the energy storage device; a risk calculation module 24, configured to calculate a risk index of the energy storage device based on the target health status; The management module 25 is configured to determine a management strategy for the energy storage device based on the risk index, and manage the energy storage device based on the management strategy.

[0116] In one embodiment of the present application, the energy storage device health management system 20 further includes: a management data set acquisition module; specifically configured to: Preprocess the original management data of the energy storage device to obtain initial management data. The preprocessing includes data cleaning and noise filtering. The initial management data is cyclically identified based on the direction of the current during the charge and discharge process of the energy storage device to obtain different types of initial management data within the current cycle; the categories include voltage, current and temperature; Based on a preset time interval, time series alignment is performed on different types of initial management data in the current cycle to obtain a management data set for the energy storage device.

[0117] In one embodiment of the present application, the first fusion module 22 is specifically configured to: Normalizing the multiple health feature vectors respectively to obtain multiple target health feature vectors; assigning weights to the multiple target health feature vectors based on the degree of influence of each of the multiple target health feature vectors on the health status of the energy storage device; Based on multiple health feature vectors and their corresponding weights, a weighted fusion is performed to obtain a comprehensive health index.

[0118] In one embodiment of the present application, the second fusion module 23 is specifically configured to: Determining a first health state of the energy storage device based on the comprehensive health index and the internal resistance of the energy storage device and using a first formula; Among them, the first formula is:

[0119] in, Indicates the first health status of the energy storage device, represents the initial internal resistance of the energy storage device, Indicates the current internal resistance of the energy storage device, Indicates the internal resistance of the energy storage device at the end of its life. Indicates the comprehensive health index of the current cycle, Indicates the current actual capacity of the energy storage device, Indicates the nominal capacity of the energy storage device.

[0120] In one embodiment of the present application, the second fusion module 23 is further configured to: Determining a second health state of the energy storage device based on the comprehensive health index and the historical comprehensive health index and using a second formula; Among them, the second formula is:

[0121] in, Indicates the second health state of the energy storage device, Indicates the comprehensive health index of the current cycle, Indicates the changing trend of the comprehensive health index from the mn cycle to the m cycle period, represents the historical comprehensive health index, represents the weight coefficient, Indicates the current actual capacity of the energy storage device, Indicates the nominal capacity of the energy storage device.

[0122] In one embodiment of the present application, the second fusion module 23 is further configured to: Calculate the basic weights corresponding to the first health state and the second health state respectively based on the confidence levels of the first health state and the second health state; Calculating the operating condition matching factors of the first health state and the second health state based on the correlation between the current operating condition characteristics of the energy storage device and the first health state and the second health state, respectively; the operating condition characteristics represent the current operating conditions of the energy storage device; the correlation between the current operating condition characteristics of the energy storage device and the first health state is the degree of correlation between the current operating conditions of the energy storage device and the first health state, and the correlation between the current operating condition characteristics of the energy storage device and the second health state is the degree of correlation between the current operating conditions of the energy storage device and the second health state; Calculating average errors of the historical first health state and the historical second health state of the energy storage device, and normalizing them based on the average errors to obtain historical performance factors corresponding to the first health state and the second health state; The fusion weight corresponding to the first health state is obtained by fusing the basic weight, the working condition matching factor, and the historical performance factor corresponding to the first health state, and the fusion weight corresponding to the second health state is obtained by fusing the basic weight, the working condition matching factor, and the historical performance factor corresponding to the second health state; A weighted fusion is performed based on the first health state, the second health state, and their corresponding fusion weights to obtain a target health state of the energy storage device.

[0123] In one embodiment of the present application, the energy storage device health management system 20 further includes: a power prediction module; specifically configured to: Based on the target health state and multiple health eigenvectors, the health decay cost for the next cycle and the current dynamic power envelope of the energy storage device are obtained. The health decay cost is the loss cost caused by aging of the energy storage device during each charge and discharge cycle. The dynamic power envelope is the maximum charge and discharge power limit allowed by the current energy storage device in a healthy state. The charge and discharge power corresponding to each future cycle of the energy storage device is predicted based on the health decay cost and dynamic power envelope.

[0124] See also Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided in one embodiment of the present application. Figure 3 The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of the modules / units in the above-mentioned system embodiments, such as Figure 2 The functions of the feature extraction module 21, the first fusion module 22, the second fusion module 23, the risk calculation module 24, and the management module 25 are shown.

[0125] It should be understood that in the embodiment of the present application, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0126] The input device 302 may include a touchpad, a fingerprint collection sensor (for collecting user fingerprint information and fingerprint direction information), a microphone, etc. The output device 303 may include a display (LCD, etc.), a speaker, etc.

[0127] The memory 304 may include a read-only memory and a random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information such as the first health status and the second health status.

[0128] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiment of the present application can execute the implementation method described in the energy storage device health management method provided in the embodiment of the present application, and can also execute the implementation method of the electronic device described in the embodiment of the present application, which will not be repeated here.

[0129] In another embodiment of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program. The computer program includes program instructions. When the program instructions are executed by a processor, all or part of the process of the method in the above embodiment is implemented. The computer program can also be used to instruct related hardware to complete the process. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of each of the above method embodiments are implemented. The computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can include: any entity or system capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium.

[0130] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. Furthermore, the computer-readable storage medium can include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or is about to be output.

[0131] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0132] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0133] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or can be an electrical, mechanical or other form of connection.

[0134] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0135] In addition, the functional modules in the various embodiments of the present application may be integrated into a single processing unit, or each module may exist physically separately, or two or more modules may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0136] The above are only specific embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and such modifications or substitutions should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for managing the health of an energy storage device, characterized in that: include: Perform feature extraction on the management data set of the energy storage device to obtain multiple health feature vectors of the current cycle; The management data set is a standardized data set collected in a cyclic manner after preprocessing the original management data of the energy storage device; The cycle is a complete charge and discharge cycle completed by the energy storage device; the original management data is the data generated by the energy storage device during the charge and discharge process; fusing the multiple health feature vectors of the current cycle to obtain a comprehensive health index; determining a first health state of the energy storage device based on the comprehensive health index and the internal resistance of the energy storage device, determining a second health state of the energy storage device based on the comprehensive health index and a historical comprehensive health index, and fusing the first health state and the second health state to obtain a target health state of the energy storage device; Calculating a risk index of the energy storage device based on the target health status; A management strategy for the energy storage device is determined based on the risk index, and the energy storage device is managed based on the management strategy.

2. The energy storage device health management method according to claim 1, characterized in that: The method for obtaining the management data set includes: Preprocessing the original management data of the energy storage device to obtain initial management data, wherein the preprocessing includes data cleaning and noise filtering; Cyclic identification of the initial management data according to the direction of the current during the charge and discharge process of the energy storage device is performed to obtain different types of initial management data within the current cycle; the types include voltage, current and temperature; Time series alignment is performed on different types of initial management data in the current cycle based on a preset time interval to obtain a management data set of the energy storage device.

3. The energy storage device health management method according to claim 1, characterized in that: The multiple health feature vectors of the current cycle are fused to obtain a comprehensive health index, including: Normalizing the multiple health feature vectors to obtain multiple target health feature vectors; assigning weights to the multiple target health feature vectors based on the degree of influence of each of the multiple target health feature vectors on the health state of the energy storage device; A comprehensive health index is obtained by performing weighted fusion based on the multiple health feature vectors and their corresponding weights.

4. The energy storage device health management method according to claim 1, characterized in that: Determining the first health state of the energy storage device based on the comprehensive health index and the internal resistance of the energy storage device includes: Determining a first health state of the energy storage device based on the comprehensive health index and the internal resistance of the energy storage device and using a first formula; Among them, the first formula is: in, represents a first health state of the energy storage device, represents the initial internal resistance of the energy storage device, Indicates the current internal resistance of the energy storage device, Indicates the internal resistance of the energy storage device at the end of its life. Indicates the comprehensive health index of the current cycle, Indicates the current actual capacity of the energy storage device, Indicates the nominal capacity of the energy storage device.

5. The energy storage device health management method according to claim 1, characterized in that: Determining the second health state of the energy storage device based on the comprehensive health index and the historical comprehensive health index includes: Determining a second health state of the energy storage device based on the comprehensive health index and the historical comprehensive health index and using a second formula; Wherein, the second formula is: in, Indicates the second health state of the energy storage device, Indicates the comprehensive health index of the current cycle, Indicates the changing trend of the comprehensive health index from the mn cycle to the m cycle period, represents the historical comprehensive health index, represents the weight coefficient, Indicates the current actual capacity of the energy storage device, Indicates the nominal capacity of the energy storage device.

6. The energy storage device health management method according to claim 1, characterized in that: The fusing the first health state and the second health state to obtain a target health state of the energy storage device includes: Calculating basic weights corresponding to the first health state and the second health state based on the confidence levels of the first health state and the second health state; Calculating the operating condition matching factors of the first health state and the second health state based on the correlation between the current operating condition characteristics of the energy storage device and the first health state and the second health state, respectively; the operating condition characteristics represent the current operating conditions of the energy storage device; the correlation between the current operating condition characteristics of the energy storage device and the first health state is the degree of correlation between the current operating conditions of the energy storage device and the first health state, and the correlation between the current operating condition characteristics of the energy storage device and the second health state is the degree of correlation between the current operating conditions of the energy storage device and the second health state; Calculating average errors of the historical first health state and the historical second health state of the energy storage device, and normalizing them based on the average errors to obtain historical performance factors corresponding to the first health state and the second health state; fusing the basic weight, the operating condition matching factor, and the historical performance factor corresponding to the first health state to obtain a fused weight corresponding to the first health state, and fusing the basic weight, the operating condition matching factor, and the historical performance factor corresponding to the second health state to obtain a fused weight corresponding to the second health state; A target health state of the energy storage device is obtained by performing weighted fusion based on the first health state, the second health state, and their corresponding fusion weights.

7. The energy storage device health management method according to claim 1, characterized in that: Also includes: Obtaining a health decay cost for a next cycle and a current dynamic power envelope of the energy storage device based on the target health state and the plurality of health feature vectors; The health decay cost is the loss cost caused by aging of the energy storage device during each charge and discharge cycle; The dynamic power envelope is the maximum charge and discharge power boundary allowed by the current energy storage device in a healthy state; The charge and discharge powers corresponding to each future cycle of the energy storage device are predicted based on the health decay cost and the dynamic power envelope.

8. An energy storage equipment health management system, characterized in that: include: A feature extraction module is used to extract features from the management data set of the energy storage device to obtain multiple health feature vectors of the current cycle; The management data set is a standardized data set collected in a cyclic manner after preprocessing the original management data of the energy storage device; The cycle is a complete charge and discharge cycle completed by the energy storage device; the original management data is the data generated by the energy storage device during the charge and discharge process; A first fusion module is used to fuse the multiple health feature vectors of the current cycle to obtain a comprehensive health index; a second fusion module, configured to determine a first health state of the energy storage device based on the comprehensive health index and the internal resistance of the energy storage device, determine a second health state of the energy storage device based on the comprehensive health index and a historical comprehensive health index, and fuse the first health state and the second health state to obtain a target health state of the energy storage device; a risk calculation module, configured to calculate a risk index of the energy storage device based on the target health status; A management module is used to determine a management strategy for the energy storage device based on the risk index, and manage the energy storage device based on the management strategy.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images