Intelligent operation and maintenance management method and system for battery of energy storage power station

Abstract

The invention discloses an intelligent operation and maintenance management method for a battery of an energy storage power station, and the method comprises the following steps: S1, constructing a battery anomaly detection and immune response mechanism based on an AIS, determining an anomaly detection intensity index through the mechanism, and judging a preliminary battery state through the index; s2, when the battery anomaly detection and immune response mechanism triggers deep repair, constructing an SONN adaptive repair function, calculating to obtain a battery health state prediction value, and predicting the battery health state; an intelligent operation and maintenance management system for a battery of an energy storage power station comprises a data acquisition and monitoring module which acquires battery state data in real time and provides basic data support for a battery anomaly detection and immune response mechanism and an SON self-adaptive repair function. According to the method, a mild optimization strategy or a deep optimization strategy can be automatically selected, and an optimal repair scheme can be executed for different fault conditions, so that high-precision anomaly detection, accurate health prediction and intelligent operation and maintenance regulation and control are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of battery operation and maintenance management, and particularly to an intelligent operation and maintenance management method and system for energy storage power station batteries. Background Art

[0002] In recent years, with the large-scale application of renewable energy, energy storage power stations have become increasingly important in the power system. As the core of the energy storage system, the operating state of the battery directly affects the safety and efficiency of the entire power station. However, during long-term operation, the battery will be affected by factors such as charge and discharge cycles, temperature changes, and load fluctuations, resulting in performance degradation and an increased risk of failure. Therefore, establishing an intelligent battery operation and maintenance management method to improve the prediction and optimization ability of the battery health state has become a key issue in energy storage system management.

[0003] Currently, traditional battery operation and maintenance mainly rely on fixed threshold monitoring and regular maintenance, which cannot accurately identify abnormal states and take targeted repair measures in a timely manner, and it is difficult to dynamically optimize operation and maintenance strategies, resulting in low efficiency of battery management. Moreover, it may even affect the overall stability of the energy storage system due to failures not being discovered in time. Therefore, there is an urgent need to design an intelligent operation and maintenance management method and system for energy storage power station batteries to solve the above problems. Summary of the Invention

[0004] The purpose of this part is to outline some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Simplifications or omissions may be made in this part, as well as in the abstract and title of the present application, to avoid obscuring the purpose of this part, the abstract, and the title, but such simplifications or omissions shall not be used to limit the scope of the present invention.

[0005] In view of the problems existing in the above-mentioned existing intelligent operation and maintenance management method and system for energy storage power station batteries, the present invention is proposed.

[0006] Therefore, the purpose of the present invention is to provide an intelligent operation and maintenance management method and system for energy storage power station batteries, which are applicable to solving the problems of inability to accurately identify abnormal states, difficulty in dynamically optimizing operation and maintenance strategies, and resulting in low efficiency of battery management.

[0007] To solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, an embodiment of the present invention provides an intelligent operation and maintenance management method for energy storage power station batteries, including the following steps:

[0009] S1: Construct a battery anomaly detection and immune response mechanism based on AIS, confirm the anomaly detection intensity index through this mechanism, and judge the preliminary battery state through this index;

[0010] S2: When the battery anomaly detection and immune response mechanism triggers deep repair, construct the SONN adaptive repair function, calculate the predicted value of the battery health state, and predict the battery health status.

[0011] S3: Combine the anomaly detection intensity index and the predicted value of the battery health state to construct a battery intelligent operation and maintenance model, and execute the final battery repair strategy.

[0012] As a preferred solution of the battery intelligent operation and maintenance management method described in the present invention, the specific steps of the battery anomaly detection and immune response mechanism are as follows:

[0013] S101: Collect battery operation data, including voltage V i (t), current I j (t) and temperature T j , and calculate the mean value μ v of the battery voltage and the standard deviation σ v , record the battery temperature deviation ΔT j and set the temperature threshold T th ;

[0014] S102: Based on the battery operation data collected in S101, construct an AIS anomaly detection intensity formula to calculate the anomaly detection intensity index, and the AIS anomaly detection intensity formula is as follows;

[0015]

[0016] Where I det is the AIS anomaly detection intensity index, λ is the time decay factor to ensure that the weight of long-term data is low, is the square of the current of the jth group of batteries, α is the non-linear adjustment factor to control the influence of temperature on anomaly detection, and N and M respectively represent the sampling numbers of voltage and current;

[0017] S103: Output the preliminary judgment result of the battery operation state through the anomaly detection intensity index obtained in S102.

[0018] As a preferred solution of the battery intelligent operation and maintenance management method described in the present invention, in S103, set the first threshold I det，high and the second threshold I det，low according to the anomaly detection intensity index calculated by the AIS anomaly detection and repair formula;

[0019] If I det > I det，high , it indicates that the battery anomaly is serious;

[0020] If I det，low ≤ I det≤I det，high , it indicates that the battery has a slight abnormality;

[0021] If I det <I det，low , it indicates that the battery is in a normal state.

[0022] As a preferred solution of the intelligent operation and maintenance management method for the energy storage power station battery described in the present invention, wherein: the specific steps of constructing the SONN adaptive repair function are as follows:

[0023] S201: Collect key battery characteristic data, including battery capacity C, internal resistance R, temperature T, battery energy loss deviation ΔE j and health state change rate ΔSOH j ;

[0024] S202: When the battery abnormality is serious, construct the SONN adaptive repair function and calculate the predicted value H of the battery health state pred ;

[0025] The SONN adaptive repair function is as follows:

[0026]

[0027] Wherein,

[0028] F(C i ,R i ,T i ) is the battery health function, used to describe the relationship between temperature, capacity and internal resistance, and T opt is the optimal operating temperature;

[0029] S203: Divide the battery health state according to the calculation result of the predicted value of the battery health state, and set the third threshold H pred，high and the fourth threshold H pred，low ;

[0030] If H pred >H pred，high , it indicates that the battery health state is good;

[0031] If H pred，low ≤H pred ≤H pred，high , it indicates that the battery has a slight decline;

[0032] If H pred <H pred，low , it indicates that the battery health state has seriously declined.

[0033] As a preferred solution of the intelligent operation and maintenance management method for energy storage power station batteries described in the present invention, wherein: the specific construction steps of the battery intelligent operation and maintenance model are as follows:

[0034] S301: Identify whether the battery has abnormalities through the abnormal detection intensity index confirmed by the battery abnormal detection and immune response mechanism;

[0035] S302: Calculate the predicted value of the battery health state through the SON adaptive repair function to provide a decision-making basis for the intelligent operation and maintenance strategy;

[0036] S303: Construct the battery intelligent operation and maintenance model formula to calculate the intelligent operation and maintenance optimization index M opt , and the formula is as follows:

[0037]

[0038] where τ is the system calculation period, defining the time window of the intelligent operation and maintenance strategy, ξ and ζ are both time decay factors to ensure that newer data has a higher weight for system optimization, Λ is the collaborative optimization threshold, and ψ is the non-linear adjustment factor to control the influence of Λ on the final intelligent operation and maintenance index;

[0039] S304: Execute the final battery repair strategy according to the intelligent operation and maintenance optimization index M opt .

[0040] As a preferred solution of the intelligent operation and maintenance management method for energy storage power station batteries described in the present invention, wherein: in the S304, construct the safety threshold M opt，safe and the critical threshold M opt，crit according to the output result of the battery intelligent operation and maintenance model formula;

[0041] If M opt > M opt，safe , maintain the current operation and maintenance strategy, and only monitor the real-time temperature and charge-discharge state of the battery;

[0042] If M opt，crit < M opt ≤ M opt，safe , execute the mild optimization strategy, optimize the charge-discharge mode, reduce the high-rate charge-discharge behavior, adaptively adjust the maximum charge-discharge rate, control the energy release rate, reduce the internal impedance loss, and adopt the staged charging method to optimize the electrochemical reaction;

[0043] If M opt ≤ M opt，crit , it indicates that the battery health state has dropped sharply or the abnormal situation is serious, and execute the deep repair strategy.

[0044] As a preferred solution of the intelligent operation and maintenance management method for energy storage power station batteries described in the present invention, wherein: the deep repair strategy includes:

[0045] First: Restrict high-stress charge and discharge behaviors. If the intelligent operation and maintenance optimization index M opt shows an upward trend, then maintain the current strategy and monitor subsequent changes; otherwise, proceed to the next optimization.

[0046] Second: Through the intelligent pulse charging strategy, make the ion distribution in the polarization region uniform. If the intelligent operation and maintenance optimization index M opt shows a recovery trend within a certain period of time, then maintain this optimization strategy and monitor subsequent changes; otherwise, proceed to the next optimization.

[0047] Third: Adopt an intelligent bypass circuit to automatically shield the irreparable battery cells and make them exit the operation. Reconstruct the load distribution at the battery pack level and adjust the energy flow path. If the intelligent operation and maintenance optimization index M opt tends to rise steadily, then end the deep optimization and enter the long-term monitoring mode; otherwise, continue iterative optimization.

[0048] In the second aspect, an embodiment of the present invention provides an intelligent operation and maintenance management system for energy storage power station batteries. The operation and maintenance management system is applicable to any of the above operation and maintenance management methods. The operation and maintenance management system includes:

[0049] Data acquisition and monitoring module: Real-time collect battery status data to provide basic data support for the battery anomaly detection and immune response mechanism and the SON adaptive repair function;

[0050] Artificial immune system module: Confirm the anomaly detection intensity index and preliminarily judge the abnormal state of the battery;

[0051] Self-organizing neural network module: Obtain the predicted value of the battery health state and predict the battery health state;

[0052] Control execution module: Combine the anomaly detection intensity index and the predicted value of the battery health state to execute the final battery repair strategy;

[0053] Cloud intelligent operation and maintenance optimization subsystem: Store, analyze, and optimize the final battery repair strategy of the entire energy storage power station.

[0054] In the third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, it implements any step of the intelligent operation and maintenance management method for energy storage power station batteries described in the first aspect of the present invention.

[0055] Fourthly, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, any step of the energy storage power station battery intelligent operation and maintenance management method described in the first aspect of the present invention is realized.

[0056] Advantages of the present invention: The present invention introduces a battery anomaly detection and immune response mechanism for anomaly detection, quantifies the anomaly degree through an anomaly detection intensity index, and calculates a predicted value of the battery health state based on the SON adaptive repair function, which can accurately predict the health state of the battery and provide a scientific basis for the operation and maintenance strategy. Innovatively, the present invention combines the anomaly detection result and the health prediction result to construct a battery intelligent operation and maintenance model, and performs dynamic regulation through an intelligent operation and maintenance optimization index. This model can not only automatically select a mild optimization strategy or a deep optimization strategy, but also execute an optimal repair plan for different fault situations, realizing high-precision anomaly detection, accurate health prediction, and intelligent operation and maintenance regulation. It can be widely applied to scenarios such as large-scale energy storage power stations, distributed energy storage systems, and energy storage management of new energy power grids, and has important engineering application value and economic value. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. Among them:

[0058] Figure 1 It is a schematic diagram of the overall process of an energy storage power station battery intelligent operation and maintenance management method proposed by the present invention;

[0059] Figure 2 It is a schematic diagram of the deep optimization strategy process of an energy storage power station battery intelligent operation and maintenance management method proposed by the present invention;

[0060] Figure 3 It is a schematic diagram of the overall framework structure of an energy storage power station battery intelligent operation and maintenance management system proposed by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0061] In order to make the above objects, features, and advantages of the present invention more obvious and understandable, the following will provide a detailed description of the specific embodiments of the present invention with reference to the accompanying drawings of the specification.

[0062] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, the present invention may be practiced in other ways than those specifically described herein, and those skilled in the art can make similar extensions without departing from the spirit of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0063] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation manner of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that mutually excludes other embodiments.

[0064] Thirdly, the present invention is described in detail in conjunction with schematic diagrams. When detailing the embodiments of the present invention, for the sake of convenience of explanation, the cross-sectional views showing the device structure will be enlarged locally in a non-general proportion, and the schematic diagrams are only examples and should not limit the scope of protection of the present invention herein. In addition, in actual production, three-dimensional spatial dimensions including length, width, and depth should be included.

[0065] Embodiment 1

[0066] Referring to Figures 1 - 3 , for an embodiment of the present invention, a method for intelligent operation and maintenance management of energy storage power station batteries is provided, including the following steps:

[0067] S1: Construct a battery anomaly detection and immune response mechanism based on AIS, confirm the anomaly detection intensity index through this mechanism, and judge the preliminary battery state through this index;

[0068] Traditional methods for detecting battery anomalies in energy storage power stations mostly rely on fixed thresholds or statistical regression analysis, which cannot adapt to complex battery operating conditions and are prone to misjudgment. The present invention first introduces the AIS theory, detects battery anomalies through a bionic immune response mechanism, quantifies the anomaly detection intensity, improves the accuracy of anomaly detection, reduces false alarms and missed reports, and can be widely used in large-scale energy storage power stations, distributed energy storage systems, and energy storage management of new energy power grids;

[0069] The specific steps of the battery anomaly detection and immune response mechanism are as follows:

[0070] S101: Collect battery operation data, including voltage V i (t), current I j (t), and temperature T j , and calculate the mean value μ v of the battery voltage and the standard deviation σ v , record the battery temperature deviation ΔT j and set the temperature threshold T th ;

[0071] ΔT j = T j - T th

[0072] S102: Based on the battery operation data collected in S101, construct the AIS anomaly detection intensity formula to calculate the anomaly detection intensity index, and the AIS anomaly detection intensity formula is as follows;

[0073]

[0074] Among them, I det is the AIS anomaly detection intensity index, λ is the time decay factor to ensure that the weight of long-term data is lower, is the square of the current of the jth group of batteries, α is the non-linear adjustment factor to control the influence of temperature on anomaly detection, and N and M respectively represent the sampling quantities of voltage and current;

[0075] S103: Output the preliminary judgment result of the battery operation state through the anomaly detection intensity index obtained in S102.

[0076] In S103, set the first threshold I det，high and the second threshold I det，low ;

[0077] If I det > I det，high , it indicates that the battery anomaly is serious;

[0078] If I det，low ≤ I det ≤ I det，high , it indicates that the battery has a minor anomaly;

[0079] If I det < I det，low , it indicates that the battery state is normal.

[0080] S2: When the battery anomaly detection and immune response mechanism triggers deep repair, then construct the SONN adaptive repair function, calculate the predicted value of the battery health state, and predict the battery health condition;

[0081] The present invention innovatively constructs the SONN adaptive repair function, enabling the prediction process to have non-linear adaptive capabilities. The SONN adaptive repair function can adjust the health prediction parameters in real time, is not only applicable to long-term trend prediction, but can also quickly respond to sudden anomalies, improve the prediction accuracy, and is applicable to various energy storage batteries such as lithium batteries, sodium-sulfur batteries, and flow batteries;

[0082] The specific steps for constructing the SONN adaptive repair function are as follows:

[0083] S201: Collect key battery feature data, including battery capacity C, internal resistance R, temperature T, battery energy loss deviation ΔE j and the rate of change of the state of health ΔSOH j ;

[0084] Normalize the data and calculate the standardized features using the Z - transform:

[0085]

[0086] where μ X and σ X are the feature mean and standard deviation respectively, and the normalized battery state data matrix X norm is used as the input to the SONN adaptive repair function;

[0087] S202: When the battery anomaly is severe, construct the SONN adaptive repair function, set the adaptive connection weight matrix W between neurons, and update the weights using the competitive learning mechanism:

[0088]

[0089] where η is the learning rate.

[0090] Calculate the predicted value H of the battery state of health pred , and the SONN adaptive repair function is as follows:

[0091]

[0092] where,

[0093] F(C i ,R i ,T i ) is the battery health function, which is used to describe the relationship between temperature, capacity and internal resistance, and T opt is the optimal operating temperature;

[0094] S203: According to the calculation result of the predicted value of the battery state of health, divide the battery state of health, and set the third threshold H pred，high and the fourth threshold H pred，low ;

[0095] If H pred > H pred，high , it means that the battery state of health is good;

[0096] If H pred，low ≤H pred ≤H pred，high , it means that the battery has a slight decline;

[0097] If Hpred <H pred，low , it indicates that the battery health state has seriously declined.

[0098] S3: Combine the abnormal detection intensity index and the predicted value of the battery health state to construct a battery intelligent operation and maintenance model, and execute the final battery repair strategy;

[0099] Different from the traditional passive maintenance mode (such as maintenance based on a fixed cycle or triggered by an alarm signal), the present invention constructs an intelligent operation and maintenance optimization model. Taking the intelligent operation and maintenance optimization index as the decision-making basis, it realizes dynamic optimization and regulation, can intelligently judge the battery state, automatically select the optimal repair plan, effectively reduce the operation and maintenance cost, is applicable to large-scale energy storage power stations, battery management in data centers, and industrial energy storage systems, and can greatly reduce manual intervention.

[0100] The specific construction steps of the battery intelligent operation and maintenance model are as follows:

[0101] S301: Identify whether there is an abnormality in the battery through the abnormal detection intensity index confirmed by the battery abnormal detection and immune response mechanism;

[0102] S302: Calculate the predicted value of the battery health state through the SON adaptive repair function, providing a decision-making basis for the intelligent operation and maintenance strategy;

[0103] S303: Construct the battery intelligent operation and maintenance model formula to calculate the intelligent operation and maintenance optimization index M opt , and the formula is as follows:

[0104]

[0105] Among them, τ is the system calculation period, defining the time window of the intelligent operation and maintenance strategy. Both ξ and ζ are time decay factors, ensuring that newer data has a higher weight for system optimization. Λ is the collaborative optimization threshold, and ψ is a non-linear adjustment factor, controlling the influence of Λ on the final intelligent operation and maintenance index;

[0106] S304: Execute the final battery repair strategy according to the intelligent operation and maintenance optimization index M opt .

[0107] In S304, construct a safety threshold M opt，safe and a critical threshold M opt，crit according to the output result of the battery intelligent operation and maintenance model formula;

[0108] If M opt > M opt，safe , maintain the current operation and maintenance strategy, and only monitor the real-time temperature and charge-discharge state of the battery;

[0109] If M opt，crit < M opt ≤Mopt，safe Implement a mild optimization strategy to optimize the charge and discharge mode, reduce high-rate charge and discharge behavior, adaptively adjust the maximum charge and discharge rate, control the energy release rate, reduce internal impedance loss, and adopt a staged charging method to optimize the electrochemical reaction;

[0110] If M opt ≤M opt，crit it indicates that the battery health state has deteriorated sharply or there is a serious abnormal situation, and a deep repair strategy is executed.

[0111] The deep repair strategy includes:

[0112] One: Restrict high-stress charge and discharge behavior. If the intelligent operation and maintenance optimization index M opt shows an upward trend, maintain the current strategy and monitor subsequent changes, otherwise proceed to the next optimization;

[0113] Two: Through the intelligent pulse charging strategy, make the ion distribution in the polarization region uniform. If the intelligent operation and maintenance optimization index M opt shows a recovery trend within a period of time, maintain this optimization strategy and monitor subsequent changes, otherwise proceed to the next optimization;

[0114] Three: Adopt an intelligent bypass circuit to automatically shield the irreparable battery cells, so that they are taken out of operation, reconstruct the load distribution at the battery pack level, adjust the energy flow path. If the intelligent operation and maintenance optimization index M opt tends to rise steadily, end the deep optimization and enter the long-term monitoring mode, otherwise continue iterative optimization.

[0115] An intelligent operation and maintenance management system for energy storage power station batteries. The operation and maintenance management system is applicable to any of the above operation and maintenance management methods. The operation and maintenance management system includes:

[0116] Data acquisition and monitoring module: Real-time collect battery status data to provide basic data support for the battery anomaly detection and immune response mechanism and the SON adaptive repair function;

[0117] Artificial immune system module: Confirm the anomaly detection intensity index and initially judge the abnormal state of the battery;

[0118] Self-organizing neural network module: Obtain the predicted value of the battery health state and predict the battery health state;

[0119] Control execution module: Combine the anomaly detection intensity index and the predicted value of the battery health state to execute the final battery repair strategy;

[0120] Cloud intelligent operation and maintenance optimization subsystem: Store, analyze and optimize the final battery repair strategy of the entire energy storage power station.

[0121] During use, the present invention introduces a battery anomaly detection and immune response mechanism for anomaly detection, quantifies the degree of anomaly through an anomaly detection intensity index, and based on the SON adaptive repair function, calculates the predicted value of the battery health state, enabling accurate prediction of the battery health state, providing a scientific basis for the operation and maintenance strategy. Innovatively combining the anomaly detection results and the health prediction results, it constructs a battery intelligent operation and maintenance model and dynamically adjusts it through the intelligent operation and maintenance optimization index. This model can not only automatically select mild optimization strategies or deep optimization strategies, but also execute the optimal repair plan for different fault situations, achieving high-precision anomaly detection, accurate health prediction, and intelligent operation and maintenance regulation.

[0122] Embodiment 2

[0123] Referring to Tables 1 - 3, this is the second embodiment of the present invention. The difference between this embodiment and the first embodiment is that, in order to verify its beneficial effects, experimental comparison data between the present invention and the prior art are provided.

[0124] In order to verify the effectiveness of the intelligent operation and maintenance management method for energy storage power station batteries of the present invention, 100 lithium battery monomers of a certain energy storage power station are selected as test objects in this experiment, and a comparative experiment is conducted. The traditional battery management method (monitoring based on a fixed threshold) is used as the control group, while the method of the present invention is used as the experimental group.

[0125] Collect key parameters of the battery such as voltage, current, temperature, SOC (state of charge), SOH (health state), record the initial state, calculate the anomaly detection intensity index using the AIS anomaly detection intensity formula, judge the battery anomaly state, calculate the predicted value of the battery health state using the SONN adaptive repair function, and predict the degradation trend of the battery;

[0126] During the experiment, the two groups of batteries are monitored for 24 hours, and the recognition rate of anomalies is calculated using the AIS anomaly detection intensity formula, and the accuracy rate, false alarm rate, and missed alarm rate of anomaly detection are recorded;

[0127] Calculate the health prediction value using the SONN adaptive repair function, compare it with the actual data, evaluate the prediction error, and calculate the mean square error (MSE) to evaluate the accuracy of health prediction;

[0128] Combining the anomaly detection intensity index and the health prediction value, adjust the optimization strategy using the battery intelligent operation and maintenance model, monitor the battery maintenance cost, available capacity, and failure rate, and compare with the traditional method to evaluate the operation and maintenance optimization effect.

[0129] Table 1: Comparison table of anomaly detection intensity

[0130]

[0131] Table 2: Comparison Table of Health Status Prediction Accuracy

[0132] Prediction period (days) MSE of traditional method MSE of the present invention Error reduction rate (%) 10 0.031 0.018 41.9 20 0.043 0.022 48.8 30 0.057 0.029 49.1 40 0.072 0.034 52.8

[0133] Table 3: Comparison Table of Operation and Maintenance Optimization Effects

[0134]

[0135] Based on the data in the above Tables 1 to 3, the analysis is specifically carried out from the following three aspects:

[0136] Abnormal detection accuracy: As can be seen from Table 1, when the monitoring duration is 24 hours, the battery abnormal detection and immune response mechanism of the present invention increases the abnormal detection rate from 78.5% to 94.3%, significantly reducing false alarms and missed detections, improving the accuracy of abnormal identification, and enabling earlier abnormalities of the battery to be detected more quickly;

[0137] Health status prediction: As can be seen from Table 2, when the prediction period is one month, the SONN adaptive repair function of the present invention reduces the average health prediction error (MSE) by 49.1%. This indicates that the present invention can more accurately predict the aging of the battery and provides more reliable data support for preventive maintenance;

[0138] In terms of operation and maintenance optimization effects: As can be seen from Table 3, when the running time is 120 days, the battery intelligent operation and maintenance model of the present invention reduces the maintenance cost by 35.0%, while the available capacity of the battery increases by 20.4% and the failure rate decreases by 25.1%. This result shows that the present invention not only reduces the operation and maintenance cost, but also significantly improves the reliability and service life of the battery.

[0139] In summary, through the experimental comparison of AIS abnormal detection, SONN health prediction, and intelligent operation and maintenance optimization in this embodiment, it is proved that the present invention has a significant improvement compared with traditional methods in terms of accuracy, prediction ability, and operation and maintenance optimization. The intelligent operation and maintenance method of the present invention can effectively improve the operation efficiency of energy storage batteries, reduce maintenance costs, and extend the battery life, with strong innovation and practical value.

[0140] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. An intelligent operation and maintenance management method for batteries in energy storage power stations, characterized in that: The following steps are involved: S1: Build an AIS-based battery anomaly detection and immune response mechanism, confirm the anomaly detection strength index through this mechanism, and judge the preliminary battery status through this index; S2: When the battery abnormality detection and immune response mechanism triggers deep repair, the SONN adaptive repair function is constructed to calculate the battery health status prediction value and predict the battery health status; S3: Build a battery intelligent operation and maintenance model based on the anomaly detection strength index and the battery health status prediction value, and execute the final battery repair strategy.

2. According to claim 1, a method for intelligent operation and maintenance management of batteries in an energy storage power station is characterized in that: The specific steps of the battery abnormality detection and immune response mechanism are as follows: S101: Collect battery operation data, including voltage V i (t), current I j (t) and temperature T j , and calculate the mean value μ of the battery voltage v and standard deviation σ v , record the battery temperature deviation ΔT j And set the temperature threshold T th ; S102: Based on the battery operation data collected in S101, an AIS abnormality detection strength formula is constructed to calculate an abnormality detection strength index, and the AIS abnormality detection strength formula is as follows; Among them, I det is the AIS anomaly detection strength indicator, λ is the time decay factor, ensuring that the weight of long-term data is low. is the square of the current of the jth battery group, α is a nonlinear adjustment factor that controls the effect of temperature on abnormality detection, N and M represent the number of samples of voltage and current, respectively; S103: A preliminary judgment result of the battery operation status is made based on the abnormal detection strength index output obtained in S102.

3. The intelligent operation and maintenance management method of an energy storage power station battery according to claim 2 is characterized in that: In S103, a first threshold I is set according to the anomaly detection strength index calculated by the AIS anomaly detection and repair formula. det，high and the second threshold I det，low ; If I det >I det，high , it indicates that the battery is seriously abnormal; If I det，low ≤I det ≤I det，high , it indicates that the battery has a slight abnormality; If I det <I det，low , it indicates that the battery status is normal.

4. The intelligent operation and maintenance management method of an energy storage power station battery according to claim 1, characterized in that: The specific steps of constructing the SONN adaptive repair function are as follows: S201: Collect key battery characteristic data, including battery capacity C, internal resistance R, temperature T, and battery energy loss deviation ΔE j and health status change rate ΔSOH j ; S202: When the battery is seriously abnormal, a SONN adaptive repair function is constructed to calculate the battery health status prediction value H pred ; The SONN adaptive repair function is as follows: in, F(C i ,R i ,T i ) is the battery health function, which is used to describe the relationship between temperature, capacity and internal resistance. opt is the best working temperature; S203: According to the calculation result of the battery health state prediction value, the battery health state is divided, and the third threshold H is set according to the output result of the SONN adaptive repair function pred，high and the fourth threshold H pred，low ; If H pred >H pred，high , it means the battery is in good health; If H pred，low ≤H pred ≤H pred，high , it means the battery is slightly degraded; If H pred <H pred，low , it means that the battery health status has seriously declined.

5. The intelligent operation and maintenance management method of an energy storage power station battery according to claim 4 is characterized in that: The specific construction steps of the battery intelligent operation and maintenance model are as follows: S301: Identify whether the battery is abnormal through the abnormality detection strength index confirmed by the battery abnormality detection and immune response mechanism; S302: Calculate the battery health status prediction value through the SON adaptive repair function to provide a decision basis for the intelligent operation and maintenance strategy; S303: Construct the battery intelligent operation and maintenance model formula and calculate the intelligent operation and maintenance optimization index M opt , the formula is as follows: Among them, τ is the system calculation cycle, which defines the time window of the intelligent operation and maintenance strategy. ξ and ζ are both time decay factors, which ensure that the newer data has a higher weight for system optimization. Λ is the collaborative optimization threshold, and ψ is the nonlinear adjustment factor, which controls the impact of Λ on the final intelligent operation and maintenance index. S304: According to the intelligent operation and maintenance optimization index M opt , execute the final battery repair strategy.

6. The intelligent operation and maintenance management method of an energy storage power station battery according to claim 5, characterized in that: In S304, a safety threshold M is constructed according to the output result of the battery intelligent operation and maintenance model formula. opt，safe and critical threshold M opt，crit ; If M opt >M opt，safe , maintain the current operation and maintenance strategy, and only monitor the real-time temperature and charge and discharge status of the battery; If M opt，crit <M opt ≤M opt，safe , implement mild optimization strategy, optimize charging and discharging mode, reduce high-rate charging and discharging behavior, adaptively adjust the maximum charging and discharging rate, control the energy release rate, reduce internal impedance loss, and adopt staged charging method to optimize electrochemical reaction; If M opt ≤M opt，crit , it indicates that the battery health status has dropped sharply or the abnormality is serious, and a deep repair strategy is executed.

7. The intelligent operation and maintenance management method of an energy storage power station battery according to claim 6 is characterized by: The deep repair strategy includes: 1: Limit high stress charging and discharging behavior. If the intelligent operation and maintenance optimization index M opt If there is an upward trend, maintain the current strategy and monitor subsequent changes, otherwise proceed to the next step of optimization; Second: Through the intelligent pulse charging strategy, the ions in the polarization area are evenly distributed. If the intelligent operation and maintenance optimization index M opt If a recovery trend is shown over a period of time, the optimization strategy is maintained and subsequent changes are monitored; otherwise, the next step of optimization is entered; 3. Adopt intelligent bypass circuit to automatically shield the irreparable battery cells and make them out of operation, reconstruct the load distribution at the battery pack level, adjust the energy flow path, and if the intelligent operation and maintenance optimization index M opt If it tends to rise steadily, end the deep optimization and enter the long-term monitoring mode, otherwise continue the iterative optimization.

8. An intelligent operation and maintenance management system for batteries in energy storage power stations, the operation and maintenance management system being applicable to any one of the operation and maintenance management methods in claims 1-7 above, characterized in that: The operation and maintenance management system includes: Data collection and monitoring module: collects battery status data in real time to provide basic data support for battery anomaly detection and immune response mechanism and SON adaptive repair function; Artificial immune system module: confirms the abnormal detection strength index and preliminarily determines the abnormal state of the battery; Self-organizing neural network module: obtains the battery health status prediction value and predicts the battery health status; Control execution module: combines the abnormal detection strength index and the battery health status prediction value to execute the final battery repair strategy; Cloud-based intelligent operation and maintenance optimization subsystem: stores, analyzes and optimizes the final battery repair strategy of the entire energy storage power station.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the intelligent operation and maintenance management method of the energy storage power station battery according to any one of claims 1-7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent operation and maintenance management method of the energy storage power station battery according to any one of claims 1 to 7 are implemented.

Images