Intelligent energy storage battery performance monitoring management system and method

Abstract

The invention discloses an intelligent energy storage battery performance monitoring management system and method, and relates to the technical field of energy storage battery performance supervision, and the system comprises a capacity attenuation analysis module, an adjustment strategy decision module, and an adjustment strategy constraint module. The capacity attenuation analysis module is used for testing and obtaining attenuation data of the capacity of each battery unit along with time, training a capacity attenuation neural network model and calculating relative capacity of each battery unit after attenuation; the adjustment strategy decision module is used for selecting a reference battery unit, screening adjustable state parameters of each battery unit to establish an adjustment constraint set, constructing an adjustment strategy equation according to the capacity of each battery unit, and determining an adjustment strategy of each battery unit; and the adjustment strategy constraint module divides and limits the adjustment time of the adjustment strategy of each battery unit through capacity consistency judgment and capacity deviation threshold judgment, and divides an adjustment time slice according to a limiting result.

Description

Technical Field

[0001] The present invention relates to the technical field of energy storage battery performance supervision, and in particular to an intelligent energy storage battery performance monitoring and management system and method. Background Art

[0002] With the widespread popularization and application of new energy and energy storage battery technologies, the flexibility and fault tolerance of distributed batteries make them a better choice in complex energy supply scenarios; However, due to the individual differences and usage conditions of battery cells in distributed batteries, their respective capacities will gradually lose consistency over time, leading to safety risks in battery use and limiting the overall performance of the battery. The current passive balancing, active balancing, and BMS management methods have the following technical defects. On the one hand, active balancing and passive balancing technologies aim to balance the power between battery cells by releasing or transferring the power in each battery cell. In actual use, there is a high energy waste and low system energy utilization efficiency. On the other hand, the traditional BMS monitors the group status parameters of the battery pack and limits charging and discharging to avoid overcharging and over-discharging. It lacks initiative and flexibility and cannot actively correct the consistency deviation between battery cells. Therefore, an intelligent energy storage battery performance monitoring and management system and method are needed to solve the above technical defects. Summary of the invention

[0003] The purpose of the present invention is to provide an intelligent energy storage battery performance monitoring management system and method to solve the problems raised in the prior art.

[0004] To achieve the above object, the present invention provides the following technical solutions: An intelligent energy storage battery performance monitoring and management method, the method comprising the following analysis steps: Step S100: Analyze and mark the influencing parameters of the capacity decay of each battery unit in the distributed battery pack, test and obtain the capacity decay data of each battery unit over time under different environmental parameters and state parameters, construct a capacity decay data set, and train a capacity decay neural network model; Step S200: measuring the capacity of each battery unit in the distributed battery pack, and calculating the relative capacity of each battery unit according to the factory rated capacity data; Step S300: monitoring the environmental parameters and state parameters of each battery cell in real time, and using the capacity decay neural network model to calculate the relative capacity of each battery cell after decay at each time point; Step S400: Select a reference battery cell, screen the adjustable state parameters of each battery cell to establish an adjustment constraint set, construct an adjustment strategy equation according to the relative capacity of each battery cell, and determine the adjustment strategy of each battery cell; Step S500: performing capacity consistency judgment and capacity deviation threshold judgment on each battery unit, and dividing the adjustment strategy into adjustment time slices according to the judgment results.

[0005] In the above technical solution, the step S100 is divided into the following steps: Step S101: Analyze and mark the capacity attenuation influencing parameters of each battery unit in the distributed battery group; The influencing parameters include environmental parameters and state parameters, wherein the environmental parameters refer to environmental factors that affect the capacity decay in the environment where the battery cell is located, and the state parameters refer to electrical parameters that affect the capacity decay of the battery cell; Step S102: testing and obtaining the data of capacity decay over time of each battery unit, and recording the environmental parameters and state parameters corresponding to each data, to construct a capacity decay data set; Step S103: Use the capacity decay data set to train a capacity decay neural network model, and record the capacity decay neural network model of battery cell n as: ; in, is the predicted value of capacity attenuation of battery cell n, is the environmental parameter set input item of the battery cell n capacity decay neural network model, is the state parameter set input item of the battery cell n capacity decay neural network model, The capacity decay time of the capacity decay neural network model of battery cell n is obtained. By analyzing and building a capacity decay neural network model for each battery cell, the capacity decay of each battery cell can be accurately predicted, providing a scientific data analysis basis for subsequent consistency adjustment strategy decisions.

[0006] In the above technical solution, step S200 includes the following contents: Use the Coulomb integration method to measure the current maximum charge of each battery cell, and according to the formula: , calculate the remaining capacity of each battery unit at the current time point; in, is the relative capacity remaining in the battery cell at the measurement time point, It is the maximum charge measurement data of the battery unit. This is the maximum charge rating of the battery unit when it leaves the factory.

[0007] In the above technical solution, step S300 includes the following contents: Real-time monitoring of the environmental parameters and state parameters of each battery cell. For any battery cell n, the capacity decay neural network model of battery cell n is used to analyze the relative capacity of battery cell n after decay. , according to the formula: ; in, is the relative capacity remaining in battery cell n at the measurement time point, is the time point at which the capacity of battery cell n is measured, is the current analysis time point, The capacity attenuation prediction value of battery cell n is differentiated with respect to time t; The remaining relative capacity of each battery cell at each time point is calculated by combining discharge test and time integration, which ensures data accuracy while avoiding redundant attenuation of battery cell capacity caused by frequent discharge tests, thereby improving the use efficiency of each battery cell.

[0008] In the above technical solution, the step S400 is divided into the following steps: Step S401: Calculate and analyze the relative capacity of each battery cell at the adjustment strategy analysis time point, and determine a reference battery cell; The capacity decay neural network model of each battery cell is used to analyze the relative capacity of each battery cell after decay at the adjustment strategy analysis time point, and the battery cell with the smallest relative capacity is selected as the reference battery cell; Step S402: Screening the adjustable state parameters of each battery cell to establish an adjustment constraint set; Analyze the usage mode of each battery cell, select the state parameters that can be adjusted from each battery cell as adjustment parameters, and establish an adjustment constraint set for each adjustment parameter to limit the adjustment range of each adjustment parameter; the adjustment constraint set refers to a set of all constraints that limit the adjustment range of the battery cell state parameters; Step S403: constructing a regulation strategy equation according to the relative capacity of each battery unit, and determining the regulation strategy of each battery unit; For any battery cell n, the regulation strategy analysis method is as follows: Obtaining an adjustment constraint set for each battery cell, calculating a derivative of the capacity decay neural network model with respect to decay time, and then calculating a decay rate of the battery cell when each adjustment parameter is combined within an adjustment range; According to the relative capacity of each battery unit, the regulation strategy equation is constructed: ; in, is the decay rate of battery cell n, is the decay rate of the reference battery cell, is a constant parameter, is the relative capacity of battery cell n, For reference battery cell relative capacity, is the battery cell number, is the number of battery cells, For battery cells The power provided, The power demand of distributed battery packs; Solve the equation group and analyze to obtain the adjustment parameter combination that meets the power demand of the distributed battery group and has the minimum attenuation rate of the reference battery cell as the adjustment target of the reference battery cell, and calculate and analyze the adjustment parameter combination of the remaining other battery cells according to the minimum attenuation rate of the reference battery cell as the adjustment target of each battery cell; An adjustment strategy equation is constructed based on the relative capacity of each battery cell to ensure that the attenuation degrees of battery cells with large relative capacity deviations tend to be consistent, thereby improving the capacity consistency between each battery cell. A constant parameter is also introduced to mitigate the attenuation rate of each battery cell in the adjustment strategy, thereby improving the use efficiency of each battery cell and avoiding an increase in the attenuation rate of each battery cell caused by excessively fast adjustment speed, while also reducing the system computing pressure. In addition, when constructing the adjustment strategy equation, a comprehensive consideration of the energy output power of each battery cell is added to ensure the reliability of energy supply while adjusting the consistency of the battery cells.

[0009] In the above technical solution, step S500 includes the following contents: Setting the battery cell capacity deviation threshold , and judge the capacity deviation of each battery unit, and adjust the time slice division according to the judgment result; Obtain the remaining relative capacity of each battery cell at the initial analysis time point, and simultaneously perform capacity consistency judgment and capacity deviation threshold judgment; The capacity consistency judgment refers to the case where the capacity of any battery cell n and the reference battery cell satisfy , and reaches after adjusting the time point , then the current adjustment strategy is determined to be completed and will reach The time point is recorded as the end point of the current adjustment strategy; is the reference battery cell capacity; The capacity deviation threshold judgment means that if the capacity between any battery cells a and b satisfies , then it is determined that the current adjustment strategy causes a large deviation in capacity consistency, and the current adjustment strategy is terminated and the The time point is recorded as the end point of the current adjustment strategy; are the relative capacities of battery cells a and b after attenuation; The above-mentioned capacity consistency judgment and capacity deviation threshold judgment are performed simultaneously, and the time end point of the adjustment strategy recorded for the first time is taken as the end point of the current adjustment time slice, and the battery unit adjustment strategy analysis of the next adjustment time slice is performed.

[0010] An intelligent energy storage battery performance monitoring and management system using an intelligent energy storage battery performance monitoring and management method in the above technical solution, the system comprising: a capacity decay analysis module, an adjustment strategy decision module, and an adjustment strategy constraint module; The capacity decay analysis module tests and obtains the data of the capacity decay of each battery cell over time, trains the capacity decay neural network model, and is also used to calculate the relative capacity of each battery cell after decay; the adjustment strategy decision module is used to select a reference battery cell, screen the adjustable state parameters of each battery cell to establish an adjustment constraint set, construct an adjustment strategy equation according to the capacity of each battery cell, and determine the adjustment strategy of each battery cell; the adjustment strategy constraint module divides and limits the adjustment time of each battery cell adjustment strategy through capacity consistency judgment and capacity deviation threshold judgment, and divides the adjustment time slice according to the limitation result.

[0011] In the above technical solution, the capacity decay analysis module includes: a capacity measurement unit, an influencing parameter analysis unit, a model building unit, and a capacity decay calculation unit; The capacity measurement unit is used to measure the battery capacity of each battery cell in the distributed battery pack at the measurement time point and calculate the relative capacity of each battery cell; the influencing parameter analysis unit is used to analyze and mark the influencing parameters of the capacity attenuation of each battery cell in the distributed battery pack; the model construction unit constructs a capacity attenuation data set and trains a capacity attenuation neural network model based on the capacity attenuation data of each battery cell under different environmental parameters and state parameters over time; the capacity attenuation calculation unit predicts the battery capacity attenuation of each battery cell from the measurement time point to the analysis time point based on the battery capacity of each battery cell at the measurement time point, and uses the capacity attenuation neural network model to calculate the relative capacity of each battery cell after attenuation at each time point.

[0012] In the above technical solution, the adjustment strategy decision module includes: a reference selection unit, an adjustment constraint construction unit, and an adjustment strategy analysis unit; The reference selection unit determines the reference battery cell according to the relative capacity of each battery cell at the adjustment strategy analysis time point; the adjustment constraint construction unit is used to screen the adjustable state parameters of each battery cell to establish an adjustment constraint set; the adjustment strategy analysis unit constructs an adjustment strategy equation according to the relative capacity of each battery cell and determines the adjustment strategy of each battery cell.

[0013] In the above technical solution, the adjustment strategy constraint module includes: a capacity consistency judgment unit, a capacity deviation threshold judgment unit, and an adjustment time slice division unit; The capacity consistency judgment unit monitors the capacity of each battery cell in real time and performs consistency judgment; the capacity deviation threshold judgment unit monitors the capacity of each battery cell in real time and performs capacity deviation threshold judgment; the adjustment time slice division unit determines the termination time of each adjustment strategy according to the results of capacity consistency judgment and capacity deviation threshold judgment, and then divides the adjustment time slice.

[0014] Compared with the prior art, the present invention has the following beneficial effects: In the present invention, the capacity of each battery cell in the distributed battery pack is analyzed to determine the adjustment strategy of each battery cell, so as to reduce the capacity deviation between each battery cell and improve the consistency between each battery cell. Compared with the prior art, it is more specific, proactive and flexible. The use of battery state parameter adjustment also avoids the problems of low system efficiency and high energy loss rate in the simple energy transfer and conversion method. Secondly, the present invention constructs a physical model of capacity decay of each battery cell in a data-driven manner, analyzes the implicit relationship between each influencing parameter, and then predicts the remaining relative capacity of each battery cell at each time point, avoiding the redundant capacity decay caused by frequent charge and discharge tests. In addition, the present invention adjusts the state parameters when the battery is in use to balance the consistency between each battery cell. At the same time, when constructing the adjustment strategy equation, a constant is introduced to mitigate the decay rate between battery cells, prolonging the single adjustment strategy time, avoiding frequent adjustments that cause the battery cells to decay too quickly, and also avoiding the overall volatility of the distributed battery pack caused by frequent adjustments. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flow chart of an intelligent energy storage battery performance monitoring and management method of the present invention; Figure 2 This is an organizational structure diagram of an intelligent energy storage battery performance monitoring and management system of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Example: See Figure 1-Figure 2 , the present invention provides the following technical solutions: like Figure 1 As shown, the present invention provides an intelligent energy storage battery performance monitoring and management method, the method comprising the following analysis steps: Step S100: Analyze and mark the influencing parameters of the capacity decay of each battery unit in the distributed battery pack, test and obtain the capacity decay data of each battery unit over time under different environmental parameters and state parameters, construct a capacity decay data set, and train a capacity decay neural network model; Step S200: measuring the capacity of each battery unit in the distributed battery pack, and calculating the relative capacity of each battery unit according to the factory rated capacity data; Step S300: monitoring the environmental parameters and state parameters of each battery cell in real time, and using the capacity decay neural network model to calculate the relative capacity of each battery cell after decay at each time point; Step S400: Select a reference battery cell, screen the adjustable state parameters of each battery cell to establish an adjustment constraint set, construct an adjustment strategy equation according to the relative capacity of each battery cell, and determine the adjustment strategy of each battery cell; Step S500: performing capacity consistency judgment and capacity deviation threshold judgment on each battery unit, and dividing the adjustment strategy into adjustment time slices according to the judgment results.

[0018] The step S100 is divided into the following steps: Step S101: Analyze and mark the capacity attenuation influencing parameters of each battery unit in the distributed battery group; The influencing parameters include environmental parameters and state parameters, wherein the environmental parameters refer to environmental factors that affect the capacity decay in the environment where the battery cell is located, and the state parameters refer to electrical parameters that affect the capacity decay of the battery cell; In specific implementation, parameters such as ambient temperature and ambient humidity are generally used as environmental parameters for analysis, and parameters such as battery state of charge, charge and discharge rate, and battery internal resistance are used as state parameters for analysis; Step S102: testing and obtaining the data of capacity decay over time of each battery unit, and recording the environmental parameters and state parameters corresponding to each data, to construct a capacity decay data set; Step S103: Use the capacity decay data set to train a capacity decay neural network model, and record the capacity decay neural network model of battery cell n as: ; in, is the predicted value of capacity attenuation of battery cell n, is the environmental parameter set input item of the battery cell n capacity decay neural network model, is the state parameter set input item of the battery cell n capacity decay neural network model, is the capacity decay time of the capacity decay neural network model of battery cell n; In specific implementation, the battery cells in the actual battery pack may have model and individual differences. Therefore, when training the capacity decay neural network model, the model training can be carried out according to the decay data of the battery cells of the same model in the production line. However, since the parameters that affect the capacity decay of the battery cells are of high dimension, a data-driven training method is adopted to avoid the mathematical structure of the multi-parameter model and analyze the invisible relationship between the parameters through the neural network.

[0019] The step S200 includes the following contents: Use the Coulomb integration method to measure the current maximum charge of each battery cell, and according to the formula: , calculate the remaining capacity of each battery unit at the current time point; in, is the relative capacity remaining in the battery cell at the measurement time point, It is the maximum charge measurement data of the battery unit. It is the maximum charge rating data of the battery unit when it leaves the factory; In specific implementation, since the distributed battery pack being analyzed is not in a factory-fresh state, it is necessary to measure the battery capacity of the battery pack as initial data for capacity decay analysis.

[0020] The step S300 includes the following contents: Real-time monitoring of the environmental parameters and state parameters of each battery cell. For any battery cell n, the capacity decay neural network model of battery cell n is used to analyze the relative capacity of battery cell n after decay. , according to the formula: ; in, is the relative capacity remaining in battery cell n at the measurement time point, is the time point at which the capacity of battery cell n is measured, is the current analysis time point, is the capacity decay prediction value of battery cell n differentiated with respect to time t; In a specific implementation, the capacity decay neural network model is differentiated with respect to time and then integrated to obtain the relative capacity remaining in the battery cell after decaying at different times. Since there will be an error accumulation effect when calculating only by the integration method, a capacity correction cycle can be set to periodically perform capacity measurement corrections on each battery cell.

[0021] The step S400 is divided into the following steps: Step S401: Calculate and analyze the relative capacity of each battery cell at the adjustment strategy analysis time point, and determine a reference battery cell; The capacity decay neural network model of each battery cell is used to analyze the relative capacity of each battery cell after decay at the adjustment strategy analysis time point, and the battery cell with the smallest relative capacity is selected as the reference battery cell; Step S402: Screening the adjustable state parameters of each battery cell to establish an adjustment constraint set; Analyze the usage mode of each battery cell, select the state parameters that can be adjusted from each battery cell as adjustment parameters, and establish an adjustment constraint set for each adjustment parameter to limit the adjustment range of each adjustment parameter; the adjustment constraint set refers to a set of all constraints that limit the adjustment range of the battery cell state parameters; In specific implementation, there are deviations in the remaining relative capacity of each battery cell within the distributed battery pack, and the relative capacity decay of the battery cell cannot be reversed through battery management. Therefore, the battery cell with the highest decay degree and the smallest remaining relative capacity is used as the reference battery cell for analysis; and when adjusting the state parameters of each battery cell, the state parameters should be adjusted to avoid scenarios where the battery cell decay rate is large. It is necessary to limit the adjustment range of each state parameter to avoid problems such as high and low state of charge causing the battery cell to decay too quickly.

[0022] Step S403: constructing a regulation strategy equation according to the relative capacity of each battery unit, and determining the regulation strategy of each battery unit; For any battery cell n, the regulation strategy analysis method is as follows: Obtaining an adjustment constraint set for each battery cell, calculating a derivative of the capacity decay neural network model with respect to decay time, and then calculating a decay rate of the battery cell when each adjustment parameter is combined within an adjustment range; According to the relative capacity of each battery unit, the regulation strategy equation is constructed: ; in, is the decay rate of battery cell n, is the decay rate of the reference battery cell, is a constant parameter, is the relative capacity of battery cell n, For reference battery cell relative capacity, is the battery cell number, is the number of battery cells, For battery cells The power provided, The power demand of distributed battery packs; In a specific implementation, the attenuation degree of the reference battery cell is relatively high, so the remaining relative capacity of the reference battery cell is used as a reference value for proportional calculation, and the attenuation rate of the battery cell capacity with a large deviation is adjusted to make the relative capacity of each battery cell tend to be consistent. At the same time, when constructing the equation group, the power demand analysis is introduced to ensure that the energy output of each battery cell meets the load demand; Solve the equation group and analyze to obtain the adjustment parameter combination that meets the power demand of the distributed battery group and has the minimum attenuation rate of the reference battery cell as the adjustment target of the reference battery cell, and calculate and analyze the adjustment parameter combination of the remaining other battery cells according to the minimum attenuation rate of the reference battery cell as the adjustment target of each battery cell; In the specific implementation, after the non-adjustable state parameters and environmental parameters are input into the equation group, the simplified equations related to the adjustable parameters are obtained, the adjustment step of each adjustable parameter is set for traversal, the attenuation rate and power of each step adjustment are calculated, and the adjustment targets of the reference battery cell and the remaining battery cells are calculated.

[0023] The step S500 includes the following contents: Setting the battery cell capacity deviation threshold , and judge the capacity deviation of each battery unit, and adjust the time slice division according to the judgment result; Obtain the remaining relative capacity of each battery cell at the initial analysis time point, and simultaneously perform capacity consistency judgment and capacity deviation threshold judgment; The capacity consistency judgment refers to the case where the capacity of any battery cell n and the reference battery cell satisfy , and reaches after adjusting the time point , then the current adjustment strategy is determined to be completed and will reach The time point is recorded as the end point of the current adjustment strategy; is the reference battery cell capacity; The capacity deviation threshold judgment means that if the capacity between any battery cells a and b satisfies , then it is determined that the current adjustment strategy causes a large deviation in capacity consistency, and the current adjustment strategy is terminated and the The time point is recorded as the end point of the current adjustment strategy; are the relative capacities of battery cells a and b after attenuation; The above-mentioned capacity consistency judgment and capacity deviation threshold judgment are performed simultaneously, and the time end point of the adjustment strategy recorded for the first time is used as the end point of the current adjustment time slice, and the battery unit adjustment strategy analysis of the next adjustment time slice is performed; In specific implementation, when the relative capacities between battery cells are consistent, the adjustment strategy is replaced to avoid overcorrection; similarly, when there are large deviations between battery cells, the adjustment strategy also needs to be replaced to avoid further expansion of the deviation.

[0024] like Figure 2 As shown, the present invention also provides an intelligent energy storage battery performance monitoring and management system, the system comprising: a capacity decay analysis module, an adjustment strategy decision module, and an adjustment strategy constraint module; The capacity decay analysis module tests and obtains the data of the capacity decay of each battery cell over time, trains the capacity decay neural network model, and is also used to calculate the relative capacity of each battery cell after decay; the adjustment strategy decision module is used to select a reference battery cell, screen the adjustable state parameters of each battery cell to establish an adjustment constraint set, construct an adjustment strategy equation according to the capacity of each battery cell, and determine the adjustment strategy of each battery cell; the adjustment strategy constraint module divides and limits the adjustment time of each battery cell adjustment strategy through capacity consistency judgment and capacity deviation threshold judgment, and divides the adjustment time slice according to the limitation result.

[0025] The capacity decay analysis module includes: a capacity measurement unit, an influencing parameter analysis unit, a model building unit, and a capacity decay calculation unit; The capacity measurement unit is used to measure the battery capacity of each battery cell in the distributed battery pack at the measurement time point and calculate the relative capacity of each battery cell; the influencing parameter analysis unit is used to analyze and mark the influencing parameters of the capacity attenuation of each battery cell in the distributed battery pack; the model construction unit constructs a capacity attenuation data set and trains a capacity attenuation neural network model based on the capacity attenuation data of each battery cell under different environmental parameters and state parameters over time; the capacity attenuation calculation unit predicts the battery capacity attenuation of each battery cell from the measurement time point to the analysis time point based on the battery capacity of each battery cell at the measurement time point, and uses the capacity attenuation neural network model to calculate the relative capacity of each battery cell after attenuation at each time point.

[0026] The adjustment strategy decision module includes: a reference selection unit, an adjustment constraint construction unit, and an adjustment strategy analysis unit; The reference selection unit determines the reference battery cell according to the relative capacity of each battery cell at the adjustment strategy analysis time point; the adjustment constraint construction unit is used to screen the adjustable state parameters of each battery cell to establish an adjustment constraint set; the adjustment strategy analysis unit constructs an adjustment strategy equation according to the relative capacity of each battery cell and determines the adjustment strategy of each battery cell.

[0027] The adjustment strategy constraint module includes: a capacity consistency judgment unit, a capacity deviation threshold judgment unit, and an adjustment time slice division unit; The capacity consistency judgment unit monitors the capacity of each battery cell in real time and performs consistency judgment; the capacity deviation threshold judgment unit monitors the capacity of each battery cell in real time and performs capacity deviation threshold judgment; the adjustment time slice division unit determines the termination time of each adjustment strategy according to the results of capacity consistency judgment and capacity deviation threshold judgment, and then divides the adjustment time slice.

[0028] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. An intelligent energy storage battery performance monitoring and management method, characterized in that , the method comprises the following analysis steps: Step S100: Analyze and mark the influencing parameters of the capacity decay of each battery unit in the distributed battery pack, test and obtain the capacity decay data of each battery unit over time under different environmental parameters and state parameters, construct a capacity decay data set, and train a capacity decay neural network model; Step S200: measuring the capacity of each battery unit in the distributed battery pack, and calculating the relative capacity of each battery unit according to the factory rated capacity data; Step S300: monitoring the environmental parameters and state parameters of each battery cell in real time, and using the capacity decay neural network model to calculate the relative capacity of each battery cell after decay at each time point; Step S400: Select a reference battery cell, screen the adjustable state parameters of each battery cell to establish an adjustment constraint set, construct an adjustment strategy equation according to the relative capacity of each battery cell, and determine the adjustment strategy of each battery cell; Step S500: performing capacity consistency judgment and capacity deviation threshold judgment on each battery unit, and dividing the adjustment strategy into adjustment time slices according to the judgment results.

2. According to claim 1, an intelligent energy storage battery performance monitoring and management method is characterized in that: The step S100 is divided into the following steps: Step S101: Analyze and mark the capacity attenuation influencing parameters of each battery unit in the distributed battery group; The influencing parameters include environmental parameters and state parameters, wherein the environmental parameters refer to environmental factors that affect the capacity decay in the environment where the battery cell is located, and the state parameters refer to electrical parameters that affect the capacity decay of the battery cell; Step S102: testing and obtaining the data of capacity decay over time of each battery unit, and recording the environmental parameters and state parameters corresponding to each data, to construct a capacity decay data set; Step S103: Use the capacity decay data set to train a capacity decay neural network model, and record the capacity decay neural network model of battery cell n as: ； in, is the predicted value of capacity attenuation of battery cell n, is the environmental parameter set input item of the battery cell n capacity decay neural network model, is the state parameter set input item of the battery cell n capacity decay neural network model, is the capacity decay time of the capacity decay neural network model of battery cell n.

3. The intelligent energy storage battery performance monitoring and management method according to claim 2 is characterized in that: The step S200 includes the following contents: Use the Coulomb integration method to measure the current maximum charge of each battery cell, and according to the formula: , calculate the remaining capacity of each battery unit at the current time point; in, is the relative capacity remaining in the battery cell at the measurement time point, It is the maximum charge measurement data of the battery unit. This is the maximum charge rating of the battery unit when it leaves the factory.

4. The intelligent energy storage battery performance monitoring and management method according to claim 1 is characterized in that: The step S300 includes the following contents: Real-time monitoring of the environmental parameters and state parameters of each battery cell. For any battery cell n, the capacity decay neural network model of battery cell n is used to analyze the relative capacity of battery cell n after decay. , according to the formula: ； in, is the relative capacity remaining in battery cell n at the measurement time point, is the time point at which the capacity of battery cell n is measured, is the current analysis time point, is the capacity decay prediction value of battery cell n differentiated with respect to time t.

5. The intelligent energy storage battery performance monitoring and management method according to claim 1 is characterized in that: The step S400 is divided into the following steps: Step S401: Calculate and analyze the relative capacity of each battery cell at the adjustment strategy analysis time point, and determine a reference battery cell; The capacity decay neural network model of each battery cell is used to analyze the relative capacity of each battery cell after decay at the adjustment strategy analysis time point, and the battery cell with the smallest relative capacity is selected as the reference battery cell; Step S402: Screening the adjustable state parameters of each battery cell to establish an adjustment constraint set; Analyze the usage mode of each battery cell, select the state parameters that can be adjusted from each battery cell as adjustment parameters, and establish an adjustment constraint set for each adjustment parameter to limit the adjustment range of each adjustment parameter; the adjustment constraint set refers to a set of all constraints that limit the adjustment range of the battery cell state parameters; Step S403: constructing a regulation strategy equation according to the relative capacity of each battery unit, and determining the regulation strategy of each battery unit; For any battery cell n, the regulation strategy analysis method is as follows: Obtaining an adjustment constraint set for each battery cell, calculating a derivative of the capacity decay neural network model with respect to decay time, and then calculating a decay rate of the battery cell when each adjustment parameter is combined within an adjustment range; According to the relative capacity of each battery unit, the regulation strategy equation is constructed: ； in, is the decay rate of battery cell n, is the decay rate of the reference battery cell, is a constant parameter, is the relative capacity of battery cell n, For reference battery cell relative capacity, is the battery cell number, is the number of battery cells, For battery cells The power provided, The power demand of distributed battery packs; Solve the equations and analyze to obtain the adjustment parameter combination that meets the power demand of the distributed battery pack and minimizes the attenuation rate of the reference battery cell, which is used as the adjustment target of the reference battery cell. Calculate and analyze the adjustment parameter combination of the remaining battery cells based on the minimum attenuation rate of the reference battery cell as the adjustment target of each battery cell.

6. The intelligent energy storage battery performance monitoring and management method according to claim 1 is characterized in that: The step S500 includes the following contents: Setting the battery cell capacity deviation threshold , and judge the capacity deviation of each battery unit, and adjust the time slice division according to the judgment result; Obtain the remaining relative capacity of each battery cell at the initial analysis time point, and simultaneously perform capacity consistency judgment and capacity deviation threshold judgment; The capacity consistency judgment refers to the case where the capacity of any battery cell n and the reference battery cell satisfy , and reaches after adjusting the time point , then the current adjustment strategy is determined to be completed and will reach The time point is recorded as the end point of the current adjustment strategy; is the reference battery cell capacity; The capacity deviation threshold judgment means that if the capacity between any battery cells a and b satisfies , then it is determined that the current adjustment strategy causes a large deviation in capacity consistency, and the current adjustment strategy is terminated and the The time point is recorded as the end point of the current adjustment strategy; are the relative capacities of battery cells a and b after attenuation; The above-mentioned capacity consistency judgment and capacity deviation threshold judgment are performed simultaneously, and the time end point of the adjustment strategy recorded for the first time is taken as the end point of the current adjustment time slice, and the battery unit adjustment strategy analysis of the next adjustment time slice is performed.

7. An intelligent energy storage battery performance monitoring and management system using an intelligent energy storage battery performance monitoring and management method according to any one of claims 1 to 6, characterized in that: The system includes: a capacity decay analysis module, a regulation strategy decision module, and a regulation strategy constraint module; The capacity decay analysis module tests and obtains the data of the capacity decay of each battery cell over time, trains the capacity decay neural network model, and is also used to calculate the relative capacity of each battery cell after decay; the adjustment strategy decision module is used to select a reference battery cell, screen the adjustable state parameters of each battery cell to establish an adjustment constraint set, construct an adjustment strategy equation according to the capacity of each battery cell, and determine the adjustment strategy of each battery cell; the adjustment strategy constraint module divides and limits the adjustment time of each battery cell adjustment strategy through capacity consistency judgment and capacity deviation threshold judgment, and divides the adjustment time slice according to the limitation result.

8. The intelligent energy storage battery performance monitoring and management system according to claim 7 is characterized in that: The capacity decay analysis module includes: a capacity measurement unit, an influencing parameter analysis unit, a model building unit, and a capacity decay calculation unit; The capacity measurement unit is used to measure the battery capacity of each battery cell in the distributed battery pack at the measurement time point and calculate the relative capacity of each battery cell; the influencing parameter analysis unit is used to analyze and mark the influencing parameters of the capacity attenuation of each battery cell in the distributed battery pack; the model construction unit constructs a capacity attenuation data set and trains a capacity attenuation neural network model based on the capacity attenuation data of each battery cell under different environmental parameters and state parameters over time; the capacity attenuation calculation unit predicts the battery capacity attenuation of each battery cell from the measurement time point to the analysis time point based on the battery capacity of each battery cell at the measurement time point, and uses the capacity attenuation neural network model to calculate the relative capacity of each battery cell after attenuation at each time point.

9. The intelligent energy storage battery performance monitoring and management system according to claim 7, characterized in that: The adjustment strategy decision module includes: a reference selection unit, an adjustment constraint construction unit, and an adjustment strategy analysis unit; The reference selection unit determines the reference battery cell according to the relative capacity of each battery cell at the adjustment strategy analysis time point; the adjustment constraint construction unit is used to screen the adjustable state parameters of each battery cell to establish an adjustment constraint set; the adjustment strategy analysis unit constructs an adjustment strategy equation according to the relative capacity of each battery cell and determines the adjustment strategy of each battery cell.

10. The intelligent energy storage battery performance monitoring and management system according to claim 7, characterized in that: The adjustment strategy constraint module includes: a capacity consistency judgment unit, a capacity deviation threshold judgment unit, and an adjustment time slice division unit; The capacity consistency judgment unit monitors the capacity of each battery cell in real time and performs consistency judgment; the capacity deviation threshold judgment unit monitors the capacity of each battery cell in real time and performs capacity deviation threshold judgment; the adjustment time slice division unit determines the termination time of each adjustment strategy according to the results of capacity consistency judgment and capacity deviation threshold judgment, and then divides the adjustment time slice.

Images