Energy storage performance adaptability optimization method and system in multiple environments

Abstract

The invention relates to the technical field related to energy storage performance optimization, in particular to an energy storage performance adaptability optimization method and system under multiple environments, and the method comprises the steps: collecting environmental parameters in real time based on an energy storage assembly, analyzing energy storage efficiency and capacity attenuation, configuring multiple adaptive paths, constructing an energy storage performance degradation map, and introducing historical data correction. The method comprises the steps of predicting a health state and capacity attenuation, inputting an optimization engine, determining an instruction set, and executing energy storage management in different environments, solves the technical problems of poor energy storage performance consistency and stability and low energy storage utilization rate of an energy storage assembly in multiple environments, realizes real-time acquisition and analysis of environmental parameters, configures multiple energy storage adaptive paths, and improves the energy storage efficiency. The method has the technical effects that the working state is automatically adjusted according to different environments, the environmental adaptability of the energy storage component is improved, the incidence matrix of historical degradation data and environmental parameters is introduced, the health state index and the residual available capacity attenuation rate of the energy storage component are predicted, the energy storage performance is optimized, and the stability of a power grid is improved.

Description

Technical Field

[0001] The present invention relates to the technical field related to the optimization of energy storage performance, and specifically relates to a method and system for optimizing the adaptability of energy storage performance in multiple environments. Background Art

[0002] As a key technology connecting the supply and demand sides, balancing grid fluctuations, and improving energy utilization efficiency, energy storage technology has become increasingly important. However, there are significant differences in energy storage performance under different environments. Environmental factors such as temperature, humidity, and air pressure have a significant impact on energy storage efficiency and capacity decay. For example, in a high-temperature environment, the internal resistance of the battery increases, resulting in a decrease in energy storage efficiency and an acceleration of capacity decay; in a high-humidity environment, there is a certain probability of battery corrosion, affecting battery performance and lifespan. In addition, the current energy storage configuration lacks a comprehensive consideration of the adaptability optimization of energy storage performance under different environments, resulting in low energy storage utilization and difficulty in meeting the diversified demands of the power grid for energy storage under high new energy penetration.

[0003] In summary, there are technical problems in the prior art such as poor consistency and stability of energy storage performance of energy storage components in multiple environments and low energy storage utilization. Summary of the Invention

[0004] This application provides a system for optimizing the adaptability of energy storage performance in multiple environments, aiming to solve the technical problems of poor consistency and stability of energy storage performance of energy storage components in multiple environments and low energy storage utilization in the prior art.

[0005] In view of the above problems, the technical solution of this application is as follows: On the one hand, this application provides a method for optimizing the adaptability of energy storage performance in multiple environments. Among them, the method includes: based on energy storage components, determining an environmental parameter set, and the environmental parameter set collected by the multi-modal environmental perception array in real time includes temperature, humidity, and air pressure; according to the environmental parameter set, analyzing the changes in energy storage efficiency and the trend of energy storage capacity decay under different environments, and configuring multiple energy storage adaptation paths, each of which has a capacity decay mark; through the multiple energy storage adaptation paths, performing correlation coupling analysis with the environmental parameter set to construct an energy storage performance degradation characteristic map; introducing a historical degradation data and environmental parameter correlation matrix to correct the phase shift of the energy storage performance degradation characteristic map, and using random forest regression to predict the health state index of the energy storage components and output the remaining available capacity decay rate; inputting the health state index and the remaining available capacity decay rate into a dynamic optimization engine to determine an adaptability optimization instruction set, including charge and discharge rate adjustment parameters, temperature compensation strategies, and load balancing schemes; executing the energy storage management of the energy storage components under different environments with the optimization instruction set.

[0006] On the other hand, the present application provides a system for optimizing the adaptability of energy storage performance in multiple environments. The system includes: a data acquisition module for determining an environmental parameter set based on energy storage components. The environmental parameter set collected in real time by the multi-modal environmental perception array includes temperature, humidity, and air pressure; a configuration module for analyzing the change in energy storage efficiency and the trend of energy storage capacity attenuation in different environments according to the environmental parameter set, and configuring multiple energy storage adaptation paths, each of which has a capacity attenuation mark; a coupling analysis module for performing correlation coupling analysis between the multiple energy storage adaptation paths and the environmental parameter set to construct a characteristic map of energy storage performance degradation; an offset correction module for introducing a correlation matrix of historical degradation data and environmental parameters to correct the phase offset of the characteristic map of energy storage performance degradation, predicting the health state index of the energy storage components using random forest regression, and outputting the remaining available capacity attenuation rate; an input module for inputting the health state index and the remaining available capacity attenuation rate into a dynamic optimization engine to determine an adaptability optimization instruction set, including charge and discharge rate adjustment parameters, temperature compensation strategies, and load balancing schemes; and an energy storage management module for performing energy storage management of the energy storage components in different environments according to the optimization instruction set.

[0007] In summary, one or more technical solutions provided in the present application achieve the technical effects of real-time collecting and analyzing environmental parameters, configuring multiple energy storage adaptation paths, automatically adjusting the working state according to different environments, improving the environmental adaptability of energy storage components, introducing a correlation matrix of historical degradation data and environmental parameters, predicting the health state index of energy storage components and the remaining available capacity attenuation rate, and further optimizing the energy storage performance and enhancing the stability of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 is a schematic flow chart of a method for optimizing the adaptability of energy storage performance in multiple environments provided by the present application; Figure 2 is a schematic structural diagram of a system for optimizing the adaptability of energy storage performance in multiple environments provided by the present application.

[0009] Description of the reference numerals: data acquisition module M100, configuration module M200, coupling analysis module M300, offset correction module M400, input module M500, energy storage management module M600. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0010] Embodiment 1 The present application will be specifically described below with reference to the drawings. As Figure 1 shown, the present application provides a method for optimizing the adaptability of energy storage performance in multiple environments. The method includes: S1: Based on the energy storage component, determine the environmental parameter set. The environmental parameter set collected in real time by the multi-modal environmental perception array includes temperature, humidity, and air pressure; S2: According to the environmental parameter set, analyze the changes in energy storage efficiency and the trend of energy storage capacity attenuation in different environments, and configure multiple energy storage adaptation paths. Each energy storage adaptation path has a capacity attenuation mark; S3: Through the multiple energy storage adaptation paths, conduct an associated coupling analysis with the environmental parameter set to construct a characteristic map of energy storage performance degradation.

[0011] Specifically, the multi-modal environmental perception array refers to a device integrated with multiple sensors, which can simultaneously sense and collect multiple environmental parameters (for example, in a temperature range of -20°C to 50°C, a humidity range of 20% to 90%, and an air pressure range of 80 kPa to 110 kPa), and achieve comprehensive monitoring of the environment through multiple sensing modes (such as thermal sensors, humidity sensors, and air pressure sensors); the energy storage adaptation path refers to the operating strategy or working mode designed for the energy storage component in different environments. Each path targets specific environmental conditions to optimize the energy storage performance; the capacity attenuation mark refers to the parameter that records and identifies the capacity attenuation of the energy storage component in each energy storage adaptation path, which is used for subsequent analysis and optimization; the associated coupling analysis refers to analyzing the environmental parameters and the performance data of the energy storage component, considering the interaction and influence between the environmental parameters and the performance data of the energy storage component, to construct a more accurate performance model; the characteristic map of energy storage performance degradation is used to display the performance degradation trend and characteristics of the energy storage component under different environmental conditions, and helps analyze and predict its health status.

[0012] The temperature, humidity, and air pressure of the environment where the energy storage component is located are collected in real time through the multi-modal environmental perception array to form an environmental parameter set; based on these parameters, analyze the efficiency changes and capacity attenuation trends of the energy storage component in different environments, and configure multiple energy storage adaptation paths according to the analysis results. Each path is marked with the corresponding capacity attenuation situation. Conduct an associated coupling analysis of these adaptation paths with the environmental parameters; by real-time sensing the environmental parameters and analyzing their impact on the energy storage performance, it is possible to provide targeted strategies for the operation of the energy storage component in different environments, thereby improving the environmental adaptability and overall performance of the energy storage component.

[0013] S4: Introduce the historical degradation data and environmental parameter correlation matrix, correct the phase shift of the characteristic map of energy storage performance degradation, use random forest regression to predict the health state index of the energy storage component, and output the remaining available capacity attenuation rate; S5: Input the health state index and the remaining available capacity attenuation rate into the dynamic optimization engine to determine the adaptive optimization instruction set, including charge and discharge rate adjustment parameters, temperature compensation strategies, and load balancing schemes; S6: Execute the energy storage management of the energy storage component in different environments with the optimization instruction set.

[0014] Specifically, historical degradation data refers to the information related to the performance degradation accumulated by the energy storage component during previous operations, including capacity attenuation and efficiency decline, which reflects the long-term performance change trend of the energy storage component under different environmental conditions; the environmental parameter correlation matrix is used to describe the quantitative relationship between environmental parameters (such as temperature, humidity, and air pressure) and the performance degradation of the energy storage component. In matrix form, it clearly expresses the interaction and influence weight between each parameter; the phase shift refers to the deviation between the actual performance change and the theoretical prediction in the energy storage performance degradation characteristic map, which is caused by the non-linear influence of environmental conditions or data acquisition errors; random forest regression is used to predict the health state index and the remaining available capacity attenuation rate of the energy storage component. By constructing multiple decision tree models and considering various factors comprehensively, the accuracy and robustness of the prediction are improved.

[0015] The dynamic optimization engine is a decision-making unit that generates an optimization instruction set adapted to the current environmental conditions based on the input health state index and the remaining capacity attenuation rate. These instruction sets include charge and discharge rate adjustment parameters, temperature compensation strategies, and load balancing schemes, which are used to dynamically adjust the working state of the energy storage component; the adaptive optimization instruction set refers to a set of optimization instructions dynamically generated according to the health state and environmental conditions of the energy storage component. These instructions can adjust the operating parameters of the energy storage component in real time to meet the performance requirements in different environments.

[0016] Combining prediction and optimization to achieve the intelligent management of the energy storage component. Specifically, introducing the historical degradation data and the environmental parameter correlation matrix to correct the energy storage performance degradation characteristic map. By correcting the phase shift, it can more accurately reflect the performance change trend of the energy storage component under the current environment; using the random forest regression model to predict the health state index and the remaining available capacity attenuation rate of the energy storage component. These prediction results provide key inputs for the dynamic optimization engine, enabling it to generate an adaptive optimization instruction set according to the current health state and capacity attenuation situation. These instruction sets include charge and discharge rate adjustment parameters, temperature compensation strategies, and load balancing schemes, which are used to guide the operation management of the energy storage component in different environments; accurately evaluating the health state of the energy storage component and dynamically adjusting its operating parameters, thereby improving the service life and operating efficiency of the energy storage component, and ensuring its stability and reliability in different environments.

[0017] Furthermore, according to the set of environmental parameters, analyzing the energy storage efficiency change and the energy storage capacity attenuation trend under different environments, and configuring multiple energy storage adaptation paths. The method of this application includes: Based on the set of environmental parameters, in combination with the thermal management characteristics, moisture-proof characteristics, and pressure adaptability of the energy storage component, configure the first energy storage optimization pointer, the second energy storage optimization pointer, and the third energy storage optimization pointer; perform unidirectional competitive iteration on the first energy storage optimization pointer, the second energy storage optimization pointer, and the third energy storage optimization pointer according to the energy storage capacity attenuation trend.

[0018] Specifically, the energy storage optimization pointer refers to the parameter index used to guide the optimized operation of the energy storage component under specific environmental conditions. These pointers combine the thermal management characteristics, moisture-proof characteristics, and pressure adaptability of the energy storage component, and are optimized and configured respectively for different environmental impact factors (such as temperature, humidity, air pressure); the first energy storage optimization pointer is usually related to temperature and is used to optimize the performance of the energy storage component under different temperature conditions; the second energy storage optimization pointer is related to humidity and is used to optimize the performance under different humidity conditions; the third energy storage optimization pointer is related to air pressure and is used to optimize the performance under different air pressure conditions; unidirectional competitive iteration means that during the optimization process, competitive adjustment is carried out among the three optimization pointers of the first energy storage optimization pointer, the second energy storage optimization pointer, and the third energy storage optimization pointer. The pointer that has the most significant improvement in energy storage performance is preferentially selected for optimization, while taking into account the auxiliary role of other pointers. This iteration method ensures the efficiency and pertinence of the optimization process.

[0019] Based on the set of environmental parameters (temperature, humidity, air pressure), in combination with the thermal management characteristics, moisture-proof characteristics, and pressure adaptability of the energy storage component, configure the first, second, and third energy storage optimization pointers respectively. These pointers respectively provide optimization directions for the operation of the energy storage component in response to the influences of temperature, humidity, and air pressure. For example, in a high-temperature environment, the first energy storage optimization pointer related to temperature is preferentially adjusted to reduce the impact of temperature on energy storage efficiency and capacity attenuation.

[0020] In a high-humidity environment, the second energy storage optimization pointer related to humidity is preferentially adjusted to prevent problems such as battery corrosion. This dynamic adjustment mechanism significantly improves the intelligent level and operation efficiency of the energy storage system; according to the energy storage capacity attenuation trend, unidirectional competitive iteration is performed on these three optimization pointers. During the iteration process, the pointer that has the most significant improvement in energy storage performance is preferentially selected for optimization, and at the same time, collaborative adjustment is carried out through the auxiliary optimization direction; by configuring and iteratively optimizing the pointers, it is possible to respond in real time to changes in environmental parameters, dynamically adjust the operation state of the energy storage component, and thus improve the adaptability and performance stability of the energy storage component in different environments.

[0021] Furthermore, for the unidirectional competitive iteration of the first energy storage optimization pointer, the method of the present application includes: By presetting temperature change scenarios, multiple temperature-sensitive regions are identified, where each temperature-sensitive region has at least one temperature fluctuation point; based on the first energy storage optimization pointer, in combination with the multiple temperature-sensitive regions, a temperature adaptability index group associated with the first energy storage optimization pointer is configured.

[0022] Specifically, the preset temperature change scenario refers to a series of temperature change situations (such as a step change from -20°C to 60°C) preset according to the actual operating environment faced by the energy storage component, including the high and low temperature ranges and the change rate. These scenarios are used to simulate the operating conditions of the energy storage component under different temperature conditions; the temperature-sensitive region refers to the interval in the preset temperature change scenario where the performance of the energy storage component is particularly sensitive to temperature changes. These regions usually correspond to the temperature ranges where the performance of the energy storage component changes significantly. For example, in the lithium battery electrolyte region, the charge and discharge efficiency and internal resistance of the battery will change rapidly with temperature in these regions; the temperature fluctuation point refers to the key node of temperature change within the temperature-sensitive region, which is the temperature value at which the performance of the energy storage component undergoes a sudden change or a turning point. For example, the internal resistance of the battery increases sharply or the capacity decreases rapidly at a certain temperature point; the temperature adaptability index group refers to a set of parameters used to evaluate the adaptability and performance of the energy storage component in different temperature-sensitive regions, including the temperature compensation coefficient and the thermal management adjustment factor, which are used to guide the optimized operation of the energy storage component under different temperature conditions.

[0023] By presetting temperature change scenarios, multiple temperature-sensitive regions are identified, and at least one temperature fluctuation point is determined within each region. These temperature-sensitive regions and fluctuation points are determined based on the thermal management characteristics and actual operating data of the energy storage component, reflecting the performance change characteristics of the energy storage component under different temperature conditions; based on the first energy storage optimization pointer (an optimization pointer related to temperature), in combination with these temperature-sensitive regions, a temperature adaptability index group associated with it is configured. These index groups are used to evaluate and optimize the operating performance of the energy storage component under different temperature conditions. Preferably, in the high-temperature sensitive region, by adjusting the temperature compensation coefficient in the temperature adaptability index group, the heat dissipation strategy of the energy storage component is optimized to reduce the impact of high temperature on energy storage efficiency and lifespan; by identifying temperature-sensitive regions and fluctuation points, the performance bottlenecks of the energy storage component under different temperature conditions can be more accurately located. In combination with the temperature adaptability index group, the operating parameters of the energy storage component can be dynamically adjusted, thereby improving the adaptability and operating efficiency of the energy storage component in different temperature environments.

[0024] Furthermore, the method of this application further includes: Based on the temperature adaptability index group, evaluate the influence weight of temperature fluctuations on energy storage efficiency, and determine the priority of the multiple temperature-sensitive regions; based on the priority, establish a first energy storage efficiency compensation mechanism, and the first energy storage efficiency compensation mechanism is used to iteratively constrain the energy storage adaptation paths in different environments.

[0025] Specifically, the temperature adaptability index group is a set of parameters used to evaluate the performance of energy storage components under different temperature conditions, including the temperature compensation coefficient and the thermal management adjustment factor, which reflect the adaptability of energy storage components to temperature changes; the influence weight refers to the quantification degree of the impact of temperature fluctuations on energy storage efficiency. By evaluating the temperature adaptability index group, the specific impact degree of different temperature fluctuation points or temperature-sensitive regions on energy storage efficiency is determined, thereby providing a basis for optimization strategies; the priority refers to sorting multiple temperature-sensitive regions according to the influence weight of temperature fluctuations on energy storage efficiency. A region with a higher priority indicates that the temperature fluctuations in this region have a more significant impact on energy storage efficiency and need to be optimized preferentially; the first energy storage efficiency compensation mechanism is an optimization strategy used to dynamically adjust the operating parameters of energy storage components according to the priority of temperature-sensitive regions to compensate for the negative impact of temperature fluctuations on energy storage efficiency. This mechanism ensures the performance optimization of energy storage components in different environments by iteratively constraining the energy storage adaptation path.

[0026] Based on the temperature adaptability index group, evaluate the influence weight of temperature fluctuations on energy storage efficiency. Specifically, by analyzing the performance changes of energy storage components in temperature-sensitive regions, determine the influence degree of each region on energy storage efficiency. Subsequently, according to these influence weights, sort the multiple temperature-sensitive regions by priority. A region with a higher priority indicates that the temperature fluctuations have a more significant impact on energy storage efficiency and need to be optimized preferentially; based on the determined priority, establish the first energy storage efficiency compensation mechanism. This mechanism iteratively constrains the energy storage adaptation path in different environments by dynamically adjusting the operating parameters of energy storage components (such as charge and discharge rates, heat dissipation strategies). For example, in the temperature-sensitive region with the highest priority, by adjusting the temperature compensation coefficient, optimize the thermal management strategy of energy storage components to compensate for the negative impact of temperature fluctuations on energy storage efficiency. This compensation mechanism can ensure the optimized operating efficiency of energy storage components under different temperature conditions and improve the overall performance and stability of the energy storage system; through a refined temperature management strategy, dynamically optimize the operating state of energy storage components. By evaluating the influence weight of temperature fluctuations and determining the priority, it is possible to specifically address the negative impact of temperature on energy storage efficiency, thereby improving the adaptability and operating efficiency of energy storage components in different environments.

[0027] Furthermore, based on the above priority, establish the first energy storage efficiency compensation mechanism. The method of this application includes: Based on the above priorities, a first energy storage efficiency compensation parameter set is configured. The first energy storage efficiency compensation parameter set includes a temperature compensation coefficient, a thermal management adjustment factor, and a temperature fluctuation tolerance threshold. The first energy storage efficiency compensation mechanism is used in the one-way competition iteration process. According to the first energy storage efficiency compensation parameter set, taking the first energy storage optimization pointer as the dominant optimization direction and combining the auxiliary optimization directions of the second energy storage optimization pointer and the third energy storage optimization pointer, multi-path collaborative optimization is carried out.

[0028] Specifically, the first energy storage efficiency compensation parameter set refers to a set of specific parameters used to implement the first energy storage efficiency compensation mechanism, including: a temperature compensation coefficient, a thermal management adjustment factor, and a temperature fluctuation tolerance threshold. Among them, the temperature compensation coefficient is used to adjust the operating parameters of the energy storage components under different temperature conditions to compensate for the impact of temperature changes on the energy storage efficiency. The thermal management adjustment factor is used to control the thermal management system of the energy storage components (such as heat dissipation or heating devices) to maintain the energy storage components within the optimal operating temperature range. The temperature fluctuation tolerance threshold defines the temperature fluctuation range that the energy storage components can withstand, and beyond this range, the compensation mechanism is triggered.

[0029] One-way competition iteration means that in the optimization process, competitive adjustments are made among the first energy storage optimization pointer, the second energy storage optimization pointer, and the third energy storage optimization pointer. The pointer that has the most significant improvement in energy storage performance is preferentially selected for optimization, while taking into account the auxiliary role of other pointers, ensuring the efficiency and pertinence of the optimization process. Multi-path collaborative optimization means that in the optimization process, considering the dominant optimization direction (such as the first energy storage optimization pointer) and combining the auxiliary roles of other optimization pointers (such as the second and third energy storage optimization pointers), multi-path collaborative optimization is achieved to obtain better overall performance.

[0030] Based on the priorities of the temperature-sensitive region, a first energy storage efficiency compensation parameter set is configured. These parameter sets include a temperature compensation coefficient, a thermal management adjustment factor, and a temperature fluctuation tolerance threshold, which are used to dynamically adjust the operating state of the energy storage components under different temperature conditions. Subsequently, in the one-way competition iteration process, taking the first energy storage optimization pointer (the optimization pointer related to temperature) as the dominant optimization direction, and at the same time combining the auxiliary optimization directions of the second energy storage optimization pointer (related to humidity) and the third energy storage optimization pointer (related to air pressure), multi-path collaborative optimization is carried out. Through refined parameter configuration and collaborative optimization mechanism, the operating state of the energy storage components is dynamically adjusted to meet the performance requirements under different environmental conditions. Preferably, in a high-temperature environment, by adjusting the temperature compensation coefficient and the thermal management adjustment factor, the heat dissipation strategy of the energy storage components is optimized to reduce the negative impact of temperature on the energy storage efficiency and lifespan. At the same time, combining the auxiliary roles of the humidity and air pressure optimization pointers, the overall performance of the energy storage components is further improved. This multi-path collaborative optimization mechanism can ensure the efficient operation of the energy storage components in a complex environment and improve their adaptability and reliability.

[0031] Furthermore, in combination with the auxiliary optimization directions of the second energy storage optimization pointer and the third energy storage optimization pointer, for multi-path collaborative optimization, the method of the present application further includes: By presetting a humidity change scenario, multiple humidity-sensitive regions are identified, where each humidity-sensitive region has at least one humidity fluctuation point; based on the second energy storage optimization pointer, in combination with the multiple humidity-sensitive regions, a humidity adaptability index group associated with the second energy storage optimization pointer is configured; based on the humidity adaptability index group, a second energy storage efficiency compensation mechanism is established, and the second energy storage efficiency compensation mechanism is used to assist the first energy storage optimization pointer in optimizing the energy storage adaptation path during the one-way competitive iteration process.

[0032] Specifically, the preset humidity change scenario refers to a series of preset humidity change situations (such as 30%-95% step change) according to the actual operating environment faced by the energy storage components, including the high and low humidity ranges and the change rate, used to simulate the operation of the energy storage components under different humidity conditions; the humidity-sensitive region refers to the interval in the preset humidity change scenario where the performance of the energy storage components is particularly sensitive to humidity changes, and these regions usually correspond to the humidity ranges where the performance of the energy storage components changes significantly. For example, the charge and discharge efficiency and internal resistance of the battery will change rapidly with humidity in these regions; the humidity fluctuation point refers to the key node of humidity change within the humidity-sensitive region, and these points are usually the humidity values at which the performance of the energy storage components undergoes sudden changes or turns. For example, the internal resistance of the battery increases sharply or the capacity drops rapidly at a certain humidity point.

[0033] The humidity adaptability index group refers to a set of parameters used to evaluate the adaptability and performance of the energy storage components in different humidity-sensitive regions, including the humidity compensation coefficient and the moisture-proof adjustment factor, used to guide the optimal operation of the energy storage components under different humidity conditions; the second energy storage efficiency compensation mechanism is used to dynamically adjust the operating parameters of the energy storage components according to the humidity adaptability index group to compensate for the negative impact of humidity fluctuations on the energy storage efficiency. This mechanism assists the first energy storage optimization pointer (temperature optimization pointer) during the one-way competitive iteration process to jointly optimize the energy storage adaptation path.

[0034] By presetting a humidity change scenario, multiple humidity-sensitive regions are identified, and at least one humidity fluctuation point is determined within each region. These humidity-sensitive regions and fluctuation points are determined based on the moisture-proof characteristics of the energy storage components and the actual operating data, reflecting the performance change characteristics of the energy storage components under different humidity conditions; based on the second energy storage optimization pointer (humidity-related optimization pointer), in combination with these humidity-sensitive regions, a humidity adaptability index group associated with it is configured, and these index groups are used to evaluate and optimize the operating performance of the energy storage components under different humidity conditions.

[0035] Based on the humidity adaptability index group, a second energy storage efficiency compensation mechanism is established. During the unidirectional competition iteration process, this mechanism assists the first energy storage optimization pointer (temperature optimization pointer) in optimizing the energy storage adaptation path. Specifically, when the first energy storage optimization pointer dominates the optimization direction, the second energy storage optimization pointer provides an auxiliary optimization strategy through the humidity adaptability index group to ensure that while optimizing temperature adaptability, the influence of humidity on energy storage performance is also considered; by identifying humidity-sensitive areas and fluctuation points, the performance bottlenecks of energy storage components under different humidity conditions can be more accurately located. Combining the humidity adaptability index group and the second energy storage efficiency compensation mechanism, it has been verified that the second energy storage efficiency compensation mechanism is triggered when the humidity > 85%, and the nitrogen filling and sealing technology is activated to stabilize the internal humidity below 60% and reduce the corrosion rate by 40%. It can dynamically adjust the operating parameters of energy storage components (such as moisture-proof strategies, charge and discharge rates), thereby improving the adaptability and operating efficiency of energy storage components in different humidity environments.

[0036] Furthermore, a characteristic map of energy storage performance degradation is constructed. The method of this application includes: Based on the energy storage components, three-dimensional grid units are set, and the size of the three-dimensional grid units does not exceed 1 / 3 of the heat conduction characteristic length; the coupling weights of temperature, humidity, and air pressure in the three-dimensional grid units are fused to establish unsteady heat transfer-electrochemical coupling mapping parameters, and the characteristic map of energy storage performance degradation is configured.

[0037] Specifically, the three-dimensional grid unit refers to a three-dimensional grid structure divided within the physical space of the energy storage component, used for discretely modeling the internal state of the energy storage component. Each grid unit represents a local area of the energy storage component and is used to analyze and calculate the physical and chemical processes within this area; the heat conduction characteristic length refers to the characteristic scale of the internal heat conduction process of the energy storage component, which is usually related to the geometric size and material thermal conductivity of the energy storage component and is an important parameter for measuring the heat conduction efficiency, used to determine the reasonable size of the three-dimensional grid unit; the coupling weight refers to the quantification degree of the influence of temperature, humidity, and air pressure on the performance of the energy storage component in the three-dimensional grid unit. These weights reflect the interaction and influence intensity of different environmental parameters within the energy storage component; the unsteady heat transfer-electrochemical coupling mapping parameters refer to a set of parameters that combine the unsteady heat transfer process (such as heat conduction, convection, radiation) with the electrochemical process (such as battery charge and discharge reactions). These parameters are used to describe the thermal-electrochemical behavior of the energy storage component under dynamic environmental conditions; the characteristic map of energy storage performance degradation is used to display the performance degradation trend and characteristics of the energy storage component under different environmental conditions.

[0038] Based on the physical structure of the energy storage component, three-dimensional grid units are set, and their size does not exceed 1 / 3 of the heat conduction characteristic length. Preferably, on the one hand, the thermal diffusivity of the energy storage component material is / s (typical lithium - ion battery electrolyte), characteristic time t = 1 s (transient thermal analysis time step), then: = , and the calculated value is 0.00316 m, that is, 3.16 mm; the grid size corresponding to the three - dimensional grid element needs to satisfy / 3, and the calculated value is 1.05 mm to ensure accuracy.

[0039] On the other hand, further restrictions ensure that the grid elements can accurately capture the heat conduction process inside the energy storage component, while avoiding ignoring local details due to overly large grid elements. According to the criteria of spatial discretization, in steady - state or transient thermal analysis, the grid size needs to meet certain resolution requirements. For example, in finite - element analysis, it is usually recommended that there be at least 3 grid points in each wavelength or gradient - change region. To meet the accuracy requirements (at least 3 grid points to resolve the temperature gradient) simultaneously, the grid size does not exceed 1 / 3 of the characteristic length, so as to more accurately capture the temperature distribution.

[0040] Fuse the coupling weights of temperature, humidity, and air pressure in the three - dimensional grid element to establish non - steady - state heat transfer - electrochemistry coupling mapping parameters. These parameters couple and analyze the heat - electrochemical process by quantifying the influence of different environmental parameters on the performance of the energy storage component, configure the energy storage performance degradation characteristic map. The energy storage performance degradation characteristic map visually shows the performance degradation characteristics of the energy storage component under different environmental conditions; through refined modeling and analysis, comprehensively evaluate the performance changes of the energy storage component under dynamic environmental conditions. By setting three - dimensional grid elements and fusing the coupling weights of multiple environmental parameters, it is possible to more accurately simulate the internal physical and chemical processes of the energy storage component, and thus provide support for the health management and performance optimization of the energy storage component.

[0041] Furthermore, to establish non - steady - state heat transfer - electrochemistry coupling mapping parameters and configure the energy storage performance degradation characteristic map, the method of this application further includes: Activate the reference load at preset intervals, measure the transient response characteristics of the energy storage component; set the environmental sensitivity matrix according to the transient response characteristics of the energy storage component; extract the pattern - associated features in the historical degradation data based on the environmental sensitivity matrix, and use a recurrent neural network to iteratively compensate for the phase shift to update the confidence parameters of the energy storage performance degradation characteristic map.

[0042] Specifically, the reference load is the standard load condition used to test the performance of the energy storage component, which is used to activate the energy storage component and measure its response characteristics; the transient response characteristic refers to the change characteristic of output parameters (such as voltage, current, power) over time when the energy storage component is under load changes or other external excitations. The transient response characteristic reflects the dynamic performance of the energy storage component, including response speed and stability; the environmental sensitivity matrix is a mathematical matrix that quantitatively describes the sensitivity of the energy storage component's performance to different environmental parameters (such as temperature, humidity, air pressure). The elements in the matrix represent the influence weights of specific environmental parameter changes on the energy storage component's performance; the mode correlation feature is the key feature extracted from historical degradation data related to the performance degradation of the energy storage component, which reflects the degradation mode and trend of the energy storage component under different environmental conditions; the recurrent neural network is used to iteratively compensate for the phase shift in the energy storage performance degradation feature map to improve the prediction accuracy; the confidence parameter is used to measure the reliability degree of the prediction result in the energy storage performance degradation feature map. By updating the confidence parameter, the prediction accuracy and credibility of the map are dynamically adjusted.

[0043] By activating the reference load within a preset period. Specifically, the reference load is activated every 10 minutes (such as 0.5C charge and discharge), and the transient response characteristics of the energy storage component are measured. The transient response characteristics can reflect the dynamic performance changes of the energy storage component under different environmental conditions, such as voltage drop and power output stability; according to the transient response characteristics of the energy storage component, an environmental sensitivity matrix is set up. This matrix establishes a direct connection between environmental conditions and energy storage performance by quantifying the influence of different environmental parameters on the energy storage component's performance. For example, a certain probability of temperature change will cause an increase in the internal resistance of the energy storage component, and a certain probability of humidity change will affect the insulation performance of the energy storage component. The environmental sensitivity matrix identifies the environmental parameters that have the most significant impact on the energy storage component's performance.

[0044] Based on the environmental sensitivity matrix, mode correlation features are extracted from historical degradation data. These features reflect the degradation mode and trend of the energy storage component under different environmental conditions. By using the recurrent neural network to iteratively compensate for the phase shift, the prediction result in the energy storage performance degradation feature map can be dynamically adjusted to make it closer to the actual performance change. The confidence parameter of the energy storage performance degradation feature map is updated to improve the prediction accuracy and reliability of the map; by dynamically monitoring and analyzing the transient response characteristics of the energy storage component and combining historical degradation data, the prediction accuracy of the energy storage performance degradation feature map is optimized. By introducing the environmental sensitivity matrix and the recurrent neural network, the performance prediction model of the energy storage component can be adjusted in real time to make it more adaptable to complex environmental changes. This dynamic optimization mechanism improves the accuracy of the energy storage component performance prediction.

[0045] Furthermore, taking the first energy storage optimization pointer as the dominant optimization direction and combining the auxiliary optimization directions of the second and third energy storage optimization pointers, the method of the present application further includes: Comparing the change in the capacity attenuation gradient before and after optimization to evaluate the performance improvement coefficient; based on the performance improvement coefficient, monitoring the execution deviation of the first energy storage efficiency compensation mechanism to generate a thermal management effectiveness evaluation matrix; and feeding back the performance improvement coefficient and the thermal management effectiveness evaluation matrix to the non-linear state estimation model for switching and adjustment of the dominant optimization direction.

[0046] Specifically, the change in the capacity attenuation gradient refers to the change in the capacity attenuation rate of the energy storage component, that is, the capacity loss rate per unit time, such as decreasing from 0.5% / cycle to 0.3% / cycle. By comparing the change in the capacity attenuation gradient before and after optimization, the actual impact of the optimization measures on the performance of the energy storage component is quantified; the performance improvement coefficient is a quantitative indicator used to measure the degree of improvement in the performance of the energy storage component by the optimization measures, which is calculated by comparing the performance parameters (such as capacity attenuation gradient, efficiency) before and after optimization, reflecting the significance of the optimization effect; the execution deviation refers to the difference between the actual operation of the first energy storage efficiency compensation mechanism and the expected target, which is caused by changes in environmental conditions, model errors, or system dynamic characteristics; the thermal management effectiveness evaluation matrix is a matrix used to quantify the effect of the thermal management strategy. By evaluating the actual impact of the thermal management measures on the performance of the energy storage component, relevant effectiveness indicators are generated, and the thermal management effectiveness evaluation matrix can reflect the effectiveness and adaptability of the thermal management strategy; the non-linear state estimation model is a mathematical model for dynamic system modeling and state estimation, which can handle the non-linear characteristics in the system and is used to adjust the dominant direction of the optimization strategy according to the feedback information to achieve dynamic optimization.

[0047] By comparing the change in the capacity attenuation gradient before and after optimization, the performance improvement coefficient is calculated. By quantifying the actual improvement effect of the optimization measures on the performance of the energy storage component, a basis is provided for subsequent adjustment of the optimization strategy. The calculation of the performance improvement coefficient is based on the change in the capacity attenuation rate, efficiency, or other performance indicators of the energy storage component before and after optimization; based on the performance improvement coefficient, the execution deviation of the first energy storage efficiency compensation mechanism is monitored. By evaluating the difference between the actual operation effect of the compensation mechanism and the expected target, a thermal management effectiveness evaluation matrix is generated, which can reflect the effectiveness and adaptability of the thermal management strategy under the current environmental conditions.

[0048] Feedback the performance improvement coefficient and the thermal management efficiency evaluation matrix to the nonlinear state estimation model for switching and adjusting the dominant optimization direction. This process ensures that the performance of the energy storage components is always in the optimal state under different environmental conditions by dynamically adjusting the dominant direction of the optimization strategy. It has been verified that in a high-temperature environment (temperature ≥ 40°C), the battery capacity decay gradient is 0.8% / week. After optimization by the first energy storage efficiency compensation mechanism, the capacity decay gradient is reduced to 0.5% / week, and the performance improvement coefficient is 37.5%. The thermal management efficiency evaluation matrix shows that the execution deviation of the first energy storage efficiency compensation mechanism is ±5%, indicating that the optimization strategy has high stability in a high-temperature environment.

[0049] When the efficiency of the thermal management strategy is insufficient, switch the optimization direction and preferentially adjust the charge and discharge strategy or the load balancing scheme to optimize the overall performance. Through the dynamic monitoring and feedback mechanism, the adaptive adjustment of the energy storage component optimization strategy is realized. By quantifying the optimization effect, monitoring the execution deviation, and dynamically adjusting the optimization direction, it can ensure that the performance of the energy storage components is always in the best state under complex environmental conditions, thereby improving the overall efficiency and reliability of the energy storage system.

[0050] In summary, the beneficial effects of the embodiments of this application are as follows: By adopting an energy storage component-based approach to determine the environmental parameter set, analyze the changes in energy storage efficiency and the trend of energy storage capacity decay under different environments, configure multiple energy storage adaptation paths, each of which has a capacity decay mark and is associated and coupled with the environmental parameter set for analysis, and construct a characteristic map of energy storage performance degradation; introduce the historical degradation data and environmental parameter correlation matrix to correct the phase shift of the energy storage performance degradation characteristic map, predict the health state index of the energy storage component, and output the remaining available capacity decay rate, which is input into the dynamic optimization engine to determine the adaptive optimization instruction set; use the optimization instruction set to execute the energy storage management of the energy storage components under different environments. This application provides a method and system for adapting and optimizing energy storage performance in multiple environments, achieving the technical effects of real-time collecting and analyzing environmental parameters, configuring multiple energy storage adaptation paths, automatically adjusting the working state according to different environments, improving the environmental adaptability of energy storage components, introducing the historical degradation data and environmental parameter correlation matrix, predicting the health state index and the remaining available capacity decay rate of energy storage components, and further optimizing energy storage performance and enhancing the stability of the power grid.

[0051] Embodiment 2 Based on the same inventive concept as the method for adapting and optimizing energy storage performance in multiple environments in the foregoing embodiment, as Figure 2 shown, the embodiments of this application provide a system for adapting and optimizing energy storage performance in multiple environments, wherein the system includes: The data acquisition module M100 is used to determine an environmental parameter set based on an energy storage component. The environmental parameter set collected by the multi-modal environmental perception array in real time includes temperature, humidity, and air pressure.

[0052] The configuration module M200 is used to analyze the change of energy storage efficiency and the attenuation trend of energy storage capacity under different environments according to the environmental parameter set, and configure multiple energy storage adaptation paths. Each energy storage adaptation path has a capacity attenuation mark.

[0053] The coupling analysis module M300 is used to perform correlation coupling analysis with the environmental parameter set through the multiple energy storage adaptation paths to construct a characteristic map of energy storage performance degradation.

[0054] The offset correction module M400 is used to introduce a historical degradation data and environmental parameter correlation matrix, correct the phase offset of the energy storage performance degradation characteristic map, predict the health state index of the energy storage component using random forest regression, and output the remaining available capacity attenuation rate.

[0055] The input module M500 is used to input the health state index and the remaining available capacity attenuation rate into a dynamic optimization engine to determine an adaptive optimization instruction set, including charge and discharge rate adjustment parameters, temperature compensation strategies, and load balancing schemes.

[0056] The energy storage management module M600 is used to perform energy storage management of the energy storage component under different environments according to the optimization instruction set.

[0057] Furthermore, the configuration module M200 is used to execute the following method: Based on the environmental parameter set, combining the thermal management characteristics, moisture-proof characteristics, and pressure adaptability of the energy storage component, configure a first energy storage optimization pointer, a second energy storage optimization pointer, and a third energy storage optimization pointer; perform one-way competitive iteration on the first energy storage optimization pointer, the second energy storage optimization pointer, and the third energy storage optimization pointer according to the energy storage capacity attenuation trend.

[0058] Furthermore, the configuration module M200 is also used to execute the following method: Identify multiple temperature-sensitive regions through a preset temperature change scenario. Each temperature-sensitive region has at least one temperature fluctuation point; based on the first energy storage optimization pointer, combine the multiple temperature-sensitive regions to configure a temperature adaptability index group associated with the first energy storage optimization pointer.

[0059] Furthermore, the configuration module M200 is also used to execute the following method: Based on the temperature adaptability index group, evaluate the influence weight of temperature fluctuation on the energy storage efficiency, and determine the priority of the multiple temperature-sensitive regions; based on the priority, establish a first energy storage efficiency compensation mechanism, and the first energy storage efficiency compensation mechanism is used to iteratively constrain the energy storage adaptation paths in different environments.

[0060] Further, the configuration module M200 is further configured to execute the following method: Based on the priority, configure a first set of energy storage efficiency compensation parameters, and the first set of energy storage efficiency compensation parameters includes a temperature compensation coefficient, a thermal management adjustment factor, and a temperature fluctuation tolerance threshold; the first energy storage efficiency compensation mechanism is used to, in the one-way competitive iteration process, according to the first set of energy storage efficiency compensation parameters, take the first energy storage optimization pointer as the dominant optimization direction, and combine the auxiliary optimization directions of the second energy storage optimization pointer and the third energy storage optimization pointer to perform multi-path collaborative optimization.

[0061] Further, the configuration module M200 is further configured to execute the following method: Through a preset humidity change scenario, identify multiple humidity-sensitive regions, where each humidity-sensitive region has at least one humidity fluctuation point; based on the second energy storage optimization pointer, in combination with the multiple humidity-sensitive regions, configure a humidity adaptability index group associated with the second energy storage optimization pointer; based on the humidity adaptability index group, establish a second energy storage efficiency compensation mechanism, and the second energy storage efficiency compensation mechanism is used to assist the first energy storage optimization pointer in optimizing the energy storage adaptation path in the one-way competitive iteration process.

[0062] Further, the coupling analysis module M300 is further configured to execute the following method: Based on the energy storage components, set three-dimensional grid units, and the size of the three-dimensional grid units does not exceed 1 / 3 of the heat conduction characteristic length; fuse the coupling weights of temperature, humidity, and air pressure in the three-dimensional grid units, establish a non-steady heat transfer-electrochemical coupling mapping parameter, and configure the energy storage performance degradation characteristic map.

[0063] Further, the coupling analysis module M300 is further configured to execute the following method: Activate the reference load at every preset period, measure the transient response characteristics of the energy storage components; according to the transient response characteristics of the energy storage components, set the environmental sensitivity matrix; based on the environmental sensitivity matrix, extract the pattern correlation features in the historical degradation data, and use a recurrent neural network to iteratively compensate for the phase shift to update the confidence parameters of the energy storage performance degradation characteristic map.

[0064] Further, the configuration module M200 is further configured to execute the following method: Compare the changes in the capacity attenuation gradient before and after optimization to evaluate the performance improvement coefficient; based on the performance improvement coefficient, monitor the execution deviation of the first energy storage efficiency compensation mechanism and generate a thermal management efficiency evaluation matrix; feedback the performance improvement coefficient and the thermal management efficiency evaluation matrix to the nonlinear state estimation model to perform switching adjustment of the dominant optimization direction.

[0065] In summary, any step can be stored as computer instructions or programs in an unrestricted computer memory and can be called and recognized by an unrestricted computer processor, without any additional restrictions here.

[0066] Furthermore, the above technical solutions only represent the preferred technical solutions of the technical solutions of the embodiments of the present application. Some changes that those skilled in the art may make to some parts thereof all reflect the principles of the novel embodiments of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application.

Claims

1. Method for optimizing energy storage performance adaptability in multiple environments, characterized in that, The method includes: Based on the energy storage component, determine the environmental parameter set. The environmental parameter set collected by the multi-modal environmental perception array in real time includes temperature, humidity, and air pressure. According to the environmental parameter set, analyze the changes in energy storage efficiency and the trend of energy storage capacity attenuation in different environments, and configure multiple energy storage adaptation paths. Each energy storage adaptation path has a capacity attenuation mark. Through the multiple energy storage adaptation paths, conduct correlation coupling analysis with the environmental parameter set to construct a characteristic map of energy storage performance degradation. Introduce the historical degradation data and environmental parameter correlation matrix, correct the phase shift of the characteristic map of energy storage performance degradation, use random forest regression to predict the health state index of the energy storage component, and output the remaining available capacity attenuation rate. Input the health state index and the remaining available capacity attenuation rate into the dynamic optimization engine to determine the adaptive optimization instruction set, including charge and discharge rate adjustment parameters, temperature compensation strategies, and load balancing schemes. Execute the energy storage management of the energy storage component in different environments according to the optimization instruction set.

2. The method for optimizing the adaptability of energy storage performance in multiple environments according to claim 1, wherein According to the environmental parameter set, analyze the changes in energy storage efficiency and the trend of energy storage capacity attenuation in different environments, and configure multiple energy storage adaptation paths. The method includes: Based on the environmental parameter set, combine the thermal management characteristics, moisture-proof characteristics, and pressure adaptability of the energy storage component to configure the first energy storage optimization pointer, the second energy storage optimization pointer, and the third energy storage optimization pointer. According to the trend of energy storage capacity attenuation, perform one-way competitive iteration on the first energy storage optimization pointer, the second energy storage optimization pointer, and the third energy storage optimization pointer.

3. The method for optimizing the adaptability of energy storage performance in multiple environments according to claim 2, characterized in that, Perform one-way competitive iteration on the first energy storage optimization pointer. The method includes: Through a preset temperature change scenario, identify multiple temperature-sensitive regions. Each temperature-sensitive region has at least one temperature fluctuation point. Based on the first energy storage optimization pointer, combine the multiple temperature-sensitive regions to configure a temperature adaptability index group associated with the first energy storage optimization pointer.

4. The method for optimizing the adaptability of energy storage performance in multiple environments according to claim 3, wherein Based on the temperature adaptability index group, evaluate the influence weight of temperature fluctuation on energy storage efficiency and determine the priority of the multiple temperature-sensitive regions. Based on the priority, establish a first energy storage efficiency compensation mechanism. The first energy storage efficiency compensation mechanism is used to perform iterative constraints on the energy storage adaptation paths in different environments.

5. The method for optimizing the adaptability of energy storage performance in multiple environments according to claim 4, wherein, Based on the priority, establish a first energy storage efficiency compensation mechanism. The method includes: Based on the priority, configure a first energy storage efficiency compensation parameter set. The first energy storage efficiency compensation parameter set includes a temperature compensation coefficient, a thermal management adjustment factor, and a temperature fluctuation tolerance threshold. The first energy storage efficiency compensation mechanism is used to, during the one-way competitive iteration process, use the first energy storage optimization pointer as the dominant optimization direction according to the first energy storage efficiency compensation parameter set, and combine the auxiliary optimization directions of the second energy storage optimization pointer and the third energy storage optimization pointer to perform multi-path collaborative optimization.

6. The method for optimizing the adaptability of energy storage performance in multiple environments according to claim 5, characterized in that Combine the auxiliary optimization directions of the second energy storage optimization pointer and the third energy storage optimization pointer to perform multi-path collaborative optimization. The method further includes: Through a preset humidity change scenario, identify multiple humidity-sensitive regions. Each humidity-sensitive region has at least one humidity fluctuation point. Based on the second energy storage optimization pointer and in combination with the multiple humidity-sensitive regions, configure a humidity adaptability index group associated with the second energy storage optimization pointer; Based on the humidity adaptability index group, establish a second energy storage efficiency compensation mechanism, which is used to assist the first energy storage optimization pointer in optimizing the energy storage adaptation path during the one-way competition iteration process.

7. The method for optimizing the adaptability of energy storage performance in multiple environments according to claim 6, wherein Construct a characteristic map of energy storage performance degradation, and the method includes: Based on the energy storage components, set three-dimensional grid cells, and the size of the three-dimensional grid cells does not exceed 1 / 3 of the heat conduction characteristic length; Fuse the coupling weights of temperature, humidity, and air pressure in the three-dimensional grid cells, establish a non-steady heat transfer-electrochemical coupling mapping parameter, and configure the characteristic map of energy storage performance degradation.

8. The method for optimizing the adaptability of energy storage performance in multiple environments according to claim 7, wherein Establish a non-steady heat transfer-electrochemical coupling mapping parameter and configure the characteristic map of energy storage performance degradation. The method further includes: Activate the reference load at preset intervals and measure the transient response characteristics of the energy storage components; Set an environmental sensitivity matrix according to the transient response characteristics of the energy storage components; Based on the environmental sensitivity matrix, extract the pattern correlation features in the historical degradation data, and use a recurrent neural network to iteratively compensate for the phase shift to update the confidence parameter of the characteristic map of energy storage performance degradation.

9. The method for optimizing the adaptability of energy storage performance in multiple environments according to claim 5, characterized in that, Take the first energy storage optimization pointer as the main optimization direction and combine the auxiliary optimization directions of the second energy storage optimization pointer and the third energy storage optimization pointer. The method further includes: Compare the change in the capacity decay gradient before and after optimization and evaluate the performance improvement coefficient; Based on the performance improvement coefficient, monitor the execution deviation of the first energy storage efficiency compensation mechanism and generate a thermal management efficiency evaluation matrix; Feed back the performance improvement coefficient and the thermal management efficiency evaluation matrix to the non-linear state estimation model for switching adjustment of the main optimization direction.

10. Energy storage performance adaptability optimization system in multiple environments, characterized in that, A system for implementing the multi-environment energy storage performance adaptability optimization method according to any one of claims 1-9, the system includes: A data acquisition module for determining an environmental parameter set based on the energy storage components. The environmental parameter set collected by the multi-modal environmental perception array includes temperature, humidity, and air pressure; A configuration module for analyzing the energy storage efficiency change and the energy storage capacity decay trend under different environments according to the environmental parameter set, configuring multiple energy storage adaptation paths, and each energy storage adaptation path has a capacity decay mark; A coupling analysis module for performing associated coupling analysis between the multiple energy storage adaptation paths and the environmental parameter set to construct a characteristic map of energy storage performance degradation; An offset correction module for introducing a historical degradation data and environmental parameter correlation matrix to correct the phase shift of the characteristic map of energy storage performance degradation, predicting the health state index of the energy storage components using random forest regression, and outputting the remaining available capacity decay rate; An input module for inputting the health state index and the remaining available capacity decay rate into a dynamic optimization engine to determine an adaptability optimization instruction set, including charge and discharge rate adjustment parameters, temperature compensation strategies, and load balancing schemes; An energy storage management module for performing energy storage management of the energy storage components under different environments according to the optimization instruction set.

Images