Battery management system enhancement method and system based on artificial intelligence

Abstract

The invention discloses a battery management system enhancement method and system based on artificial intelligence. The method comprises heterogeneous data fusion acquisition, dynamic digital twinborn modeling, dynamic charging and discharging enhancement, multi-dimensional security situation awareness enhancement and battery management system enhancement. The invention relates to the technical field of battery management enhancement, and adopts a comprehensive battery management system management enhancement method combining dynamic digital twinborn modeling optimization, dynamic charging and discharging strategy optimization and multi-dimensional security situation awareness optimization. The dynamism and the prediction precision of the battery management system and the adjustment efficiency of the overall strategy are improved; carrying out dynamic digital twinning modeling by adopting a four-stage digital twinning integrated model; performing dynamic charging and discharging enhancement by combining a reinforcement learning method of double-delay depth deterministic strategy gradient and reward function updating; and carrying out multi-dimensional security situation awareness enhancement by adopting a space-time diagram convolutional network combined with a battery microstructure evolution graph.

Description

Technical Field

[0001] The present invention relates to the technical field of battery management enhancement, specifically to a method and system for enhancing a battery management system based on artificial intelligence. Background Art

[0002] The method and system for enhancing a battery management system based on artificial intelligence optimize the management and monitoring of batteries by combining advanced artificial intelligence technologies. Its core function is to enhance the overall performance of the battery system. The system can effectively improve battery usage efficiency, extend battery life, predict potential risks and adjust the battery working state in real time to ensure the safety and reliability of the battery, and is widely used in fields such as electric vehicles and energy storage devices.

[0003] However, in existing battery management systems, traditional systems mainly monitor voltage, temperature and current and perform charge and discharge control to achieve balanced management and safety optimization. However, the existing technical solutions are not accurate enough in predicting battery aging. At the same time, the adaptability to dynamic working conditions is poor, it is difficult to cope with the changing battery working environment, and the charge and discharge strategy is not efficient enough. As a result, there are technical problems that the existing battery management systems need to be enhanced and optimized in terms of intelligence.

[0004] In the existing dynamic digital twin modeling process, there are technical problems that traditional battery digital twin modeling combines less of the internal and external conditions of the battery and it is difficult to fully reflect the state changes and health state changes of the battery, resulting in the fact that the modeling at both the macroscopic and microscopic levels is difficult to reflect the dynamics of the battery.

[0005] In the existing dynamic charge and discharge enhancement methods, there are technical problems that the intelligence and dynamics of the existing battery charge and discharge adjustment strategies combined with dynamic digital modeling are also insufficient. At the same time, this further leads to the situation that the change of the battery working environment is faster than the adjustment strategy of the battery management.

[0006] In the existing multi-dimensional security situation awareness enhancement methods, there are technical problems that most existing battery security management systems rely on traditional prediction methods, such as predicting the life based on data during the battery charge and discharge process. However, many traditional methods cannot effectively capture the changes at the microscopic level of the battery and the early signals of faults, and these systems lack the ability to dynamically and intelligently perceive and analyze the microscopic changes in the entire life cycle of the battery. Summary of the Invention

[0007] In view of the above situation, to overcome the deficiencies of the prior art, the present invention provides a method and system for enhancing a battery management system based on artificial intelligence. In the existing battery management system, the traditional system mainly monitors voltage, temperature and current and conducts charge and discharge control to achieve balanced management and safety optimization. However, the existing technical solutions are not accurate enough in predicting battery aging. At the same time, the adaptability to dynamic working conditions is poor, making it difficult to cope with the changing battery working environment, and the charge and discharge strategies are not efficient enough. As a result, the existing battery management system needs to be enhanced and optimized in terms of intelligence. This solution creatively adopts a comprehensive battery management system management enhancement method that combines dynamic digital twin modeling optimization, dynamic charge and discharge strategy optimization, and multi-dimensional safety situation awareness optimization. Through enhancements and optimizations in multiple dimensions, the dynamic performance, prediction accuracy, and overall strategy adjustment efficiency of the battery management system are improved. In the existing dynamic digital twin modeling process, there is a problem that the traditional battery digital twin modeling combines less of the internal and external conditions of the battery, making it difficult to fully reflect the state changes and health state changes of the battery, resulting in the inability of the macro and micro-level modeling to reflect the dynamics of the battery. This solution creatively adopts a four-level digital twin integration model for dynamic digital twin modeling, and by introducing multi-scale coupling in electronic structure calculations, introducing non-uniform potential distribution correction in the phase field model, and introducing the double-layer effect and dynamic equivalent resistance calculation from the perspectives of single-cell and system integration, the dynamics of the battery digital twin model are improved, thus forming a complete digital twin system that is adaptive and dynamically adjustable, which helps to achieve subsequent battery health management, charge and discharge optimization, and fault prediction. In the existing dynamic charge and discharge enhancement method, there is a problem that the intelligence and dynamics of the existing method for adjusting the battery charge and discharge strategy in combination with dynamic digital modeling are also insufficient. At the same time, this further leads to the situation that the change of the battery working environment is faster than the adjustment strategy of the battery management. This solution creatively combines the reinforcement learning method of double-delay deep deterministic policy gradient and reward function update for dynamic charge and discharge enhancement. Through the double-delay update strategy combined with the improvement of the fine reward function, the intelligence and dynamics of the battery charge and discharge adjustment strategy are improved from bottom to top, which not only helps to extend the battery life, improve the charge and discharge efficiency, but also ensures that the battery works within a safe range, improving the overall performance and reliability of the battery system and the battery management system.In the existing multi-dimensional security situation awareness enhancement methods, most of the existing battery safety management systems rely on traditional prediction methods, such as predicting the battery life based on the data during the battery charging and discharging process. However, many traditional methods cannot effectively capture the changes at the micro level of the battery and the early signals of faults, and these systems lack the ability to dynamically and intelligently perceive and analyze the micro changes in the entire life cycle of the battery. In view of this technical problem, this solution creatively uses a spatio-temporal graph convolutional network combined with the battery microstructure evolution map to enhance multi-dimensional security situation awareness, and through dynamic monitoring and multi-dimensional comprehensive analysis, provides more refined, comprehensive and dynamic security monitoring and management capabilities.

[0008] The technical solution adopted by the present invention is as follows: The method for enhancing a battery management system based on artificial intelligence provided by the present invention includes the following steps:

[0009] Step S1: Heterogeneous data fusion acquisition;

[0010] Step S2: Dynamic digital twin modeling;

[0011] Step S3: Dynamic charge and discharge enhancement;

[0012] Step S4: Multi-dimensional security situation awareness enhancement;

[0013] Step S5: Battery management system enhancement.

[0014] Further, in step S1, the heterogeneous data fusion acquisition is used to collect the original data related to the battery state required for the analysis of the battery management system. Specifically, through heterogeneous data fusion acquisition, the original data set for battery state management is collected, and preliminary optimization and preprocessing are performed to obtain the enhanced data set for the battery management system;

[0015] The heterogeneous data fusion acquisition specifically performs battery state data acquisition by deploying a sensor array and collecting dynamic characteristics of electrochemical impedance spectroscopy;

[0016] The original data set for battery state management includes battery voltage data, current data, temperature data, electrochemical data, mechanical support data, solid electrolyte interface film evolution data, and multi-physical field fusion data;

[0017] The steps of the preliminary optimization and preprocessing include data denoising, missing value processing, outlier correction, data standardization, time series data smoothing, and feature selection. By performing the preliminary optimization and preprocessing on the original data set for battery state management, the enhanced data set for the battery management system is obtained;

[0018] The enhanced dataset of the battery management system includes optimized timing data, derived feature data, multi-physical field fusion data, fusion metric data, evolutionary feature data, labeled data, and synchronized multi-dimensional data.

[0019] Further, in step S2, the dynamic digital twin modeling is used to construct a four-level digital twin model for battery state management. Specifically, based on the enhanced dataset of the battery management system, a four-level resolution twin model construction method is adopted for dynamic digital twin modeling to obtain an enhanced digital twin model for battery management.

[0020] The enhanced dataset of the battery management system includes a quantum chemical scale model, an electrode particle scale model, a single battery scale model, and a system integration scale model.

[0021] The quantum chemical scale model is used to introduce a multi-scale coupling strategy for comprehensive modeling of electron states and battery internal and external environment parameters.

[0022] The electrode particle scale model is used to introduce a non-uniform TV distribution correction for modeling the spatial variation of electric potential within the electrode particles and to improve the traditional phase field model.

[0023] The single battery scale model is used to introduce the double layer effect for modeling and improving the influence of the double layer on the current distribution in the traditional motor model.

[0024] The system integration scale model is used to introduce a dynamic resistance correction method based on state estimation for modeling and improving the dynamic adjustment of the equivalent resistance model.

[0025] The steps of adopting the four-level resolution twin model construction method for dynamic digital twin modeling to obtain an enhanced digital twin model for battery management include:

[0026] Step S21: Electron structure modeling, which is used to construct a quantum chemical scale model. Specifically, by introducing a multi-scale coupling strategy for electron structure calculation, a reference value of the electron structure Hamiltonian is obtained.

[0027] Step S22: Particle electrochemical reaction modeling, which is used to construct an electrode particle scale model. Specifically, by introducing an electric potential correction coefficient into the standard phase field model for particle electrochemical reaction modeling, reference values of ion diffusion and reaction rate are obtained.

[0028] Step S23: Electrode current density modeling, which is used to construct a single battery scale model. Specifically, by introducing a double layer effect correction into the standard porous motor model for electrode current density modeling, an improved modeling model of electrode current density is obtained.

[0029] Step S24: Battery equivalent circuit modeling, which is used to construct a system integration scale model. Specifically, in the standard equivalent circuit model, the resistance is regarded as a dynamic variable and the resistance is dynamically corrected to obtain a battery equivalent circuit modeling model. The calculation formula is as follows:

[0030] ;

[0031] In the formula, V OC is the open-circuit voltage value, I is the battery current value, R eq is the equivalent resistance value, V(t) is the battery operating voltage value,

[0032] is the battery equivalent circuit modeling model. By dynamically correcting the equivalent resistance value R eq , a system integration scale model is constructed. R eq (t) is the equivalent resistance value regarded as a dynamic variable, and R1 is the base resistance, which is used to represent the resistance value of the battery under normal operating conditions. is the dynamic resistance change term, SOC(t) is the state of charge of the battery, and SOH(t) is the state of health of the battery. is the battery temperature state;

[0033] Step S25: Four-level integration, which is used to construct a four-level resolution twin model. Specifically, through the electronic structure modeling, the particle electrochemical reaction modeling, the electrode current density modeling, and the battery equivalent circuit modeling, a four-level digital twin model integration is carried out to obtain a battery management enhanced digital twin model.

[0034] Further, in step S3, the dynamic charge and discharge enhancement is used to dynamically enhance the battery charge and discharge management. Specifically, based on the battery management system enhanced dataset and the battery management enhanced digital twin model, a reinforcement learning method combining double-delay deep deterministic policy gradient and reward function update is adopted to perform dynamic charge and discharge enhancement to obtain a dynamic charge and discharge enhancement reference policy, including the following steps:

[0035] Step S31: Construct a double-delay reinforcement learning framework. Specifically, construct a standard reinforcement learning environment parameter model, and adopt a deep deterministic gradient policy to combine the value function and the policy function to set up the reinforcement learning basic framework, and update the parameters of the value network and the policy network by constructing a double-delay update policy;

[0036] Step S32: Dynamic charge and discharge enhancement reward improvement. Specifically, by designing a multi-dimensional reward function, comprehensive integration is carried out from the aspects of battery life, efficiency, and safety to perform dynamic charge and discharge enhancement reward improvement to obtain a dynamic charge and discharge enhancement reward function, and based on the dynamic charge and discharge enhancement reward function, reinforcement learning training is carried out;

[0037] The calculation formula of the multi-dimensional reward function is as follows:

[0038] ;

[0039] In the formula, R w is the multi-dimensional reward function, which is used as the reward function of the double-delay reinforcement learning framework described in step S31, is the battery life weight, is the battery life gain term, is the charge-discharge efficiency weight, is the charge-discharge efficiency term, is the safety factor weight, and S is the safety factor term;

[0040] Step S33: Iteratively update the dynamic charge-discharge strategy. Specifically, by applying the multi-dimensional reward function to the double-delay reinforcement learning framework, iteratively update the dynamic charge-discharge strategy to obtain iteratively updated dynamic charge-discharge strategy data;

[0041] Step S34: Enhance the dynamic charge-discharge. Specifically, through the double-delay reinforcement learning framework, the dynamic charge-discharge enhancement reward improvement, and the iterative update of the dynamic charge-discharge strategy, perform iterative training of the reinforcement learning of the dynamic charge-discharge enhancement model to obtain the dynamic charge-discharge enhancement model Model DH and by using the dynamic charge-discharge enhancement model Model DH , based on the battery management system enhancement dataset and the battery management enhanced digital twin model, perform dynamic charge-discharge enhancement to obtain a dynamic charge-discharge enhancement reference strategy;

[0042] The dynamic charge-discharge enhancement reference strategy specifically includes battery health state data, charge-discharge control data, and optimized charge-discharge data.

[0043] Furthermore, in step S4, the multi-dimensional safety situation awareness enhancement is used to perform multi-dimensional enhancement on the battery safety situation awareness management. Specifically, based on the battery management system enhancement dataset and the battery management enhanced digital twin model, adopt a spatio-temporal graph convolutional network combined with the battery microstructure evolution map to perform multi-dimensional safety situation awareness enhancement to obtain multi-dimensional safety situation awareness reference data, including the following steps:

[0044] Step S41: Construct a spatio-temporal graph convolutional basic network for capturing spatio-temporal dependencies and basic features in the battery microstructure. Specifically, by constructing battery microstructure graph data and constructing a standard spatio-temporal graph convolutional network as the basic network for multi-dimensional safety situation awareness enhancement;

[0045] Step S42: Construct an evolution map of the battery microstructure for modeling the evolution process of the internal structure of the battery and supporting dynamic prediction. Specifically, construct a basic model for the evolution of the battery microstructure state, and based on the basic model for the evolution of the battery microstructure state, perform evolution predictions of battery micro-deformation, lithium plating, and the growth of the solid electrolyte interface film;

[0046] Step S43: Model the early fault propagation for detecting microstructural changes and implementing early warning predictions of battery faults. Specifically, through the coupling effect of current, temperature, and charge state in the battery, model the early fault propagation, and through the modeling of the early fault propagation, perform early warning predictions of battery faults;

[0047] Step S44: Train the multi-dimensional security situation awareness enhancement model. Specifically, through the spatio-temporal graph convolutional basic network, the evolution map of the battery microstructure, and the modeling of the early fault propagation, train the multi-dimensional security situation awareness enhancement model to obtain the multi-dimensional security situation awareness enhancement model Model EH ;

[0048] Step S45: Enhance the multi-dimensional security situation awareness. Specifically, use the multi-dimensional security situation awareness enhancement model Model EH , and based on the enhanced dataset of the battery management system and the enhanced digital twin model of the battery management, perform multi-dimensional security situation awareness enhancement to obtain multi-dimensional security situation awareness reference data.

[0049] The multi-dimensional security situation awareness reference data specifically includes battery prediction parameters, fault propagation prediction rates, and battery safety state change prediction reference data.

[0050] Furthermore, in step S5, the enhancement of the battery management system is used to comprehensively enhance the battery management system by combining battery charge and discharge management and security situation management. Specifically, construct a basic mathematical model required for enhancing the battery management system through dynamic digital twin modeling, and through the dynamic charge and discharge enhancement and the multi-dimensional security situation awareness enhancement, perform comprehensive enhancement of the battery management system to obtain dynamic charge and discharge enhancement reference strategies and multi-dimensional security situation awareness reference data, and through combining the dynamic charge and discharge enhancement reference strategies and multi-dimensional security situation awareness reference data, obtain battery management system comprehensive enhancement reference data.

[0051] The battery management system enhancement system based on artificial intelligence provided by the present invention includes a quantum sensing module, a digital twin module, a dynamic optimization module, a security situation awareness module, and a battery management system enhancement module;

[0052] The quantum sensing module is used for heterogeneous data fusion acquisition. Through heterogeneous data fusion acquisition, an enhanced dataset of the battery management system is obtained, and the enhanced dataset of the battery management system is sent to the digital twin module, the dynamic optimization module, and the security situation awareness module;

[0053] The digital twin module is used for dynamic digital twin modeling. Through dynamic digital twin modeling, an enhanced digital twin model of the battery management is obtained, and the enhanced digital twin model of the battery management is applied to the dynamic optimization module and the security situation awareness module;

[0054] The dynamic optimization module is used for dynamic charge and discharge enhancement. Through dynamic charge and discharge enhancement, a reference strategy for dynamic charge and discharge enhancement is obtained, and the reference strategy for dynamic charge and discharge enhancement is sent to the enhanced module of the battery management system;

[0055] The security situation awareness module is used for multi-dimensional security situation awareness enhancement. Through multi-dimensional security situation awareness enhancement, reference data for multi-dimensional security situation awareness is obtained, and the reference data for multi-dimensional security situation awareness is sent to the enhanced module of the battery management system;

[0056] The enhanced module of the battery management system is used for battery management system enhancement. Through battery management system enhancement, comprehensive reference data for the battery management system is obtained.

[0057] The beneficial effects achieved by the present invention using the above solution are as follows:

[0058] (1) In the existing battery management system, the traditional system mainly monitors voltage, temperature, and current and performs charge and discharge control to achieve balanced management and safety optimization. However, the existing technical solutions are not accurate enough in predicting battery aging. At the same time, the adaptability to dynamic working conditions is poor, it is difficult to cope with the changing battery working environment, and the charge and discharge strategy is not efficient enough. As a result, the existing battery management system needs to be enhanced and optimized in terms of intelligence. This solution creatively adopts a comprehensive battery management system management enhancement method that combines dynamic digital twin modeling optimization, dynamic charge and discharge strategy optimization, and multi-dimensional security situation awareness optimization. Through enhancement and optimization in multiple dimensions, the dynamic performance, prediction accuracy, and overall strategy adjustment efficiency of the battery management system are improved;

[0059] (2)In view of the technical problem that in the existing dynamic digital twin modeling process, the traditional battery digital twin modeling combines less of the internal and external conditions of the battery, making it difficult to fully reflect the state changes and health state changes of the battery, resulting in the inability of both macro and micro-level modeling to reflect the dynamics of the battery, this solution creatively adopts a four-level digital twin integration model for dynamic digital twin modeling. By introducing multi-scale coupling in electronic structure calculations, introducing non-uniform electric potential distribution correction in the phase field model, and introducing the double-layer effect and dynamic equivalent resistance calculation methods from the perspectives of single cells and system integration, the dynamics of the battery digital twin model are improved, thus forming a complete digital twin system that is adaptive and dynamically adjustable, which helps to achieve subsequent battery health management, charge and discharge optimization, and fault prediction;

[0060] (3)In view of the technical problem that in the existing dynamic charge and discharge enhancement methods, the intelligence and dynamics of the battery charge and discharge adjustment strategy combined with dynamic digital modeling are insufficient. At the same time, this further leads to the situation that the change of the battery working environment is faster than the adjustment strategy of the battery management. This solution creatively combines the reinforcement learning method of double-delay deep deterministic policy gradient and reward function update for dynamic charge and discharge enhancement. Through the double-delay update strategy combined with the improvement of the fine reward function, the intelligence and dynamics of the battery charge and discharge adjustment strategy are improved from bottom to top. This not only helps to extend the battery life, improve the charge and discharge efficiency, but also ensures that the battery operates within a safe range, improving the overall performance and reliability of the battery system and the battery management system;

[0061] (4)In view of the technical problem that in the existing multi-dimensional security situation awareness enhancement methods, most of the existing battery security management systems rely on traditional prediction methods, such as predicting the life based on the data during the battery charge and discharge process. However, many traditional methods cannot effectively capture the changes at the micro level of the battery and the early signals of faults, and these systems lack the ability to dynamically and intelligently perceive and analyze the micro changes in the entire life cycle of the battery. This solution creatively adopts a spatio-temporal graph convolutional network combined with the battery microstructural evolution map for multi-dimensional security situation awareness enhancement. Through dynamic monitoring and multi-dimensional comprehensive analysis, it provides more refined, comprehensive, and dynamic security monitoring and management capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 It is a schematic flow chart of the method for enhancing a battery management system based on artificial intelligence provided by the present invention;

[0063] Figure 2 It is a schematic diagram of the system for enhancing a battery management system based on artificial intelligence provided by the present invention;

[0064] Figure 3Schematic diagram of the process for dynamic digital twin modeling in step S2;

[0065] Figure 4 Schematic diagram of the process for dynamic charge and discharge enhancement in step S3;

[0066] Figure 5 Schematic diagram of the process for multi-dimensional security situation awareness enhancement in step S4.

[0067] The accompanying drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention, and do not constitute a limitation to the present invention. Detailed implementation manners

[0068] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0069] In the description of the present invention, it should be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", etc. indicating the orientation or positional relationship are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention.

[0070] Embodiment 1. Refer to Figure 1 , the method for enhancing a battery management system based on artificial intelligence provided by the present invention includes the following steps:

[0071] Step S1: Heterogeneous data fusion acquisition;

[0072] Step S2: Dynamic digital twin modeling;

[0073] Step S3: Dynamic charge and discharge enhancement;

[0074] Step S4: Multi-dimensional security situation awareness enhancement;

[0075] Step S5: Enhancement of the battery management system.

[0076] By performing the above operations, in the existing battery management system, the traditional system mainly monitors voltage, temperature and current and conducts charge and discharge control to achieve balanced management and safety optimization. However, the existing technical solutions are not accurate enough in predicting battery aging. At the same time, the adaptability to dynamic working conditions is poor, making it difficult to cope with the changing battery working environment, and the charge and discharge strategies are not efficient enough. As a result, there are technical problems that the existing battery management system needs to be enhanced and optimized in terms of intelligence. This solution creatively adopts a comprehensive battery management system management enhancement method that combines dynamic digital twin modeling optimization, dynamic charge and discharge strategy optimization, and multi-dimensional safety situation awareness optimization. Through enhancements and optimizations in multiple dimensions, the dynamic performance, prediction accuracy, and overall strategy adjustment efficiency of the battery management system are improved.

[0077] Example 2. Refer to Figure 1 and Figure 2 , in step S1, the heterogeneous data fusion acquisition is used to collect the original data related to the battery state required for the analysis of the battery management system. Specifically, through heterogeneous data fusion acquisition, the original data set for battery state management is collected, and preliminary optimization and preprocessing are performed to obtain the enhanced data set for the battery management system.

[0078] The heterogeneous data fusion acquisition specifically collects battery state data by deploying a sensor array and collecting dynamic characteristics of electrochemical impedance spectroscopy.

[0079] The original data set for battery state management includes battery voltage data, current data, temperature data, electrochemical data, mechanical support data, solid electrolyte interface film evolution data, and multi-physical field fusion data.

[0080] The battery voltage data specifically includes battery terminal voltage data and battery internal voltage distribution sensing data.

[0081] The current data specifically includes charging current data, discharging current data, and current fluctuation data.

[0082] The temperature data specifically includes battery surface temperature data and battery internal sensing temperature data.

[0083] The electrochemical data specifically includes electrochemical impedance spectroscopy data and ion migration rate reference data.

[0084] The mechanical support data specifically includes battery expansion data and battery contraction data.

[0085] The solid electrolyte interface film evolution data specifically includes film thickness data and film composition analysis data.

[0086] The multi-physical field fusion data specifically refers to the coupled comprehensive data of heat-mechanics-electricity-chemistry, including multi-dimensional data that fuses the heat field, mechanical field, electric field, and chemical reaction data;

[0087] The steps of the preliminary optimization and preprocessing include data denoising, missing value handling, outlier correction, data standardization, time series data stationarization, and feature selection. By performing the preliminary optimization and preprocessing on the original battery state management dataset, an enhanced dataset for the battery management system is obtained;

[0088] The enhanced dataset for the battery management system includes optimized time series data, derivative feature data, multi-physical field fusion data, fusion metric data, evolution feature data, labeled data, and synchronized multi-dimensional data;

[0089] The optimized time series data specifically refers to the optimized battery voltage, current, and temperature data;

[0090] The derivative feature data specifically refers to the optimized charge and discharge rate, heat change rate, and internal resistance change rate feature data;

[0091] The multi-physical field fusion data specifically refers to the fused heat, mechanics, electricity, and chemical data, which is used to reflect the complex behaviors of the battery under different working conditions;

[0092] The fusion metric data specifically refers to the optimized electrochemistry impedance spectroscopy data and physical data;

[0093] The evolution feature data specifically refers to the optimized membrane thickness data and membrane composition analysis data;

[0094] The labeled data specifically refers to the data obtained by labeling the battery state, and the labels include normal, overcharging, overdischarging, and aging;

[0095] The synchronized multi-dimensional data specifically refers to the battery voltage, current, and temperature data after synchronizing the timestamps.

[0096] Example 3, refer to Figure 1 、 Figure 2 and Figure 3 Based on the above example, in step S2, the dynamic digital twin modeling is used to construct a four-level digital twin model for battery state management. Specifically, according to the enhanced dataset of the battery management system, a four-level resolution twin model construction method is adopted for dynamic digital twin modeling to obtain an enhanced digital twin model for battery management;

[0097] The enhanced dataset for the battery management system includes a quantum chemistry scale model, an electrode particle scale model, a single battery scale model, and a system integration scale model;

[0098] The quantum chemistry scale model is used to introduce a multi-scale coupling strategy for comprehensive modeling of electron states and internal and external environmental parameters of the battery;

[0099] The electrode particle scale model is used to introduce non-uniform TV distribution correction for modeling the spatial variation of electric potential within the electrode particles and improving the traditional phase field model;

[0100] The single battery scale model is used to introduce the double layer effect for modeling and improving the influence of the double layer on the current distribution in the traditional motor model;

[0101] The system integration scale model is used to introduce a dynamic resistance correction method based on state estimation for modeling and improving the dynamic adjustment of the equivalent resistance model;

[0102] The steps of using the four-level resolution twin model construction method for dynamic digital twin modeling to obtain the enhanced digital twin model for battery management include:

[0103] Step S21: Electron structure modeling, which is used to construct the quantum chemistry scale model. Specifically, by introducing a multi-scale coupling strategy for electron structure calculation, a reference value of the electron structure Hamiltonian is obtained. The calculation formula is:

[0104] ;

[0105] In the formula, H is the Hamiltonian, which is used to describe the total energy of the system, is the wave function, which is used to represent the quantum state and electron state of the system. E is the total energy of the system, T is the kinetic energy, which is used to represent the kinetic energy state of the particle, V ext (r) is the potential energy affected by the external electric field, V elec (r) is the electric potential of electrons within the electrode, r is the potential energy parameter, V therm (T) is the potential energy of temperature, which is used to represent the thermal effect state inside the battery;

[0106] Step S22: Particle electrochemistry reaction modeling, which is used to construct the electrode particle scale model. Specifically, a potential correction coefficient is introduced into the standard phase field model for particle electrochemistry reaction modeling to obtain reference values of ion diffusion and reaction rate. The calculation formula is:

[0107] ;

[0108] In the formula, C is the ion concentration, t is the time variable, The whole is the partial derivative of the ion concentration, which is used to represent the reference values of ion diffusion and reaction rate. D is the diffusion coefficient, R is the reaction rate, is the Laplace operator of the spatial distribution of ion concentration diffusion, is the gradient term operator, is the potential correction coefficient, which is used to represent the influence of the electric field in the electrode material. is the electric potential inside the electrode particles. As a whole, it is the electric potential gradient term, and R0 is the reaction rate parameter.

[0109] Step S23: Modeling of the electrode current density, which is used to construct a single-cell scale model. Specifically, the double-layer effect correction is introduced into the standard porous electrode model to perform the modeling of the electrode current density, and an improved modeling model of the electrode current density is obtained. The calculation formula is:

[0110] ;

[0111] In the formula, j is the current density value. is the conductivity parameter. is the electric potential inside the electrode particles. As a whole, it is the electric potential gradient term, F is the Faraday constant, R is the gas constant. is the temperature, C is the ion concentration. is the double-layer effect coefficient. is the ion concentration of the double layer. is the electric potential of the double layer.

[0112] Step S24: Modeling of the battery equivalent circuit, which is used to construct a system integration scale model. Specifically, in the standard equivalent circuit model, the resistance is regarded as a dynamic variable and the resistance is dynamically corrected to obtain a battery equivalent circuit modeling model. The calculation formula is:

[0113] ;

[0114] In the formula, V OC is the open-circuit voltage value, I is the battery current value, R eq is the equivalent resistance value, V(t) is the battery working voltage value.

[0115] is the battery equivalent circuit modeling model. By dynamically correcting the equivalent resistance value R eq a system integration scale model is constructed. R eq (t) is the equivalent resistance value regarded as a dynamic variable, and R1 is the basic resistance, which is used to represent the resistance value of the battery in the normal working state. is the dynamic resistance change term, SOC(t) is the state of charge of the battery, and SOH(t) is the state of health of the battery. is the battery temperature state.

[0116] Step S25: Four - level integration, used to build a four - level resolution twin model. Specifically, through the electronic structure modeling, the particle electrochemical reaction modeling, the electrode current density modeling, and the battery equivalent circuit modeling, the four - level digital twin model integration is carried out to obtain a battery management enhanced digital twin model.

[0117] By performing the above operations, in the existing dynamic digital twin modeling process, there are technical problems that in traditional battery digital twin modeling, the combination of the internal and external conditions of the battery is less, and it is difficult to fully reflect the state changes and health state changes of the battery, resulting in the difficulty of reflecting the dynamics of the battery in both macroscopic and microscopic modeling. This solution creatively adopts a four - level digital twin integration model for dynamic digital twin modeling. By introducing multi - scale coupling in electronic structure calculations, introducing non - uniform potential distribution correction in the phase - field model, and introducing the double - layer effect and dynamic equivalent resistance calculation methods from the perspectives of single - cell and system integration, the dynamics of the battery digital twin model is improved, thus forming a complete digital twin system that is adaptive and dynamically adjustable, which helps to realize battery health management, charge - discharge optimization, and fault prediction in the follow - up.

[0118] Example 4, refer to Figure 1 、 Figure 2 and Figure 4 Based on the above - mentioned example, in step S3, the dynamic charge - discharge enhancement is used to dynamically enhance the battery charge - discharge management. Specifically, according to the battery management system enhanced dataset and the battery management enhanced digital twin model, a reinforcement learning method combining double - delay deep deterministic policy gradient and reward function update is adopted for dynamic charge - discharge enhancement to obtain a dynamic charge - discharge enhancement reference policy, including the following steps:

[0119] Step S31: Build a double - delay reinforcement learning framework. Specifically, build a standard reinforcement learning environment parameter model, and adopt a deep deterministic gradient policy, combine the value function and the policy function for the reinforcement learning basic framework setting, and update the parameters of the value network and the policy network by building a double - delay update policy;

[0120] Step S32: Improve the dynamic charge - discharge enhancement reward. Specifically, by designing a multi - dimensional reward function, comprehensively integrate from the aspects of battery life, efficiency, and safety for dynamic charge - discharge enhancement reward improvement to obtain a dynamic charge - discharge enhancement reward function, and perform reinforcement learning training according to the dynamic charge - discharge enhancement reward function;

[0121] The calculation formula of the multi - dimensional reward function is:

[0122] ;

[0123] where Rw is a multi-dimensional reward function, which is used as the reward function of the double-delayed reinforcement learning framework described in step S31. is the battery life weight. is the battery life gain term. is the charge-discharge efficiency weight. is the charge-discharge efficiency term. is the safety factor weight, and S is the safety factor term.

[0124] The battery life gain term is used to represent the change in the health of the battery under the current charge-discharge operation. The calculation formula is:

[0125] ;

[0126] In the formula, is the battery life gain term, SOH(t) is the state of health of the battery, and SOH opt (t) is the state of health of the battery under the optimal charge-discharge strategy.

[0127] The charge-discharge efficiency term is used to represent the capacity utilization rate during the charge-discharge process. The calculation formula is:

[0128] ;

[0129] In the formula, is the charge-discharge efficiency term, P out is the power output by the battery during discharge, and P in is the power input to the battery during charging.

[0130] The safety factor term is used to represent the safety of the current charge-discharge operation of the battery. The calculation formula is:

[0131] ;

[0132] In the formula, S is the safety factor term, exp(·) is the natural base function, is the safety sensitivity temperature weight, T current is the temperature at the current moment, and T safe is the safety temperature of the battery. is the safety sensitivity state of charge weight, SOC current is the current state of charge of the battery, and SOC safe is the safe state of charge of the battery.

[0133] Step S33: Iteratively update the dynamic charge-discharge strategy. Specifically, by applying the multi-dimensional reward function to the double-delayed reinforcement learning framework, iteratively update the dynamic charge-discharge strategy to obtain the iteratively updated dynamic charge-discharge strategy data.

[0134] Step S34: Dynamic charge and discharge enhancement. Specifically, through the dual-delay reinforcement learning framework, the dynamic charge and discharge enhancement reward improvement, and the dynamic charge and discharge policy iteration update, perform the reinforcement learning iteration training of the dynamic charge and discharge enhancement model to obtain the dynamic charge and discharge enhancement model Model DH and by using the dynamic charge and discharge enhancement model Model DH , based on the battery management system enhanced dataset and the battery management enhanced digital twin model, perform dynamic charge and discharge enhancement to obtain a dynamic charge and discharge enhancement reference policy;

[0135] The dynamic charge and discharge enhancement reference policy specifically includes battery health state data, charge and discharge control data, and optimized charge and discharge data.

[0136] By performing the above operations, in the existing dynamic charge and discharge enhancement methods, there are technical problems that the intelligence and dynamics of the battery charge and discharge adjustment strategy combined with dynamic digital modeling in the existing methods are insufficient, and at the same time, this further leads to the change of the battery working environment being faster than the adjustment strategy of the battery management. This solution creatively combines the reinforcement learning method of dual-delay deep deterministic policy gradient and reward function update to perform dynamic charge and discharge enhancement. Through the dual-delay update strategy combined with the refined reward function improvement, the intelligence and dynamics of the battery charge and discharge adjustment strategy are improved from bottom to top, which not only helps to extend the battery life and improve the charge and discharge efficiency, but also ensures that the battery works within a safe range, improving the overall performance and reliability of the battery system and the battery management system.

[0137] Example Five. Refer to Figure 1 、 Figure 2 and Figure 5 , based on the above example, in step S4, the multi-dimensional security situation awareness enhancement is used to perform multi-dimensional enhancement on the battery security situation awareness management. Specifically, based on the battery management system enhanced dataset and the battery management enhanced digital twin model, adopt a spatio-temporal graph convolutional network combined with the battery microstructure evolution map to perform multi-dimensional security situation awareness enhancement to obtain multi-dimensional security situation awareness reference data, including the following steps:

[0138] Step S41: Construct a spatio-temporal graph convolutional basic network for capturing the spatio-temporal dependence and basic features in the battery microstructure. Specifically, by constructing battery microstructure graph data and constructing a standard spatio-temporal graph convolutional network as the basic network for multi-dimensional security situation awareness enhancement;

[0139] Step S42: Construct an evolution map of the battery microstructure for modeling the evolution process of the internal structure of the battery and supporting dynamic prediction. Specifically, construct a basic model for the evolution of the battery microstructure state, and based on the basic model of the battery microstructure state evolution, perform evolution predictions of battery micro-deformation, lithium plating, and the growth of the solid electrolyte interface film;

[0140] The calculation formula of the basic model for the evolution of the battery microstructure state is:

[0141] ;

[0142] In the formula, S(t) is the state of the battery microstructure at the current time t, which is used to represent the evolution states of battery micro-deformation, lithium plating, and the growth of the solid electrolyte interface film, is the change amount of the battery microstructure in time t;

[0143] Step S43: Early fault propagation modeling for detecting microstructure changes and implementing early warning predictions of battery faults. Specifically, through the coupling effect of current, temperature, and charge state in the battery, perform early fault propagation modeling, and through the early fault propagation modeling, perform early warning predictions of battery faults;

[0144] The calculation formula of the early fault propagation modeling is:

[0145] ;

[0146] In the formula, Fp(t) is the fault propagation rate parameter, w1 is the weight of battery microstructure evolution, m Li is the battery microstructure evolution rate, w2 is the temperature change weight, is the temperature change rate, w3 is the battery charge state weight, is the battery charge state change rate;

[0147] Step S44: Training of the multi-dimensional security situation awareness enhancement model. Specifically, through the spatio-temporal graph convolutional basic network, the battery microstructure evolution map, and the early fault propagation modeling, perform training of the multi-dimensional security situation awareness enhancement model to obtain the multi-dimensional security situation awareness enhancement model Model EH ;

[0148] Step S45: Enhancement of multi-dimensional security situation awareness. Specifically, use the multi-dimensional security situation awareness enhancement model Model EH , and based on the enhanced dataset of the battery management system and the enhanced digital twin model of the battery management, perform enhancement of multi-dimensional security situation awareness to obtain multi-dimensional security situation awareness reference data;

[0149] The multi-dimensional security situation awareness reference data specifically includes battery prediction parameters, fault propagation prediction rates, and battery safety state change prediction reference data.

[0150] By performing the above operations, in view of the technical problem that in the existing multi-dimensional security situation awareness enhancement methods, most of the existing battery safety management systems rely on traditional prediction methods, such as predicting the battery life based on the data during the battery charging and discharging process. However, many traditional methods cannot effectively capture the changes at the micro level of the battery and the early signals of faults, and these systems lack the ability to dynamically and intelligently sense and analyze the micro changes in the entire life cycle of the battery, this solution creatively uses a spatio-temporal graph convolutional network combined with the battery microstructure evolution map to enhance multi-dimensional security situation awareness. Through dynamic monitoring and multi-dimensional comprehensive analysis, it provides more refined, comprehensive, and dynamic security monitoring and management capabilities.

[0151] Embodiment Six, refer to Figure 1 and Figure 2 Based on the above embodiment, in step S5, the enhanced battery management system is used to comprehensively enhance the battery management system by combining battery charging and discharging management and security situation management. Specifically, a basic mathematical model required for enhancing the battery management system is constructed through dynamic digital twin modeling, and through the dynamic charging and discharging enhancement and the multi-dimensional security situation awareness enhancement, the comprehensive management of the battery management system is enhanced to obtain a dynamic charging and discharging enhancement reference strategy and multi-dimensional security situation awareness reference data, and by combining the dynamic charging and discharging enhancement reference strategy and the multi-dimensional security situation awareness reference data, the comprehensive enhancement reference data of the battery management system is obtained.

[0152] Embodiment Seven, refer to Figure 1 and Figure 2 Based on the above embodiment, the battery management system enhancement system based on artificial intelligence provided by the present invention includes a quantum sensing module, a digital twin module, a dynamic optimization module, a security situation awareness module, and a battery management system enhancement module;

[0153] The quantum sensing module is used for heterogeneous data fusion acquisition. Through heterogeneous data fusion acquisition, a battery management system enhancement data set is obtained, and the battery management system enhancement data set is sent to the digital twin module, the dynamic optimization module, and the security situation awareness module;

[0154] The digital twin module is used for dynamic digital twin modeling. Through dynamic digital twin modeling, a battery management enhanced digital twin model is obtained, and the battery management enhanced digital twin model is applied to the dynamic optimization module and the security situation awareness module;

[0155] The dynamic optimization module is used for dynamic charge and discharge enhancement. Through dynamic charge and discharge enhancement, a dynamic charge and discharge enhancement reference strategy is obtained, and the dynamic charge and discharge enhancement reference strategy is sent to the battery management system enhancement module;

[0156] The security situation awareness module is used for multi-dimensional security situation awareness enhancement. Through multi-dimensional security situation awareness enhancement, multi-dimensional security situation awareness reference data is obtained, and the multi-dimensional security situation awareness reference data is sent to the battery management system enhancement module;

[0157] The battery management system enhancement module is used for battery management system enhancement. Through battery management system enhancement, comprehensive battery management system enhancement reference data is obtained.

[0158] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0159] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principle and spirit of the present invention.

[0160] The above describes the present invention and its implementation manners. This description is not restrictive. What is shown in the drawings is only one of the implementation manners of the present invention, and the actual structure is not limited thereto. All in all, if those of ordinary skill in the art are inspired by it and design similar structural manners and embodiments without creative efforts without departing from the purpose of the present invention, they shall fall within the protection scope of the present invention.

Claims

1. Method for enhancing battery management system based on artificial intelligence, characterized in that: The method includes the following steps: Step S1: Heterogeneous data fusion acquisition to obtain an enhanced dataset of the battery management system; Step S2: Dynamic digital twin modeling. Based on the enhanced dataset of the battery management system, a four-level resolution twin model construction method is adopted for dynamic digital twin modeling to obtain an enhanced digital twin model of the battery management; the enhanced dataset of the battery management system includes a quantum chemical scale model, an electrode particle scale model, a single battery scale model, and a system integration scale model; The quantum chemical scale model is used to introduce a multi-scale coupling strategy for comprehensive modeling of electron states and battery internal and external environment parameters; the electrode particle scale model is used to introduce non-uniform television distribution correction for modeling the spatial variation of electric potential within electrode particles and improving the traditional phase field model; the single battery scale model is used to introduce the double layer effect for modeling and improving the influence of the double layer on current distribution in the traditional motor model; the system integration scale model is used to introduce a dynamic resistance correction method based on state estimation for dynamic adjustment modeling and improvement of the equivalent resistance model; Step S3: Dynamic charge and discharge enhancement. A reinforcement learning method combining double-delay deep deterministic policy gradient and reward function update is adopted for dynamic charge and discharge enhancement to obtain a dynamic charge and discharge enhancement reference policy; By designing a multi-dimensional reward function, the reward function update is performed. The calculation formula of the multi-dimensional reward function is: ； where R w is a multi-dimensional reward function used as the reward function in the double-delay reinforcement learning framework, is the battery life weight, is the battery life gain term, is the charge-discharge efficiency weight, is the charge-discharge efficiency term, is the safety factor weight, and S is the safety factor term; Step S4: Multi-dimensional security situation awareness enhancement. A spatio-temporal graph convolutional network combined with a battery microstructure evolution atlas is adopted for multi-dimensional security situation awareness enhancement to obtain multi-dimensional security situation awareness reference data; Step S5: Enhancement of the battery management system to obtain comprehensive enhanced reference data of the battery management system.

2. The method for enhancing an artificial intelligence-based battery management system according to claim 1, wherein: In step S1, the heterogeneous data fusion acquisition is used to collect the original data related to the battery state required for battery management system analysis. Specifically, through heterogeneous data fusion acquisition, the original dataset of battery state management is collected, and preliminary optimization and preprocessing are performed to obtain the enhanced dataset of the battery management system; The heterogeneous data fusion acquisition specifically collects battery state data through the deployment of a sensor array and the dynamic feature acquisition of electrochemical impedance spectroscopy; The original dataset of battery state management includes battery voltage data, current data, temperature data, electrochemical data, mechanical support data, solid electrolyte interface film evolution data, and multi-physical field fusion data; The steps of the preliminary optimization and preprocessing include data denoising, missing value processing, outlier correction, data standardization, time series data stationarization, and feature selection. By performing the preliminary optimization and preprocessing on the original dataset of battery state management, the enhanced dataset of the battery management system is obtained; The enhanced dataset of the battery management system includes optimized time series data, derived feature data, multi-physical field fusion data, fusion index data, evolution feature data, labeled data, and synchronized multi-dimensional data.

3. The method for enhancing a battery management system based on artificial intelligence according to claim 2, wherein: In step S2, the dynamic digital twin modeling is used to construct a four-level digital twin model for battery state management. Specifically, based on the enhanced dataset of the battery management system, a four-level resolution twin model construction method is adopted for dynamic digital twin modeling to obtain an enhanced digital twin model for battery management; The steps of adopting the four-level resolution twin model construction method for dynamic digital twin modeling to obtain an enhanced digital twin model for battery management include: Step S21: Electronic structure modeling is used to construct a quantum chemistry scale model. Specifically, by introducing a multi-scale coupling strategy for electronic structure calculation, a reference value of the electronic structure Hamiltonian is obtained; Step S22: Particle electrochemical reaction modeling is used to construct an electrode particle scale model. Specifically, a potential correction coefficient is introduced into the standard phase field model for particle electrochemical reaction modeling to obtain reference values of ion diffusion and reaction rate; Step S23: Electrode current density modeling is used to construct a single battery scale model. Specifically, the double layer effect correction is introduced into the standard porous motor model for electrode current density modeling to obtain an improved modeling model of electrode current density; Step S24: Battery equivalent circuit modeling is used to construct a system integration scale model. Specifically, in the standard equivalent circuit model, the resistance is regarded as a dynamic variable and resistance dynamic correction is performed to obtain a battery equivalent circuit modeling model. The calculation formula is: ； Wherein, V OC is the open circuit voltage value, I is the battery current value, R eq is the equivalent resistance value, V(t) is the battery operating voltage value, is the battery equivalent circuit modeling model. By performing dynamic correction on the equivalent resistance value R eq to construct a system integration scale model, R eq (t) is the equivalent resistance value regarded as a dynamic variable, R1 is the base resistance, which is used to represent the resistance value of the battery under normal operating conditions, is the dynamic resistance change term, SOC(t) is the state of charge of the battery, SOH(t) is the state of health of the battery, is the battery temperature state; Step S25: Four-level integration is used to construct a four-level resolution twin model. Specifically, through the electronic structure modeling, the particle electrochemical reaction modeling, the electrode current density modeling, and the battery equivalent circuit modeling, four-level digital twin model integration is performed to obtain an enhanced digital twin model for battery management.

4. The method for enhancing an artificial intelligence-based battery management system according to claim 3, wherein: In step S3, the dynamic charge and discharge enhancement is used to dynamically enhance the battery charge and discharge management. Specifically, based on the enhanced dataset of the battery management system and the enhanced digital twin model for battery management, a reinforcement learning method combining double-delay deep deterministic policy gradient and reward function update is adopted for dynamic charge and discharge enhancement to obtain a dynamic charge and discharge enhancement reference policy, including the following steps: Step S31: Construct a double-delay reinforcement learning framework. Specifically, a standard reinforcement learning environment parameter model is constructed, and the deep deterministic gradient strategy is adopted. Combining the value function and the policy function, the basic framework of reinforcement learning is set, and the parameters of the value network and the policy network are updated by constructing a double-delay update strategy; Step S32: Dynamic charge and discharge enhancement reward improvement. Specifically, by designing a multi-dimensional reward function and comprehensively integrating from the aspects of battery life, efficiency, and safety, dynamic charge and discharge enhancement reward improvement is carried out to obtain a dynamic charge and discharge enhancement reward function, and based on the dynamic charge and discharge enhancement reward function, reinforcement learning training is carried out; Step S33: Iterative update of the dynamic charge and discharge strategy. Specifically, by applying the multi-dimensional reward function to the double-delay reinforcement learning framework, iterative update of the dynamic charge and discharge strategy is carried out to obtain iterative update dynamic charge and discharge strategy data; Step S34: Dynamic charge and discharge enhancement, specifically, through the double-delay reinforcement learning framework, the dynamic charge and discharge enhancement reward improvement, and the dynamic charge and discharge strategy iterative update, perform the reinforcement learning iterative training of the dynamic charge and discharge enhancement model to obtain the dynamic charge and discharge enhancement model Model DH , and by using the dynamic charge and discharge enhancement model Model DH , based on the battery management system enhanced dataset and the battery management enhanced digital twin model, perform dynamic charge and discharge enhancement to obtain a dynamic charge and discharge enhancement reference strategy; The dynamic charge-discharge enhancement reference strategy specifically includes battery health state data, charge-discharge control data, and optimized charge-discharge data.

5. The method for enhancing an artificial-intelligence-based battery management system according to claim 4, wherein: In step S4, the multi-dimensional security situation awareness enhancement is used to perform multi-dimensional enhancement on battery security situation awareness management. Specifically, based on the battery management system enhancement data set and the battery management enhancement digital twin model, a spatio-temporal graph convolutional network combined with the battery microstructure evolution map is used to perform multi-dimensional security situation awareness enhancement to obtain multi-dimensional security situation awareness reference data, including the following steps: Step S41: Construct a spatio-temporal graph convolutional basic network for capturing spatio-temporal dependencies and basic features in the battery microstructure. Specifically, by constructing battery microstructure graph data and constructing a standard spatio-temporal graph convolutional network as the basic network for multi-dimensional security situation awareness enhancement; Step S42: Construct a battery microstructure evolution map for modeling the evolution process of the internal structure of the battery and supporting dynamic prediction. Specifically, construct a basic model for the evolution of the battery microstructure state, and based on the basic model for the evolution of the battery microstructure state, perform evolution predictions of battery micro-deformation, lithium plating, and solid electrolyte interphase film growth; Step S43: Early fault propagation modeling for detecting microstructure changes and implementing early warning predictions of battery faults. Specifically, through the coupling effect of current, temperature, and charge state in the battery, perform early fault propagation modeling, and through the early fault propagation modeling, perform early warning predictions of battery faults; Step S44: Training of the multi-dimensional security situation awareness enhancement model, specifically, through the spatio-temporal graph convolutional basic network, the battery microstructure evolution map, and the early fault propagation modeling, training the multi-dimensional security situation awareness enhancement model to obtain the multi-dimensional security situation awareness enhancement model Model EH ; Step S45: Multidimensional security situation awareness enhancement, specifically using the Multidimensional Security Situation Awareness Enhancement Model Model EH , based on the enhanced dataset of the battery management system and the enhanced digital twin model of the battery management, perform multidimensional security situation awareness enhancement to obtain multidimensional security situation awareness reference data.

6. The method for enhancing an artificial intelligence-based battery management system according to claim 5, wherein: In step S4, the multi-dimensional security situation awareness reference data specifically includes battery prediction parameters, fault propagation prediction rates, and battery security state change prediction reference data.

7. The method for enhancing an artificial intelligence-based battery management system according to claim 6, characterized in that: In step S5, the battery management system enhancement is used to perform comprehensive management enhancement of the battery management system by combining battery charge-discharge management and security situation management. Specifically, construct a basic mathematical model required for battery management system enhancement through dynamic digital twin modeling, and through the dynamic charge-discharge enhancement and the multi-dimensional security situation awareness enhancement, perform comprehensive management enhancement of the battery management system to obtain a dynamic charge-discharge enhancement reference strategy and multi-dimensional security situation awareness reference data, and through combining the dynamic charge-discharge enhancement reference strategy and multi-dimensional security situation awareness reference data, obtain battery management system comprehensive enhancement reference data.

8. An enhanced system for a battery management system based on artificial intelligence, for implementing the method for enhancing a battery management system based on artificial intelligence according to any one of claims 1-7, characterized in that: It includes a quantum sensing module, a digital twin module, a dynamic optimization module, a security situation awareness module, and a battery management system enhancement module.

9. The enhanced system for battery management system based on artificial intelligence according to claim 8, characterized in that: The quantum sensing module is used for heterogeneous data fusion acquisition. Through heterogeneous data fusion acquisition, a battery management system enhancement data set is obtained, and the battery management system enhancement data set is sent to the digital twin module, the dynamic optimization module, and the security situation awareness module; The digital twin module is used for dynamic digital twin modeling. Through dynamic digital twin modeling, a battery management enhancement digital twin model is obtained, and the battery management enhancement digital twin model is applied to the dynamic optimization module and the security situation awareness module; The dynamic optimization module is used for dynamic charge and discharge enhancement. Through dynamic charge and discharge enhancement, a dynamic charge and discharge enhancement reference strategy is obtained, and the dynamic charge and discharge enhancement reference strategy is sent to the battery management system enhancement module; The security situation awareness module is used for multi-dimensional security situation awareness enhancement. Through multi-dimensional security situation awareness enhancement, multi-dimensional security situation awareness reference data is obtained, and the multi-dimensional security situation awareness reference data is sent to the battery management system enhancement module; The battery management system enhancement module is used for battery management system enhancement. Through battery management system enhancement, battery management system comprehensive enhancement reference data is obtained.

Images