Multi-objective optimization lithium ion battery charging design method, system and equipment

Abstract

The invention discloses a multi-objective optimization lithium ion battery charging design method, system and equipment, and the method comprises the steps: constructing an electrochemical-thermal-aging model, and constructing an enhanced Chebyshev function; based on the first database and an enhanced Chebyshev function, performing scaling on each single-target sub-problem corresponding to each first charging protocol to obtain a scaling target data set; on the basis of a second database and an enhanced Chebyshev function, performing scaling on each single-target sub-problem corresponding to each second charging protocol to obtain a scaling source data set; based on the scaled target data set, constructing a Gaussian process model of the single-target sub-problem; and designing a migration acquisition function by adopting a Gaussian process model based on the scaled source data set, solving the migration acquisition function, evaluating a solving result by adopting an electrochemical-thermal-aging model, and determining a group of target charging protocols. The accuracy of the charging protocol can be improved, and the model simulation time is shortened.

Description

Technical Field

[0001] This application relates to the technical field of battery charging, and in particular, to a multi-objective optimization method, system, and device for lithium-ion battery charging design. Background Art

[0002] As the most popular energy storage device at present, lithium-ion batteries have been widely used in many fields such as electric vehicles, portable electronic devices, and clean energy storage due to their high energy density, high power density, long cycle life, good safety, and relative environmental friendliness. However, the long charging time caused by slow charging speed and the battery performance degradation caused by fast charging are still the key problems hindering the further popularization and development of lithium-ion batteries.

[0003] In order to accurately evaluate the impact of different charging protocols on battery performance, the academic community generally relies on the coupled electrochemistry-thermal-aging model, which is based on the pseudo-two-dimensional (P2D) electrochemical equation, heat conduction equation, and solid electrolyte interface membrane (SEI) nucleation and growth kinetic equation, and accurately reproduces the ion diffusion, electrode reaction, and heat source distribution inside the battery by solving the partial differential equation system. However, the simulation of the full-order model is extremely time-consuming, which is not conducive to online optimization and large-scale sample screening. For this reason, some people have proposed the equivalent circuit model (ECM) and reduced-order model (ROM) to replace the high-complexity P2D model. ECM uses a series of RC networks to approximate the battery polarization and transmission process, and can estimate the terminal voltage and internal impedance in real time, but the description of the temperature field and aging mechanism is relatively rough; ROM (such as the single-particle model SPM and its coupled thermal-aging extension) simplifies and assumes the key modes of the P2D model, reducing the calculation amount while retaining some physical interpretability, but there will still be accuracy deviations under high-rate, low-temperature, or non-uniform boundary conditions.

[0004] Therefore, the accuracy of the charging protocols in the existing related battery charging protocol design methods is relatively low, and the model simulation is time-consuming. Summary of the Invention

[0005] This application aims to propose a multi-objective optimization method, system, and device for lithium-ion battery charging design, which can improve the accuracy of the charging protocol and reduce the model simulation time.

[0006] In a first aspect, an embodiment of this application provides a multi-objective optimization method for lithium-ion battery charging design, and the method includes: Construct a constrained multi-objective optimization problem including multiple single-objective sub-problems and constraint conditions, where each single-objective sub-problem satisfies the constraint conditions; Construct a first database that uses historical data corresponding to the current battery health state and includes multiple first charging protocols and the total target values corresponding to the first charging protocols, and construct a second database that uses empirical data corresponding to other battery health states and includes multiple second charging protocols and the total target values corresponding to the second charging protocols, where the total target value is the overall optimization objective in the constrained multi-objective optimization problem corresponding to the charging protocol; Construct an electrochemistry-thermal-aging model and an enhanced Chebyshev function; Based on the first database and the enhanced Chebyshev function, scalarize the constrained multi-objective optimization problem corresponding to each first charging protocol to obtain a scalarized target data set; Based on the second database and the enhanced Chebyshev function, scalarize the constrained multi-objective optimization problem corresponding to each second charging protocol to obtain a scalarized source data set; Based on the scalarized target data set, construct a Gaussian process model for the single-objective sub-problem; Based on the scalarized source data set, design a transfer acquisition function using the Gaussian process model, solve the transfer acquisition function, and evaluate the solution result using the electrochemistry-thermal-aging model to determine a set of target charging protocols.

[0007] Compared with the prior art, the first aspect of the present application has the following beneficial effects: This method constructs a constrained multi-objective optimization problem that includes multiple single-objective sub-problems and constraints, where each single-objective sub-problem satisfies the constraints. Historical data corresponding to the current battery health state is used to construct a first database that includes multiple first charging protocols and the total objective values corresponding to the first charging protocols, and empirical data corresponding to other battery health states is used to construct a second database that includes multiple second charging protocols and the total objective values corresponding to the second charging protocols, where the total objective value is the overall optimization objective in the constrained multi-objective optimization problem corresponding to the charging protocol. An electrochemistry-thermal-aging model is constructed, and an enhanced Chebyshev function is constructed. Based on the first database and the enhanced Chebyshev function, the constrained multi-objective optimization problem corresponding to each first charging protocol is scalarized to obtain a scalarized objective data set. Based on the second database and the enhanced Chebyshev function, the constrained multi-objective optimization problem corresponding to each second charging protocol is scalarized to obtain a scalarized source data set. Based on the scalarized objective data set, a Gaussian process model for the single-objective sub-problem is constructed. Based on the scalarized source data set, a Gaussian process model is used to design a transfer acquisition function, the transfer acquisition function is solved, and the electrochemistry-thermal-aging model is used to evaluate the solution result to determine a set of target charging protocols. In this way, by using the enhanced Chebyshev function to achieve the scalarization of the charging protocol, and based on the scalarized objective data set, a Gaussian process model for the single-objective sub-problem is constructed, and the Gaussian process model is trained with limited real simulation results to achieve the rapid prediction and uncertainty evaluation of the scalarized objective of the charging protocol, which can significantly reduce expensive simulation calls, that is, reduce the model simulation time. Then, a Gaussian process model is used to design a transfer acquisition function, which can effectively combine historical data and empirical data, dynamically adjust the optimization direction, avoid repeated exploration, and quickly generate new charging protocols, that is, improve the accuracy of the charging protocol and the charging protocol design efficiency.

[0008] In some embodiments, the electrochemistry-thermal-aging model includes an electrochemistry model, a thermal model, and an aging model. The construction of the electrochemistry-thermal-aging model includes: Constructing an electrochemistry model: ; Constructing a thermal model: ; Constructing an aging model: ; Wherein, represents the terminal voltage at time represents the solid-phase potential, represents the spatial coordinate, represents the length of the negative electrode, represents the length of the separator, represents the length of the positive electrode, represents the battery density, represents the specific heat capacity, represents the temperature, represents the thermal conductivity, represents the heat generation rate determined by the electrochemical model, represents the lithium ion loss, represents the reaction current for the formation of the solid electrolyte interface layer, represents the reaction current related to the continuous formation of the surface solid electrolyte interface, represents the reaction current for the formation of a new solid electrolyte interface layer on the crack of the graphite particle.

[0009] In some embodiments, constructing the enhanced Chebyshev function includes: ; wherein, represents the scalarized objective generated by the enhanced Chebyshev function, represents the number of single-objective sub-problems in the constrained multi-objective optimization problem, represents the weight vector the th component of represents the protocol parameter vector, represents the th normalized single-objective sub-problem in the constrained multi-objective optimization problem, represents the positive weight coefficient.

[0010] In some embodiments, constructing the Gaussian process model of the single-objective sub-problem based on the scalarized objective dataset includes: Using a Gaussian kernel function to quantify the correlation between any two charging protocols in the scalarized objective dataset; Constructing a correlation matrix according to the correlation between any two charging protocols; Based on the correlation matrix and the scalarized objective dataset, calculating the predicted value of the charging protocol and the uncertainty of the predicted value; Constructing a Gaussian process model of the single-objective sub-problem according to the predicted value and the uncertainty of the predicted value.

[0011] In some embodiments, based on the correlation matrix and the scalarized objective dataset, calculating the predicted value of the charging protocol and the uncertainty of the predicted value includes: ; ; ; ; Among them, represents the predicted value of the charging protocol, represents an N-dimensional full vector, represents the transpose, represents the correlation matrix, represents the inverse transformation of the correlation matrix, represents the set of target values in the scalarized target dataset, represents an N-dimensional vector, represents the uncertainty of the predicted value, represents the N dimension, represents the protocol parameter vector.

[0012] In some embodiments, based on the scalarized source dataset, the Gaussian process model is used to design a transfer acquisition function, solve the transfer acquisition function, and use the electrochemistry-thermal-aging model to evaluate the solution result to determine a set of target charging protocols, including: Based on the scalarized source dataset, use the predicted value and the uncertainty of the predicted value in the Gaussian process model to design a transfer acquisition function; Use an evolutionary algorithm to solve the transfer acquisition function to obtain a new charging protocol; Add the new charging protocol to the first database to obtain an updated database; Use the electrochemistry-thermal-aging model to evaluate the new charging protocol to obtain an evaluation result; According to the evaluation result, select a set of target charging protocols from the updated database.

[0013] In some embodiments, based on the scalarized source dataset, using the predicted value and the uncertainty of the predicted value in the Gaussian process model to design a transfer acquisition function includes: ; ; Among them, represents the transfer acquisition function, represents the predicted value of the charging protocol, represents the balance coefficient, represents the uncertainty of the predicted value, represents the weight term, represents the Gaussian distribution derived from the scalarized source dataset, represents the maximum number of iterations, represents the current iteration number, represents a preset constant, denotes the KL divergence, represents the Gaussian distribution derived from the scalarized target dataset, represents the protocol parameter vector.

[0014] In a second aspect, an embodiment of the present application further provides a multi-objective optimization lithium-ion battery charging design system, the system includes: A first construction unit, configured to construct a constrained multi-objective optimization problem including multiple single-objective sub-problems and constraints, wherein each single-objective sub-problem satisfies the constraints; A second construction unit, configured to construct a first database including multiple first charging protocols and the total objective values corresponding to the first charging protocols by using historical data corresponding to the current battery health state, and construct a second database including multiple second charging protocols and the total objective values corresponding to the second charging protocols by using empirical data corresponding to other battery health states, wherein the total objective value is the total optimization objective in the constrained multi-objective optimization problem corresponding to the charging protocol; A third construction unit, configured to construct an electrochemistry-thermal-aging model and an enhanced Chebyshev function; A first scalarization unit, configured to scalarize the constrained multi-objective optimization problem corresponding to each first charging protocol based on the first database and the enhanced Chebyshev function to obtain a scalarized target dataset; A second scalarization unit, configured to scalarize the constrained multi-objective optimization problem corresponding to each second charging protocol based on the second database and the enhanced Chebyshev function to obtain a scalarized source dataset; A model construction unit, configured to construct a Gaussian process model of the single-objective sub-problem based on the scalarized target dataset; A charging protocol determination unit, configured to design a migration acquisition function based on the scalarized source dataset by using the Gaussian process model, solve the migration acquisition function, and evaluate the solution result by using the electrochemistry-thermal-aging model to determine a set of target charging protocols.

[0015] In a third aspect, an embodiment of the present application further provides an electronic device, including at least one control processor and a memory for communicatively connecting with the at least one control processor; the memory stores instructions executable by the at least one control processor, and the instructions are executed by the at least one control processor to enable the at least one control processor to execute a multi-objective optimization lithium-ion battery charging design method as described above.

[0016] Fourthly, an embodiment of the present application further provides a computer-readable storage medium storing computer-executable instructions for causing a computer to execute a multi-objective optimization method for lithium-ion battery charging design as described above.

[0017] It can be understood that the beneficial effects of the above second to fourth aspects compared with the related art are the same as those of the above first aspect compared with the related art. For relevant descriptions, reference can be made to the relevant descriptions in the above first aspect, which will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and / or additional aspects and advantages of the present application will become apparent and easier to understand from the following description of the embodiments in conjunction with the accompanying drawings, in which: Figure 1 is a schematic flowchart of an embodiment of a multi-objective optimization method for lithium-ion battery charging design provided by the present application; Figure 2 is a schematic diagram for determining a charging protocol in the best embodiment of a multi-objective optimization method for lithium-ion battery charging design provided by the present application; Figure 3 is a schematic diagram of a multi-stage constant current protocol in the best embodiment of a multi-objective optimization method for lithium-ion battery charging design provided by the present application; Figure 4 is a schematic diagram of an electrochemistry-thermal-aging model in the best embodiment of a multi-objective optimization method for lithium-ion battery charging design provided by the present application; Figure 5 is a schematic diagram for charging design using Bayesian optimization in the best embodiment of a multi-objective optimization method for lithium-ion battery charging design provided by the present application; Figure 6 is a schematic diagram of the overall framework of experience-driven multi-objective Bayesian optimization in the best embodiment of a multi-objective optimization method for lithium-ion battery charging design provided by the present application; Figure 7 is a schematic structural diagram of an embodiment of a multi-objective optimization system for lithium-ion battery charging design provided by the present application; Figure 8 is a schematic structural diagram of an embodiment of an electronic device provided by the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] Embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary only for explaining the present application and should not be construed as limiting the present application.

[0020] In the description of this application, if the first, second, etc. are described only for the purpose of distinguishing technical features, they should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features or implicitly specifying the sequence of the indicated technical features.

[0021] In the description of this application, it should be understood that for the orientation description, such as up, down, etc., the indicated orientation or positional relationship is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing this application and simplifying the description, rather than indicating or implying that the indicated device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to this application.

[0022] In the description of this application, it should be noted that unless otherwise clearly defined, words such as setting, installation, connection, etc. should be understood in a broad sense. Those skilled in the art can reasonably determine the specific meanings of the above words in this application in combination with the specific content of the technical solution.

[0023] To accurately evaluate the impact of different charging protocols on battery performance, the academic community generally relies on the coupled electrochemistry-thermal-aging model, which is based on the pseudo-two-dimensional (P2D) electrochemistry equation, heat conduction equation, and solid electrolyte interface membrane (SEI) nucleation and growth kinetic equation. By solving the partial differential equation set, it can accurately reproduce the ion diffusion, electrode reaction, and heat source distribution inside the battery. However, the simulation of the full-order model takes a huge amount of time, which is not conducive to online optimization and large-scale sample screening. For this reason, some people have proposed the equivalent circuit model (ECM) and reduced-order model (ROM) to replace the high-complexity P2D model. ECM uses a series of RC networks to approximate the battery polarization and transmission process, and can estimate the terminal voltage and internal impedance in real time, but the description of the temperature field and aging mechanism is relatively rough; ROM (such as the single-particle model SPM and its coupled thermal-aging extension) simplifies and assumes the key modes of the P2D model, while reducing the calculation amount, retains part of the physical interpretability, but there will still be accuracy deviations under high-rate, low-temperature, or non-uniform boundary conditions.

[0024] To solve the problems of relatively low accuracy of the charging protocol and large simulation time consumption in the existing related battery charging protocol design methods, this application proposes a multi-objective optimization lithium-ion battery charging design method, system, and device.

[0025] Refer to Figure 1 , the flowchart of the multi-objective optimization lithium-ion battery charging design method provided by the embodiment of this application. This multi-objective optimization lithium-ion battery charging design method is applied to an electronic device, and the electronic device can be a server or a mobile terminal, etc. As Figure 1 shown, this multi-objective optimization lithium-ion battery charging design method can include the following steps: Step S100: Construct a constrained multi-objective optimization problem including multiple single-objective sub-problems and constraint conditions, where each single-objective sub-problem satisfies the constraint conditions; Step S200: Construct a first database including multiple first charging protocols and the total objective values corresponding to the first charging protocols by using the historical data corresponding to the current battery health state, and construct a second database including multiple second charging protocols and the total objective values corresponding to the second charging protocols by using the empirical data corresponding to other battery health states, where the total objective value is the overall optimization objective in the constrained multi-objective optimization problem corresponding to the charging protocol; Step S300: Construct an electrochemistry-thermal-aging model and an enhanced Chebyshev function; Step S400: Based on the first database and the enhanced Chebyshev function, scalarize the constrained multi-objective optimization problem corresponding to each first charging protocol to obtain a scalarized objective data set; Step S500: Based on the second database and the enhanced Chebyshev function, scalarize the constrained multi-objective optimization problem corresponding to each second charging protocol to obtain a scalarized source data set; Step S600: Based on the scalarized objective data set, construct a Gaussian process model for the single-objective sub-problem; Step S700: Based on the scalarized source data set, design a transfer acquisition function by using the Gaussian process model, solve the transfer acquisition function, and evaluate the solution result by using the electrochemistry-thermal-aging model to determine a set of target charging protocols.

[0026] In this embodiment, a constrained multi-objective optimization problem including multiple single-object sub-problems and constraint conditions is constructed, where each single-object sub-problem satisfies the constraint conditions; historical data corresponding to the current battery health state is used to construct a first database including multiple first charging protocols and the total objective values corresponding to the first charging protocols, and empirical data corresponding to other battery health states is used to construct a second database including multiple second charging protocols and the total objective values corresponding to the second charging protocols, where the total objective value is the overall optimization objective in the constrained multi-objective optimization problem corresponding to the charging protocol; an electrochemistry-thermal-aging model is constructed, and an enhanced Chebyshev function is constructed; based on the first database and the enhanced Chebyshev function, the constrained multi-objective optimization problem corresponding to each first charging protocol is scalarized to obtain a scalarized objective data set; based on the second database and the enhanced Chebyshev function, the constrained multi-objective optimization problem corresponding to each second charging protocol is scalarized to obtain a scalarized source data set; based on the scalarized objective data set, a Gaussian process model of the single-object sub-problem is constructed; based on the scalarized source data set, a transfer acquisition function is designed using the Gaussian process model, the transfer acquisition function is solved, and the solution result is evaluated using the electrochemistry-thermal-aging model to determine a set of target charging protocols. In this way, by using the enhanced Chebyshev function to realize the scalarization of the charging protocol, and based on the scalarized objective data set, a Gaussian process model of the single-object sub-problem is constructed, and the Gaussian process model is trained with limited real simulation results to realize the rapid prediction and uncertainty evaluation of the scalarized objective of the charging protocol, which can greatly reduce expensive simulation calls, that is, reduce the model simulation time; then the transfer acquisition function is designed using the Gaussian process model, which can effectively combine historical data and empirical data, dynamically adjust the optimization direction, avoid repeated exploration, and quickly generate new charging protocols, that is, improve the accuracy of the charging protocol and improve the charging protocol design efficiency.

[0027] The empirical data corresponding to the above other battery health states may be the empirical data of other battery health states except the current battery health state. For example, the charging design data of the battery at different health state levels represents the corresponding experience.

[0028] The above electrochemistry-thermal-aging model may be a combined model including an electrochemistry model, a thermal model, and an aging model.

[0029] In some embodiments, the electrochemistry-thermal-aging model includes an electrochemistry model, a thermal model, and an aging model. Constructing the electrochemistry-thermal-aging model includes: Constructing the electrochemistry model: ; Constructing the thermal model: ; Construct an aging model: ; Among them, represents the terminal voltage at time represents the solid-phase potential, represents the spatial coordinate, represents the length of the negative electrode, represents the length of the separator, represents the length of the positive electrode, represents the battery density, represents the specific heat capacity, represents the temperature, represents the thermal conductivity, represents the heat generation rate determined by the electrochemical model, represents the lithium-ion loss, represents the reaction current for the formation of the solid electrolyte interface layer, represents the reaction current related to the continuous formation of the surface solid electrolyte interface, represents the reaction current for the formation of a new solid electrolyte interface layer on the cracks of graphite particles.

[0030] In this embodiment, since establishing a battery model that can accurately describe the internal mechanism of the battery and is computationally efficient can effectively solve the difficulties in optimizing the battery charging strategy. By combining the electrochemical model, the thermal model, and the aging model to construct an electrochemical-thermal-aging model (i.e., the battery model), it is possible to accurately simulate a real battery, thereby improving the accuracy of evaluating the performance of the charging protocol in the later stage.

[0031] In some embodiments, construct an enhanced Chebyshev function, including: ; Among them, represents the scalarized objective generated by the enhanced Chebyshev function, represents the number of single-objective sub-problems in the constrained multi-objective optimization problem, represents the weight vector of the th component, represents the protocol parameter vector, represents the th

[0032] normalized single-objective sub-problem in the constrained multi-objective optimization problem,

[0033] In some embodiments, based on the scalarized target dataset, constructing a Gaussian process model for a single-objective sub-problem includes: Using a Gaussian kernel function to quantify the correlation between any two charging protocols in the scalarized target dataset; Constructing a correlation matrix according to the correlation between any two charging protocols; Based on the correlation matrix and the scalarized target dataset, calculating the predicted value of the charging protocol and the uncertainty of the predicted value; Constructing a Gaussian process model for the single-objective sub-problem according to the predicted value and the uncertainty of the predicted value.

[0034] In this embodiment, by using a Gaussian kernel function to quantify the correlation between any two charging protocols in the scalarized target dataset; constructing a correlation matrix according to the correlation between any two charging protocols; based on the correlation matrix and the scalarized target dataset, calculating the predicted value of the charging protocol and the uncertainty of the predicted value; constructing a Gaussian process model for the single-objective sub-problem according to the predicted value and the uncertainty of the predicted value. In this way, based on the scalarized target dataset, a Gaussian process model for the single-objective sub-problem is constructed, and the Gaussian process model is trained with limited real simulation results to achieve rapid prediction and uncertainty evaluation of the scalarized target of the charging protocol, which can significantly reduce expensive simulation calls, that is, reduce the model simulation time.

[0035] In some embodiments, based on the correlation matrix and the scalarized target dataset, calculating the predicted value of the charging protocol and the uncertainty of the predicted value includes: ; ; ; ; wherein, represents the predicted value of the charging protocol, represents an N-dimensional all- vector, represents the transpose, represents the correlation matrix, represents the inverse transformation of the correlation matrix, represents the set of target values in the scalarized target dataset, represents an N-dimensional vector, represents the uncertainty of the predicted value, represents the N dimension, represents the protocol parameter vector.

[0036] In some embodiments, based on the scalarized source dataset, a Gaussian process model is used to design a transfer acquisition function, the transfer acquisition function is solved, and an electrochemistry-thermal-aging model is used to evaluate the solution result to determine a set of target charging protocols, including: Based on the scalarized source dataset, use the predicted value and the uncertainty of the predicted value in the Gaussian process model to design a transfer acquisition function; Use an evolutionary algorithm to solve the transfer acquisition function to obtain a new charging protocol; Add the new charging protocol to the first database to obtain an updated database; Use an electrochemistry-thermal-aging model to evaluate the new charging protocol to obtain an evaluation result; According to the evaluation result, select a set of target charging protocols from the updated database.

[0037] In this embodiment, by using the predicted value and the uncertainty of the predicted value in the Gaussian process model based on the scalarized source dataset, a transfer acquisition function is designed; an evolutionary algorithm is used to solve the transfer acquisition function to obtain a new charging protocol; the new charging protocol is added to the first database to obtain an updated database; an electrochemistry-thermal-aging model is used to evaluate the new charging protocol to obtain an evaluation result; according to the evaluation result, a set of target charging protocols is selected from the updated database. In this way, through the designed transfer acquisition function, historical data and empirical data can be effectively combined, the optimization direction can be dynamically adjusted, repeated exploration can be avoided, and new charging protocols can be generated quickly, that is, the accuracy of the charging protocol is improved and the design efficiency of the charging protocol is also improved.

[0038] In some embodiments, based on the scalarized source dataset, using the predicted value and the uncertainty of the predicted value in the Gaussian process model to design a transfer acquisition function, including: ; ; wherein, represents the transfer acquisition function, represents the predicted value of the charging protocol, represents the balance coefficient, represents the uncertainty of the predicted value, represents the weight term, represents the Gaussian distribution derived from the scalarized source dataset, represents the maximum number of iterations, represents the current iteration number, represents the preset constant, represents the KL divergence, represents the Gaussian distribution derived from the scalarized target dataset, represents the protocol parameter vector.

[0039] In this embodiment, by designing a transfer acquisition function based on a scalarized source dataset and using the predicted values and uncertainties of the predicted values in the Gaussian process model, the historical optimization data in a high health state can be modeled as a Gaussian distribution, and its similarity to the current health state (SOH) task can be quantified by KL divergence to dynamically adjust the empirical weights , avoiding interference from irrelevant experiences (negative transfer). Cross-SOH experience reuse is achieved, reducing repeated exploration.

[0040] For the convenience of those skilled in the art to understand, the following provides a set of best embodiments: As the most popular energy storage device at present, lithium-ion batteries have been widely used in many fields such as electric vehicles, portable electronic devices, and clean energy storage due to their high energy density, high power density, long cycle life, good safety, and relatively friendly environment. However, the long charging time caused by slow charging speed and the battery performance degradation caused by fast charging are still the key problems hindering the further promotion and development of lithium-ion batteries. Therefore, the charging problem of lithium-ion batteries is an important topic. Given a fixed battery capacity, optimizing the battery charging process and designing an efficient charging strategy can effectively reduce the charging time while ensuring the battery health state, thus bringing convenience to the users of lithium-ion battery products. The design process of the lithium-ion battery charging protocol is essentially a constrained multi-objective optimization problem (CMOP) because an ideal optimal charging strategy should not only significantly shorten the charging time but also ensure the safety of the charging process and minimize the battery aging caused by charging. It can be seen that optimizing the charging strategy requires balancing objectives such as charging time ( ), peak temperature ( ), and lithium-ion loss ( ), while satisfying dynamic constraints such as current, voltage, temperature, and SOC.

[0041] To accurately evaluate the impact of different charging protocols on battery performance, the academic community generally relies on a coupled electrochemical-thermal-aging model, which is based on pseudo-two-dimensional (P2D) electrochemical equations, heat conduction equations, and SEI nucleation and growth kinetic equations, and accurately reproduces the internal ion diffusion, electrode reactions, and heat source distribution in the battery by solving a system of partial differential equations. However, the simulation of the full-order model is extremely time-consuming, which is not conducive to online optimization and large-scale sample screening. For this reason, some people have proposed an equivalent circuit model (ECM) and a reduced-order model (ROM) to replace the high-complexity P2D model: The ECM uses a series of RC networks to approximate the battery polarization and transmission processes, and can estimate the terminal voltage and internal impedance in real time. However, its description of the temperature field and aging mechanism is relatively rough. The ROM (such as the single particle model SPM and its coupled thermal-aging extension) simplifies and assumes the key modes of the P2D model, reducing the computational cost while retaining some physical interpretability. However, accuracy deviations still occur under high rate, low temperature, or non-uniform boundary conditions.

[0042] The existing related technologies have the following disadvantages: 1. The simulation cost of high-fidelity battery models is extremely high: The full-order electrochemistry-thermal-aging model requires solving a coupled partial differential equation system, and each single simulation takes a long time, making it difficult to meet the requirements of online or real-time optimization.

[0043] 2. The accuracy of equivalent circuit and reduced-order models is insufficient: Although ECM and ROM (such as the single particle model) can accelerate the calculation, due to simplifying assumptions, it is difficult to accurately describe the temperature field and aging mechanism under high-rate fast charging, affecting the reliability of the optimization results.

[0044] 3. Data starvation in multi-objective Bayesian optimization: Existing multi-objective BO methods (such as the framework based on Chebyshev decomposition) require a large number of simulation samples to converge when jointly optimizing the three objectives of charging time, peak temperature, and capacity decay, resulting in low optimization efficiency.

[0045] 4. Lack of cross-health state experience transfer: As the battery ages during use, the optimal charging protocol varies with the state of health (SOH). Existing methods need to optimize from scratch for each SOH, causing serious waste of computing power and response delay.

[0046] To solve the problems existing in the prior art, this embodiment proposes an experience-driven multi-objective Bayesian optimization algorithm (EIMO). Experience transfer is introduced under the decomposed multi-objective BO framework, and the optimal protocol data at the historical SOH level is used to accelerate the optimization at the current SOH. By constructing a Gaussian process model, the GP model is trained with limited real simulation results to achieve fast prediction and uncertainty assessment of the charging protocol scalarization objective (enhanced Tchebycheff function), significantly reducing expensive simulation calls. By designing a transfer acquisition function, on the basis of the common lower confidence bound (LCB) acquisition function, an empirical distribution term is introduced, and the balance between experience and exploration / exploitation is adjusted through an adaptive weight to accelerate the exploration of the optimal protocol. This embodiment designs an adaptive empirical weight strategy, which dynamically adjusts according to the KL divergence between the empirical distribution and the current surrogate distribution , ensure that experience is fully utilized in similar tasks, optimize the gradual dependence on real-time data in the later stage, and avoid negative transfer. Finally, this embodiment realizes an efficient, online, and cross-SOH adaptive charging design, providing new methodological support for intelligent charging management and promoting the development of related industries.

[0047] The technical solution of this embodiment specifically includes the following content: As Figure 2 shown, the charging design problem determines the charging protocol through an optimization technique considering the battery state, which is usually constructed as a constrained multi-objective optimization problem (CMOP). Generally speaking, a higher charging current can shorten the charging time, but it will lead to higher voltage temperature peaks and shorter service life, and it needs to simultaneously meet the conflicting requirements in terms of rapidity, safety, and sustainability. Considering these different requirements, the charging protocol design problem can be constructed as a multi-objective optimization problem, and the optimization objectives of the multi-objective optimization problem are defined as follows: (1); Among them, is the charging time, representing the objective in terms of rapidity, is the peak temperature during the charging process, representing the objective in terms of safety, and These two objective values can be directly obtained from the state variables calculated by battery simulation, is the battery capacity attenuation caused by the charging process, calculated through the aging model: (2); Among them, is the amount of electricity increased in one charge, is the total available cycle charge and discharge amount under the current strategy, calculated by formula (3).

[0048] (3); Among them, represents a non-linear aging function used to describe the impact of relevant battery state variables on battery capacity attenuation, represents the exponential factor, represents the average SOC of the lithium-ion battery in one charging cycle, represents the average input current magnitude, represents the average battery temperature.

[0049] To ensure the safety of the charging process, the following constraint conditions also need to be considered: (4); Among them, represents the battery temperature, represents the terminal voltage, represents the state of charge (SOC) of the battery, represents the input current. represents the starting time, represents the initial temperature, represents the upper limit of the battery temperature. and represent the upper and lower limits of the SOC of the battery respectively, and represent the upper and lower limits of the terminal voltage respectively, and represent the upper and lower limits of the input current respectively. The above constraints include the limitations on the battery voltage and battery temperature, the limitation on the input current, and the definition of the SOC range during charging.

[0050] Considering that the multi-stage constant current (MCC) protocol has no slow constant voltage stage and no rest stage, and has higher charging efficiency, this embodiment takes the MCC protocol as the optimization object. As Figure 3 shown, the MCC protocol divides the charging process into stages. Each stage charges the battery with an independent current. The goal of the MCC protocol is to increase the SOC of the battery from the minimum value to the maximum value . In the th stage, the charging current is , the charging amount is , and the charging time is . For simplicity of representation, a protocol parameter vector can be used to describe the MCC protocol. Generally speaking, increasing the number of stages in the protocol can improve its theoretical optimal performance, but it will also introduce a larger parameter space, increase the complexity of the optimization task, and make it more difficult to search for the optimal protocol.

[0051] Establishing a battery model that can accurately describe the internal mechanism of the battery and is computationally efficient can effectively solve the difficulties in the above charging strategy optimization. According to different modeling process objects, battery models can be divided into electrochemical models, thermal models, and aging models, as Figure 4 shown. Electrochemical models are used to describe the electrochemical kinetics inside lithium-ion batteries. The pseudo-two-dimensional (P2D) model based on solution theory, porous electrode theory, and kinetic equations is well-known for its ability to accurately simulate real batteries. Specifically, this model consists of a set of partial differential equations and algebraic equations, which are used to describe the internal dynamics of the battery. Based on these equations, when a given input current is applied, the terminal voltage is calculated as follows: (5); where, represents the solid-phase potential, represent spatial coordinates, , and represent the length of the negative electrode, the length of the separator, and the length of the positive electrode, respectively.

[0052] The thermal model is used to represent the temperature distribution within the lithium-ion battery. In this embodiment, a thermal model widely applied to cylindrical batteries is adopted: (6); This model needs to satisfy the boundary conditions: (7); (8); and the initial condition constraints: (9); wherein, is the spatial coordinate, represents the temperature, represents the battery density, is the specific heat capacity, represents the thermal conductivity, is the heat generation rate determined by the electrochemical model, is the specific thermal conductivity, represents the non-uniform Robin boundary, is the heat transfer coefficient, is the ambient temperature, is the initial temperature.

[0053] The aging model is used to describe the capacity decay of the lithium-ion battery. In this embodiment, an aging model based on physical principles is adopted. This model reflects the degradation of the battery by simulating the formation of the solid electrolyte interface (SEI) layer. Specifically, the description of lithium-ion loss (represented as ) is as follows: (10); wherein, represents the reaction current for SEI formation, is the reaction current related to the continuous formation of the surface SEI, represents the reaction current for the formation of a new SEI layer on the graphite particle cracks.

[0054] The combination of the above models constitutes an electrochemical-thermal-aging model. Since the solution of partial differential equations is involved, each simulation of this model is time-consuming. Therefore, when using this model for charging design, it is crucial to develop appropriate optimization techniques to accelerate the design process.

[0055] In the constrained multi-objective optimization problem that formulates the charging design problem, Bayesian optimization has been applied to the design of charging protocols (i.e., the multi-stage constant current (MCC) protocol). Although it can accelerate the design process by constructing an informative surrogate model using the least number of evaluation samples, Bayesian optimization often has the problem of high data requirements when solving the CMOP problem. In fact, the experience of other similar scenarios can be used to reduce the dependence on the data of the current task. For charging design, the experience obtained from lithium-ion batteries in different states of health (SOH) can be used to optimize the charging protocol of the battery at the current SOH. As Figure 5 shown, the EIMO proposed in this embodiment uses Bayesian optimization for charging design and combines transfer learning to integrate the historical data at the current SOH level with the experience at a higher SOH level, further improving the efficiency.

[0056] The framework schematic diagram of EIMO is as Figure 6 shown. First, a database is constructed by sampling a set of charging protocols and evaluating the corresponding battery states. The charging design problem described by equations (1) and (4) is decomposed into several single-objective sub-problems. In each iteration, a sub-problem is randomly selected, and Bayesian optimization is used to generate a new charging protocol for this sub-problem. Specifically, Bayesian optimization consists of two key parts: the Gaussian process (GP) model and the acquisition function. The GP model is used to approximate the time-consuming electrochemical-thermal-aging model in the previous text, while the acquisition function is used to sample new charging protocols. The GP model is constructed using the historical data in the database, and a transfer learning technique is proposed to integrate the historical data and the empirical data into the formulation of the acquisition function. By solving the acquisition function using an evolutionary algorithm, a new charging protocol is obtained. Then, this charging protocol is evaluated using the electrochemical-thermal-aging model and added to the database. Repeat this process until the computing resources are exhausted, and then select and output the optimal set of charging protocols (i.e., the set of optimal charging protocols that meet the various needs of users) from the database.

[0057] The main steps of EIMO include initialization, problem decomposition, GP modeling, and transfer acquisition function, which are specifically as follows: 1. Initialization: Set the initial number of iterations to 0. Next, randomly sample charging protocols at the current SOH level and evaluate them. Based on these protocols, construct a database (i.e., the first database), denoted as , where and represent the th sampled charging protocol and its corresponding total objective value (the total objective value is the overall optimization objective, that is ). Here, data from other scenarios, such as the charging design data of the battery at different SOH levels, represents the corresponding experience. These data are integrated into an experience database (i.e., the second database) where and respectively represent the th charging protocol sampled from other SOH levels and its corresponding total target value, represents the total charging protocol sampled at the SOH level, represents the set of charging protocols sampled from other state of health (SOH) levels, represents the relative to the set of target values corresponding to the charging protocols in, represents multiple stages of the charging process.

[0058] 2. Problem decomposition: EIMO uses a decomposition method to solve the target CMOP problem. In each iteration a weight vector is randomly selected from a predefined set generated using the Riesz s - energy method, where the Riesz s - energy in this embodiment is prior art and will not be specifically described in this embodiment. For details, refer to the document "Rieszs - energy - based Reference Sets for Multi - Objective optimization". Using the selected weight vector, based on and the enhanced Chebyshev function, scalarized objectives are generated in the target data set to obtain the scalarized target data set , where (11); where represents the scalarized objective generated by the enhanced Chebyshev function, represents the protocol parameter vector, is the number of single - objective sub - problems of the target CMOP problem, is the th normalized single - objective sub - problem of the target CMOP, is the th component of, is a small positive weight. Note that the normalization formula for the th single - objective sub - problem is as follows: (12); Among them, is the original objective function corresponding to the th single-objective sub-problem, and are the maximum and minimum values of the th single-objective sub-problem in the data set (i.e., ). In the same way, based on and the enhanced Chebyshev function, a scalarized source data set can also be generated.

[0059] 3. GP Modeling: For the selected single-objective sub-problem, construct a GP model, denoted as , to approximate the Chebyshev scalarized objective based on the data set , so as to accelerate the design process: (13); (14); (15); (16); Among them, represents the set of objective values after enhanced Chebyshev scalarization processing in the scalarized objective data set , represents the predicted value, represents the uncertainty of the predicted value, 1 is a -dimensional (i.e., N = 3M) all-ones vector, is an (N×N) matrix (i.e., the correlation matrix), and its element ), represents the th sampled charging protocol in the objective data set , , is a N -dimensional vector, and its element ). Here, represents the correlation (i.e., the degree of correlation) between two vectors, which is quantified by the Gaussian kernel function: (17); Among them, is a weight parameter, and are respectively the and th -dimensional components.

[0060] 4. Migration acquisition function: In traditional Bayesian optimization, a migration acquisition function is designed using the GP model to sample a new decision vector that can effectively balance exploitation and exploration. To effectively combine data with experience, EIMO introduces a migration acquisition function (denoted as ), which combines the representing experience: (18); As shown in Equation (18), consists of three key parts: the lower confidence bound (LCB) , the term representing experience , and the weight term .

[0061] The LCB is a commonly used sampling criterion in traditional Bayesian optimization, known for its ability to effectively balance exploitation and exploration. Specifically, minimizing helps with exploitation in promising regions with good objective values, while minimizing ( ) encourages exploration in the decision space with high uncertainty. By appropriately setting , a balance between exploitation and exploration can be achieved. is a Gaussian distribution derived from . First, best decision vectors are selected from . Then, the mean and covariance matrix are calculated using the maximum likelihood estimation method. Intuitively, decision vectors with larger values may perform well in scenarios where the battery charging protocol at different SOH levels is optimized. Since these scenarios are similar to the current task, minimizing ( ) can utilize the experience of these scenarios to accelerate the design process.

[0062] The weight controls the impact of experience on the optimization process. There are two reasons for adjusting : First, to ensure that experience has a greater influence when is very similar to ; Second, as the optimization progresses and new data continuously increases, the influence of experience should gradually weaken to reduce the risk of negative transfer.

[0063] Based on the above considerations, adopts the following adaptive adjustment method: (19); where is the Kullback-Leibler (KL) divergence, used to quantify and the similarity between and is derived in the same way from , which is a Gaussian distribution derived from . is the maximum number of iterations, is a preset constant. As shown in formula (19), is jointly affected by the KL divergence and the number of iterations . The addition of the KL divergence term aims to encourage the EIMO to transfer more experience when and show a high degree of similarity. The smaller the KL divergence, and the higher the similarity between them. In addition, the introduction of is to guide the EIMO to mainly rely on experience at the initial stage of optimization, and gradually reduce the influence of experience as the optimization progresses. This adjustment strategy is consistent with the above analysis.

[0064] The evolutionary algorithm is used to solve the transfer acquisition function, and a new protocol (denoted as ) is obtained. Then, the electrochemical-thermal-aging model is used to evaluate and append it to . The above process is repeated until the computing resources are exhausted (i.e., ).

[0065] The above evolutionary algorithm is an "algorithm cluster". Although it has many variations, with different genetic gene expression methods, different crossover and mutation operators, the reference of special operators, and different regeneration and selection methods, their inspiration comes from the biological evolution of nature. Compared with traditional optimization algorithms such as the calculus-based method and the exhaustive method, evolutionary computation is a mature global optimization method with high robustness and wide applicability, with the characteristics of self-organization, self-adaptation, and self-learning, and can effectively handle complex problems that are difficult to solve by traditional optimization algorithms without being restricted by the nature of the problem.

[0066] Compared with the prior art, the technical solution of this embodiment has the following advantages: 1. This embodiment adopts the transfer learning technology driven by distribution similarity, models the historical optimization data in the high health state as a Gaussian distribution , quantifies its similarity with the current SOH task through the KL divergence, and dynamically adjusts the experience weight ( ), avoiding the interference of irrelevant experience (negative transfer). The cross-SOH experience reuse in this embodiment can significantly reduce the number of simulations. This embodiment integrates high-SOH historical data (such as the optimization experience with SOH = 1.0) through transfer learning, dynamically adjusts the optimization direction, and avoids repeated exploration.

[0067] 2. This embodiment adopts the design of a transfer acquisition function that fuses experience. Based on the LCB of traditional Bayesian optimization, an experience term ( ) is introduced to form a transfer acquisition function. And through LCB, the exploration and exploitation are balanced. The experience term guides the search towards the historical optimal solution region, accelerating the convergence to the high-quality Pareto front and improving the convergence and distribution uniformity of the solution set.

[0068] 3. This embodiment adopts a decomposed multi-objective optimization and evolutionary solution framework, uses the Riesz s-energy method to generate a set of uniformly distributed weight vectors, covering diverse user requirements (such as fast charging, low temperature, and low attenuation), and avoids the sparsity problem of traditional uniform sampling. At the same time, this embodiment combines the differential evolution algorithm to solve the high-dimensional non-convex transfer acquisition function, supports the optimization of the multi-stage constant current charging (MCC) protocol, and reduces the calculation time by 23% - 41%.

[0069] 4. This embodiment dynamically adapts to battery aging and supports full-life cycle management. By quantifying the similarity between the experience and the current SOH using KL divergence, the transfer weight ( ) is dynamically adjusted to avoid negative transfer, without the need to optimize from scratch for each SOH, and new protocols are quickly generated using historical experience.

[0070] Referring to Figure 7 , the embodiment of the present application also provides a multi-objective optimization lithium-ion battery charging design system, which includes a first construction unit 100, a second construction unit 200, a third construction unit 300, a first scalarization unit 400, a second scalarization unit 500, a model construction unit 600, and a charging protocol determination unit 700, where: The first construction unit 100 is used to construct a constrained multi-objective optimization problem including multiple single-objective sub-problems and constraint conditions, where each single-objective sub-problem satisfies the constraint conditions; The second construction unit 200 is used to construct a first database including multiple first charging protocols and the total objective values corresponding to the first charging protocols using the historical data corresponding to the current battery health state, and construct a second database including multiple second charging protocols and the total objective values corresponding to the second charging protocols using the experience data corresponding to other battery health states, where the total objective value is the total optimization objective in the constrained multi-objective optimization problem corresponding to the charging protocol; The third construction unit 300 is used to construct an electrochemistry-thermal-aging model and an enhanced Chebyshev function; The first scalarization unit 400 is configured to scalarize the constrained multi-objective optimization problem corresponding to each first charging protocol based on the first database and the enhanced Chebyshev function, so as to obtain a scalarized target data set; The second scalarization unit 500 is configured to scalarize the constrained multi-objective optimization problem corresponding to each second charging protocol based on the second database and the enhanced Chebyshev function, so as to obtain a scalarized source data set; The model construction unit 600 is configured to construct a Gaussian process model of a single-objective sub-problem based on the scalarized target data set; The charging protocol determination unit 700 is configured to design a transfer acquisition function by using the Gaussian process model based on the scalarized source data set, solve the transfer acquisition function, and evaluate the solution result by using the electrochemical-thermal-aging model, so as to determine a set of target charging protocols.

[0071] It should be noted that since the multi-objective optimization lithium-ion battery charging design system in this embodiment and the above-mentioned multi-objective optimization lithium-ion battery charging design method are based on the same inventive concept, the corresponding content in the method embodiment is equally applicable to the system embodiment of the present application, and will not be elaborated here.

[0072] Referring to Figure 8 , an electronic device is further provided in an embodiment of the present application. The electronic device includes: At least one memory; At least one processor; At least one program; The program is stored in the memory, and the processor executes at least one program to implement the multi-objective optimization lithium-ion battery charging design method described above in the present disclosure.

[0073] The electronic device may be any intelligent terminal including a mobile phone, a tablet computer, a personal digital assistant (PDA), an in-vehicle computer, etc.

[0074] The electronic device in the embodiment of the present application will be introduced in detail below.

[0075] The processor 1600 may be implemented by using a general-purpose central processing unit (CPU), a microprocessor, an application specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is configured to execute relevant programs to implement the technical solutions provided in the embodiments of the present disclosure; The memory 1700 can be implemented in the form of a read only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM), etc. The memory 1700 can store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 1700 and are called by the processor 1600 to execute the multi-objective optimization lithium-ion battery charging design method of the embodiments of the present disclosure.

[0076] The input / output interface 1800 is used to implement information input and output; The communication interface 1900 is used to implement communication interaction between this device and other devices. It can achieve communication through a wired method (such as USB, network cable, etc.) or through a wireless method (such as a mobile network, WIFI, Bluetooth, etc.); The bus 2000 transmits information between the various components of the device (such as the processor 1600, the memory 1700, the input / output interface 1800, and the communication interface 1900); Among them, the processor 1600, the memory 1700, the input / output interface 1800, and the communication interface 1900 are communicatively connected to each other inside the device through the bus 2000.

[0077] The embodiments of the present disclosure also provide a storage medium, which is a computer-readable storage medium. The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to cause a computer to execute the above-mentioned multi-objective optimization lithium-ion battery charging design method.

[0078] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory can include a high-speed random access memory, and can also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory optionally includes a memory remotely provided relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above networks include, but are not limited to, the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0079] The embodiments described in the embodiments of the present disclosure are for more clearly illustrating the technical solutions of the embodiments of the present disclosure, and do not constitute a limitation on the technical solutions provided by the embodiments of the present disclosure. Those skilled in the art can know that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present disclosure are equally applicable to similar technical problems.

[0080] Those skilled in the art can understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present disclosure, and may include more or fewer steps than those shown in the figures, or combine some steps, or different steps.

[0081] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0082] Those of ordinary skill in the art can understand that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, and their appropriate combinations.

[0083] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of this application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0084] It should be understood that in this application, "at least one (item)" means one or more, and "a plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" may mean: only A exists, only B exists, and both A and B exist at the same time. Among them, A and B can be singular or plural. The character " / " generally means that the associated objects before and after are in an "or" relationship. "At least one (one) of the following" or a similar expression means any combination of these items, including any combination of single items (ones) or plural items (ones). For example, at least one (one) of a, b, or c may mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0085] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical or other forms.

[0086] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0087] In addition, the functional units in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0088] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions for causing an electronic device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of the present application. The foregoing storage medium includes: various media that can store programs such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs. The embodiments of the present application have been described in detail above with reference to the drawings, but the present application is not limited to the above embodiments. Within the knowledge scope of those of ordinary skill in the art to which the present application pertains, various changes can be made without departing from the purpose of the present application.

[0089] The embodiments of the present application have been described in detail above with reference to the drawings, but the present application is not limited to the above embodiments. Within the knowledge scope of those of ordinary skill in the art to which the present application pertains, various changes can be made without departing from the purpose of the present application.

Claims

1. A multi-objective optimization method for lithium-ion battery charging design, characterized in that The method includes: Constructing a constrained multi-objective optimization problem including multiple single-objective sub-problems and constraint conditions, where each single-objective sub-problem satisfies the constraint conditions; Using historical data corresponding to the current battery health state to construct a first database including multiple first charging protocols and the total objective values corresponding to the first charging protocols, and using empirical data corresponding to other battery health states to construct a second database including multiple second charging protocols and the total objective values corresponding to the second charging protocols, where the total objective value is the total optimization objective in the constrained multi-objective optimization problem corresponding to the charging protocol; Constructing an electrochemistry-thermal-aging model, and constructing an enhanced Chebyshev function; Based on the first database and the enhanced Chebyshev function, scalarizing the constrained multi-objective optimization problem corresponding to each first charging protocol to obtain a scalarized objective data set; Based on the second database and the enhanced Chebyshev function, scalarizing the constrained multi-objective optimization problem corresponding to each second charging protocol to obtain a scalarized source data set; Based on the scalarized objective data set, constructing a Gaussian process model for the single-objective sub-problem; Based on the scalarized source data set, using the Gaussian process model to design a transfer acquisition function, solving the transfer acquisition function, and using the electrochemistry-thermal-aging model to evaluate the solution result to determine a set of target charging protocols.

2. The multi-objective optimization method for lithium-ion battery charging design according to claim 1, characterized in that The electrochemistry-thermal-aging model includes an electrochemistry model, a thermal model, and an aging model. The constructing of the electrochemistry-thermal-aging model includes: Constructing an electrochemistry model: ； Constructing a thermal model: ； Constructing an aging model: ； Among them, represents the terminal voltage at a moment, represents the solid-phase potential, represents the spatial coordinate, represents the length of the negative electrode, represents the length of the separator, represents the length of the positive electrode, represents the battery density, represents the specific heat capacity, represents the temperature, represents the thermal conductivity, represents the heat generation rate determined by the electrochemical model, represents the lithium-ion loss, represents the reaction current for the formation of the solid electrolyte interphase layer, represents the reaction current related to the continuous formation of the surface solid electrolyte interphase, represents the reaction current for the formation of a new solid electrolyte interphase layer on the cracks of graphite particles.

3. The multi-objective optimization method for lithium-ion battery charging design according to claim 1, characterized in that, The constructing of the enhanced Chebyshev function includes: ； Among them, represents the scalarized objective generated by the enhanced Chebyshev function, represents the number of single-objective subproblems in the constrained multi-objective optimization problem, represents the weight vector the -th component of represents the protocol parameter vector, represents the -th normalized single-objective subproblem in the constrained multi-objective optimization problem, represents the positive weight coefficient.

4. The multi-objective optimization method for lithium-ion battery charging design according to claim 1, wherein The constructing of the Gaussian process model for the single-objective sub-problem based on the scalarized objective data set includes: Using a Gaussian kernel function to quantify the correlation between any two charging protocols in the scalarized objective data set; Constructing a correlation matrix according to the correlation between any two charging protocols; Based on the correlation matrix and the scalarized objective data set, calculating the predicted value of the charging protocol and the uncertainty of the predicted value; Constructing a Gaussian process model for the single-objective sub-problem according to the predicted value and the uncertainty of the predicted value.

5. The multi-objective optimization lithium-ion battery charging design method according to claim 4, characterized in that The calculating of the predicted value of the charging protocol and the uncertainty of the predicted value based on the correlation matrix and the scalarized objective data set includes: ； ； ； ； Among them, represents the predicted value of the charging protocol, represents an N-dimensional full vector, represents the transpose, represents the correlation matrix, represents the inverse transformation of the correlation matrix, represents the set of target values in the scalarized target dataset, represents an N-dimensional vector, represents the uncertainty of the predicted value, represents the N dimension, represents the protocol parameter vector.

6. The multi-objective optimization method for lithium-ion battery charging design according to claim 1, wherein The determining of a set of target charging protocols based on the scalarized source data set, using the Gaussian process model to design a transfer acquisition function, solving the transfer acquisition function, and using the electrochemistry-thermal-aging model to evaluate the solution result includes: Based on the scalarized source data set, using the predicted value and the uncertainty of the predicted value in the Gaussian process model to design a transfer acquisition function; Using an evolutionary algorithm to solve the transfer acquisition function to obtain a new charging protocol; Adding the new charging protocol to the first database to obtain an updated database; Using the electrochemistry-thermal-aging model to evaluate the new charging protocol to obtain an evaluation result; Based on the evaluation results, select a set of target charging protocols from the updated database.

7. The multi-objective optimization method for lithium-ion battery charging design according to claim 6, characterized in that, Based on the scalarized source dataset, designing a transfer acquisition function by using the predicted value and the uncertainty of the predicted value in the Gaussian process model, including: ； ； Among them, represents the migration acquisition function, represents the predicted value of the charging protocol, represents the balance coefficient, represents the uncertainty of the predicted value, represents the weight term, represents the Gaussian distribution derived from the scalarized source dataset, represents the maximum number of iterations, represents the current number of iterations, represents the preset constant, represents the KL divergence, represents the Gaussian distribution derived from the scalarized target dataset, represents the protocol parameter vector.

8. A lithium-ion battery charging design system for multi-objective optimization, characterized in that, The system includes: A first construction unit, configured to construct a constrained multi-objective optimization problem including a plurality of single-objective sub-problems and constraints, wherein each single-objective sub-problem satisfies the constraints; A second construction unit, configured to construct a first database including a plurality of first charging protocols and the total objective values corresponding to the first charging protocols by using the historical data corresponding to the current battery health state, and construct a second database including a plurality of second charging protocols and the total objective values corresponding to the second charging protocols by using the empirical data corresponding to other battery health states, wherein the total objective value is the total optimization objective in the constrained multi-objective optimization problem corresponding to the charging protocol; A third construction unit, configured to construct an electrochemistry-thermal-aging model and an enhanced Chebyshev function; A first scalarization unit, configured to scalarize the constrained multi-objective optimization problem corresponding to each first charging protocol based on the first database and the enhanced Chebyshev function to obtain a scalarized target dataset; A second scalarization unit, configured to scalarize the constrained multi-objective optimization problem corresponding to each second charging protocol based on the second database and the enhanced Chebyshev function to obtain a scalarized source dataset; A model construction unit, configured to construct a Gaussian process model of the single-objective sub-problem based on the scalarized target dataset; A charging protocol determination unit, configured to design a transfer acquisition function by using the Gaussian process model based on the scalarized source dataset, solve the transfer acquisition function, and evaluate the solution result by using the electrochemistry-thermal-aging model to determine a set of target charging protocols.

9. An electronic device, characterized in that, Including at least one control processor and a memory for communicatively connecting with the at least one control processor; the memory stores instructions executable by the at least one control processor, and the instructions are executed by the at least one control processor so that the at least one control processor can execute the multi-objective optimization lithium-ion battery charging design method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions for causing a computer to execute the multi-objective optimization lithium-ion battery charging design method according to any one of claims 1 to 7.

Images