Battery SOP rapid prediction method based on electrochemical model

Abstract

The invention relates to the technical field of battery SOP prediction, and discloses a battery SOP rapid prediction method based on an electrochemical model, and the method comprises the following steps: simplifying a P2D model into an e-SPM model, and coupling the e-SPM model with a thermal model to obtain an electrothermal coupling model; respectively identifying thermal parameters and electrochemical parameters of the electrothermal coupling model through a variable-scale multi-target grey wolf optimization algorithm, and observing internal and external states of the battery by using unscented Kalman filtering as a state observer of the electrochemical model; according to the method, 21 electrochemical model parameters are quickly identified through a variable-scale multi-target grey wolf optimization algorithm, and the problem of non-convergence in the optimization process is avoided by changing the input identification scale strategy in the optimization process; through a multi-target strategy, the proportion of fitness values of various working conditions is selected through weights, and the problem of overfitting in parameter identification is avoided.

Description

Technical Field

[0001] The invention relates to the technical field of battery SOP prediction, and in particular to a battery SOP rapid prediction method based on an electrochemical model. Background Art

[0002] In order to cope with the growing environmental pollution and energy crisis, the development of clean energy has become a global urgent task and an important trend. Due to the advantages of high specific energy, fast charging speed and long life, lithium-ion batteries have been widely used, especially in the field of electric vehicles and energy storage power stations. However, in practical applications, some safety issues may occur (e.g., thermal runaway, internal short circuit, overcharge and over-discharge). Therefore, to ensure that the battery operates in a safe working state, a battery management system BMS is needed to monitor the operating state of the battery, including the battery's state of charge SOC and power state SOP. SOC is defined as the ratio of the current remaining capacity of the battery to the maximum capacity. Accurate SOC can be overcharged or over-discharged. SOP is defined in most studies as the peak power capacity of the battery within a specified prediction time without exceeding the SOA boundary. However, since SOP cannot be measured and its size is related to the state of the battery, accurate SOP prediction remains challenging.

[0003] At present, the equivalent circuit model is mainly used for online prediction of lithium-ion battery SOP. However, the equivalent circuit model is difficult to reflect the physical state inside the battery. It only limits the maximum current based on external signals, so it is difficult to ensure the safety of the battery and the accuracy of power prediction. When using electrochemical models for online prediction of SOP, most of them currently only use the surface lithium ion concentration as the safety area, without considering other internal states and the influence of temperature and temperature on internal parameters. Therefore, it is unsafe to obtain the maximum power. Time is also a major problem. Due to the slow convergence speed of the dichotomy method, it is difficult to meet online application. Therefore, a battery SOP fast prediction method based on electrochemical model is proposed. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention provides a method for quickly predicting battery SOP based on an electrochemical model, which has the advantages of faster SOP prediction time and shortening the calculation time of the dichotomy without losing accuracy, thereby solving the problems mentioned in the above background technology.

[0005] In order to achieve the above-mentioned SOP prediction time is faster and shorten the calculation time of the dichotomy without losing accuracy, the present invention provides the following technical solution: a battery SOP fast prediction method based on an electrochemical model, comprising the following steps: S1: Simplify the P2D model into the e-SPM model and couple it with the thermal model to obtain the electrothermal coupling model; S2: The thermal parameters and electrochemical parameters of the electrothermal coupling model are identified separately by the variable-scale multi-objective grey wolf optimization algorithm; S3: Use the unscented Kalman filter as the state observer of the electrochemical model to observe the internal and external states of the battery; S4: Select surface lithium ion concentration, electrolyte concentration, lithium plating overpotential, voltage, SOC, and temperature as safety constraints for SOP, select the binary method to predict the SOP of the battery at different time scales, and select Gaussian process regression to accelerate the convergence speed of the binary method to predict the battery SOP.

[0006] Preferably, the step S2 is specifically: S2.1: Using 1C discharge and DST dynamic conditions as the target fitness function of the variable-scale multi-objective grey wolf optimization algorithm, the simulated voltage V of the electrothermal coupling model is obtained. sim and the actual voltage V exp The fitness value fv of the mean square error between is expressed as: ; Where N is the number of voltage samples collected, V exp is the actual voltage, V sim is the analog voltage; S2.2: Calculate the absolute value fc of the difference between the positive electrode capacity and the negative electrode capacity, expressed as: ; Where A is the electrode area, L + is the thickness of the positive electrode, L - Negative electrode thickness, is the volume fraction of the positive electrode solid phase, is the volume fraction of the positive electrode solid phase, is the maximum lithium ion concentration at the positive electrode, is the maximum lithium ion concentration of the negative electrode, F is the Faraday constant, SOL is the SOC of the single cell electrode, SOC is the remaining power of the single cell, is the value corresponding to the positive electrode of the single cell at 0, is the value corresponding to the negative electrode when the SOC of the single battery is 0, is the value corresponding to the positive electrode of the single cell at 100, is the value corresponding to the negative electrode of the single cell at 100; S2.3: The final fitness function fm of the electrothermal coupling model is obtained by weighted calculation, and the expression is: ; Among them, W1, W2 and W3 are the weights of different fitness functions, fv1 is the mean square error of 1C discharge condition, and fv2 is the mean square error of DST dynamic stress condition; S2.4: Use 1C discharge condition to identify temperature parameters and obtain the local root square error ft of temperature, which is expressed as: ; Where ft is the local root square error, T exp Refers to the experimentally measured temperature, T sim Refers to the simulated temperature.

[0007] Preferably, the internal and external states of the battery include voltage, SOC, surface lithium ion concentration, electrolyte concentration, and lithium deposition overpotential.

[0008] Preferably, the specific steps of step S4 are: S4.1: Select surface lithium ion concentration, electrolyte concentration, lithium deposition overpotential, voltage, SOC, and temperature as the safety constraints of the SOP. The expression is: ; ; ; ; ; ; in, and The maximum lithium insertion range of the positive and negative electrodes of the battery, is the maximum concentration of the positive and negative electrodes of the battery, is the surface lithium ion concentration of the positive and negative electrodes of the battery, is the lithium deposition overpotential, is the current battery SOC, is the minimum voltage of the battery, is the maximum voltage of the battery, is the current voltage of the battery, is the minimum temperature of the battery, is the maximum temperature of the battery, is the current temperature of the battery; S4.2: Select the dichotomy method to predict the SOP of the battery at different time scales; S4.3: Select Gaussian process regression for accelerated prediction of SOP, specifically: The DST dynamic stress condition was selected as the training set, and SOC, voltage, and temperature were used as inputs. The binary predicted SOP and the 95% confidence interval of the SOP were used as outputs for offline training. When predicting SOP under other working conditions, the 95% confidence interval is obtained through the offline model, and the interval is used as the current maximum and minimum current boundaries, which speeds up the convergence of the dichotomy method.

[0009] Preferably, the specific steps of S4.2 are: S4.2.1: Set the maximum boundary current I 0，max Set to 20C, minimum boundary current I 0，min Set to 0C; S4.2.2: Let the initial maximum power current I 0，SOP Equal to the initial maximum boundary current I 0，max , the constraint state of different time periods Δt is calculated by using a constant current through an electrothermal coupling model; S4.2.3: Determine whether the six states of surface lithium ion concentration, electrolyte concentration, lithium deposition overpotential, voltage, SOC, and temperature all meet the safety constraints. If yes, the initial maximum power current I 0,SOP is the maximum constant current I in this state and this time period k,SOP , go to step S4.2.8, if not, update by binary search and go to step S4.2.4; S4.2.4: Let the maximum current I k,sop Equal to the maximum boundary current I k，max and the minimum boundary current I k，min half of the sum, taking the maximum current I k,sop The constraint state at different time periods Δt is calculated through the electrothermal coupling model; S4.2.5: Determine whether the six conditions of surface lithium ion concentration, electrolyte concentration, lithium deposition overpotential, voltage, SOC, and temperature all meet safety constraints; S4.2.6: No, then let the maximum boundary current I k，max is the maximum power current I k,sop , with a maximum current I k,sop Calculate the constraint state of different time periods Δt through the electrothermal coupling model and return to step S4.2.5. If yes, proceed to step S4.2.7; S4.2.7: Determine whether the maximum tolerance tol is met. The judgment expression is: ; ; in, is the maximum boundary current of the kth iteration, is the minimum boundary current of the kth iteration, is the current maximum current, tol is the maximum tolerance; If not, let the minimum boundary current I k，minEqual to the maximum power current I k,SOP , and return to step S4.2.5, If yes, go to step S4.2.8: S4.2.8: Iteration stops and the final maximum constant current I is calculated sop（t） , the expression is: ; S4.2.9: By the maximum constant current I sop（t） The minimum terminal voltage in the Δt time period is calculated with the electrothermal coupling model , and calculate the maximum charging power Maximum discharge power , the expression is: ; ; in, For the maximum charging power at this moment, For the maximum charging current at this moment, For this moment, the terminal voltage is For this moment, the discharge and charge power is, For the maximum charging current at this moment, is the minimum terminal voltage after calculating Δt.

[0010] Compared with the prior art, the present invention provides a method for rapid prediction of battery SOP based on an electrochemical model, which has the following beneficial effects: 1. This battery SOP rapid prediction method based on the electrochemical model quickly identifies 21 electrochemical model parameters through a variable-scale multi-objective grey wolf optimization algorithm. By changing the input identification scale during the optimization process, the non-convergence problem that occurs during the optimization process is avoided. Through a multi-objective strategy, the proportion of fitness values ​​of various working conditions is selected by weight, thus avoiding the overfitting problem in parameter identification.

[0011] 2. This battery SOP fast prediction method based on the electrochemical model uses Gaussian process regression to offline learn the relationship between SOP and its 95% confidence interval and voltage, SOC, and temperature. When predicting SOP, the interval range of the binary method is shortened, so that the binary method can converge more quickly, accelerate the prediction of SOP, and enable SOP prediction to be used online. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A schematic diagram of a method for rapid prediction of battery SOP based on an electrochemical model proposed in the present invention; Figure 2A schematic diagram of 1s charging current for a battery SOP rapid prediction method based on an electrochemical model proposed in the present invention; Figure 3 A schematic diagram of 1s charging power of a battery SOP rapid prediction method based on an electrochemical model proposed in the present invention; Figure 4 A schematic diagram of a 30s charging current for a battery SOP rapid prediction method based on an electrochemical model proposed in the present invention; Figure 5 A schematic diagram of 30s charging power of a battery SOP rapid prediction method based on an electrochemical model proposed in the present invention; Figure 6 A schematic diagram of a 60s charging current for a battery SOP rapid prediction method based on an electrochemical model proposed in the present invention; Figure 7 A schematic diagram of 60s charging power of a battery SOP rapid prediction method based on an electrochemical model proposed in the present invention; Figure 8 A schematic diagram of 1s discharge power of a battery SOP rapid prediction method based on an electrochemical model proposed in the present invention; Fig. 9 A schematic diagram of 1s discharge power flow of a battery SOP rapid prediction method based on an electrochemical model proposed in the present invention; Fig.10 A schematic diagram of a 30s discharge current for a battery SOP rapid prediction method based on an electrochemical model proposed in the present invention; Fig.11 A schematic diagram of 30s discharge power of a battery SOP rapid prediction method based on an electrochemical model proposed in the present invention; Fig.12 A schematic diagram of a 60s discharge current for a battery SOP rapid prediction method based on an electrochemical model proposed in the present invention; Fig.13 A schematic diagram of 60s discharge power of a battery SOP rapid prediction method based on an electrochemical model proposed in the present invention; Fig.14 A schematic diagram of parameter identification process of a battery SOP rapid prediction method based on an electrochemical model proposed in the present invention; Fig.15 A schematic diagram of the binary process of a battery SOP rapid prediction method based on an electrochemical model proposed in the present invention. DETAILED DESCRIPTION

[0013] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0014] See also Figure 1-15 , a battery SOP rapid prediction method based on electrochemical model, comprising the following steps: S1: The P2D model is simplified into the e-SPM model and coupled with the thermal model to obtain the electrothermal coupling model, which is expressed as: ; ; Among them, in the two electrodes, the solid phase concentration Keeping the x dimension constant, represents the initial lithium ion concentration in the electrolyte, , and denote the electrolyte volume fractions of the negative electrode, separator and positive electrode, respectively, , and Represent the lengths of the negative electrode, separator and positive electrode respectively, S represents the cross-sectional area of ​​the battery cell, and represent the initial lithium ion concentrations of the negative electrode and the positive electrode, respectively, and represent the volume fractions of the negative electrode and the positive electrode, respectively; When the battery temperature When the change in the x dimension is small and only changes with time t, after the output vector is obtained by the state estimator, the battery terminal voltage can be described as: ; ; ; ; in, is related to the equilibrium potential of the anode and cathode, and represents the estimated equilibrium potential, The first part is the ohmic potential drop due to electrolyte conductivity, and the second part is the electrolyte concentration overpotential estimate, represents the voltage across the thin film resistor, Indicates overpotential; , Represent the positive and negative electrode equilibrium potentials respectively; , represent the surface lithium ion concentrations of the negative electrode and the positive electrode, respectively; , , represent the effective reaction rate constants of the negative electrode, separator, and positive electrode, respectively; Indicates the charge and discharge current, represents the universal gas constant; represents the Faraday constant; Indicates the lithium ion migration number; , Represent the positive and negative electrode thin film resistance respectively; , Represent the interfacial areas of the positive and negative electrode spherical particles, respectively; represents the charge transfer coefficient of the electrode; , represent the exchange current density of the positive and negative electrodes respectively.

[0015] S2: The thermal parameters and electrochemical parameters of the electrothermal coupling model are identified separately by the variable-scale multi-objective grey wolf optimization algorithm; S3: Use the unscented Kalman filter as the state observer of the electrochemical model to observe the internal and external states of the battery. The internal and external states of the battery include voltage, SOC, surface lithium ion concentration, electrolyte concentration, and lithium deposition overpotential. For temperature, it is only used as a correction of the coupling parameters. The temperature tested in the previous second is used to correct the coupling parameters of the next second. S4: Select surface lithium ion concentration, electrolyte concentration, lithium deposition overpotential, voltage, SOC, and temperature as safety constraints for SOP, select the binary method to predict the SOP of the battery at different time scales, and select Gaussian process regression to accelerate the convergence speed of the binary method to predict the battery SOP; The power of lithium batteries is not only limited by external terminal voltage, current and temperature, but also by internal electrochemical reactions. Therefore, it is impossible to accurately predict power by relying solely on external measurable states. Therefore, several electrochemical states inside lithium batteries are selected as additional safety constraints. Compared with the ECM model for power prediction, the current provided by the manufacturer is not selected as a constraint because the maximum current is calculated based on other constraints.

[0016] Step S2 is specifically: Since the simultaneous identification of the electrochemical-thermal coupling model will cause mutual coupling between variables, making parameter identification more difficult, the electrochemical model and thermal model are identified separately, and the Grey Wolf optimization algorithm is used to identify the relevant parameters.

[0017] For electrochemical model parameters, the problems in the identification process are mainly identification time, overfitting and convergence.

[0018] Time issue: Even for the reconstructed electrochemical model, if the amount of input data is too large during the parameter identification process, it will take a long time to perform parameter identification.

[0019] Convergence problem: During the identification process, some intermediate values ​​of the calculation may exceed the boundaries, resulting in the appearance of complex numbers in the calculation process. This situation of the appearance of complex numbers is called non-convergence.

[0020] Overfitting problem: During the identification process, a set of parameters may only be applicable to one working condition, but not to other working conditions. This situation is called overfitting.

[0021] Aiming at the problem of identification of three electrochemical parameters, a multi-objective grey wolf optimization algorithm with variable input is designed.

[0022] Since the non-convergence problem mainly exists in the best calculated data, the identification data is divided according to the number of iterations. As the number of iterations increases, the identification data also increases. This not only avoids the non-convergence problem, but also improves the identification speed.

[0023] S2.1: Using 1C discharge and DST dynamic conditions as the target fitness function of the variable-scale multi-objective grey wolf optimization algorithm, the simulated voltage V of the electrothermal coupling model is obtained. sim and the actual voltage V exp The fitness value fv of the mean square error between is expressed as: ; Where N is the number of voltage samples collected, V exp is the actual voltage, V sim is the analog voltage; S2.2: Calculate the absolute value fc of the difference between the positive electrode capacity and the negative electrode capacity. The expression is: ; Where A is the electrode area, L + is the thickness of the positive electrode, L - Negative electrode thickness, is the volume fraction of the positive electrode solid phase, is the volume fraction of the positive electrode solid phase, is the maximum lithium ion concentration at the positive electrode, is the maximum lithium ion concentration of the negative electrode, F is the Faraday constant, SOL is the SOC of the single cell electrode, SOC is the remaining power of the single cell, is the value corresponding to the positive electrode of the single cell at 0, is the value corresponding to the negative electrode when the SOC of the single battery is 0, is the value corresponding to the positive electrode of the single cell at 100, is the value corresponding to the negative electrode of the single cell at 100; S2.3: The final fitness function fm of the electrothermal coupling model is obtained by weighted calculation, and the expression is: ; Among them, W1, W2 and W3 are the weights of different fitness functions, fv1 is the mean square error of 1C discharge condition, and fv2 is the mean square error of DST dynamic stress condition; S2.4: Use 1C discharge condition to identify temperature parameters and obtain the local root square error ft of temperature, which is expressed as: ; Where ft is the local root square error, T exp Refers to the experimentally measured temperature, T sim Refers to the simulated temperature.

[0024] The specific steps of step S4 are: S4.1: Select surface lithium ion concentration, electrolyte concentration, lithium deposition overpotential, voltage, SOC, and temperature as the safety constraints of the SOP. The expression is: ; ; ; ; ; ; in, and The maximum lithium insertion range of the positive and negative electrodes of the battery, is the maximum concentration of the positive and negative electrodes of the battery, is the surface lithium ion concentration of the positive and negative electrodes of the battery, is the lithium deposition overpotential, is the current battery SOC, is the minimum voltage of the battery, is the maximum voltage of the battery, is the current voltage of the battery, is the minimum temperature of the battery, is the maximum temperature of the battery, is the current temperature of the battery; The power prediction of lithium batteries can be defined as the maximum constant charge or discharge current that can be applied to the battery within a certain time period Δt, and does not exceed the several SOA ranges defined in 3.31. However, due to different time periods, the power prediction of batteries under the same working state is also different, so power prediction in different time ranges is also important in battery management. The technical solution considers power prediction in three time periods of 1s, 30s, and 60s to meet long-term and short-term predictions; S4.2: Select the dichotomy method to predict the SOP of the battery at different time scales; S4.3: Select Gaussian process regression for accelerated prediction of SOP, specifically: The DST dynamic stress condition was selected as the training set, and SOC, voltage, and temperature were used as inputs. The binary predicted SOP and the 95% confidence interval of the SOP were used as outputs for offline training. When predicting SOP under other working conditions, the 95% confidence interval is obtained through the offline model, and the interval is used as the current maximum and minimum current boundaries, which speeds up the convergence of the dichotomy method.

[0025] S4.2 The specific steps are: S4.2.1: Set the maximum boundary current I 0，max Set to 20C, minimum boundary current I 0，min Set to 0C; S4.2.2: Let the initial maximum power current I 0，SOP Equal to the initial maximum boundary current I 0，max , the constraint state of different time periods Δt is calculated by using a constant current through an electrothermal coupling model; S4.2.3: Determine whether the six states of surface lithium ion concentration, electrolyte concentration, lithium deposition overpotential, voltage, SOC, and temperature all meet the safety constraints. If yes, the initial maximum power current I 0,SOP is the maximum constant current I in this state and this time period k,SOP , go to step S4.2.8, if not, update by binary search and go to step S4.2.4; S4.2.4: Let the maximum current I k,sop Equal to the maximum boundary current I k，max and the minimum boundary current I k，min half of the sum, taking the maximum current I k,sop The constraint state at different time periods Δt is calculated through the electrothermal coupling model; When predicting the SOP at a certain point, the state at this point is used as the initial value of eSPM, and a constant current is applied for a period of time. Although the current is not a constraint for power prediction, the maximum current and minimum current are required as the boundaries of the dichotomy, so the current boundary (which is also the initial minimum current I0,min and the maximum current I 0，max ) is set to 0C at the minimum and 20C at the maximum. Then let the initial maximum power current I 0，SOP Equal to the initial maximum current I 0，max , and then use this constant current to calculate the constraint state of different time periods Δt through eSPM. If the final six states all meet the safety constraints, then I 0,SOP is the maximum constant current in this state and this time period; if any state exceeds the safety constraint, it is updated and iterated by binary search. Until the Kth maximum constant current I k,SOP All constraints are met, but since the maximum current that needs to meet the constraints is the maximum current, in order to make the predicted current close to the maximum current that meets the constraints, a maximum tolerance tol is set equal to 0.1, so that the predicted current is as close to the boundary current as possible; S4.2.5: Determine whether the six conditions of surface lithium ion concentration, electrolyte concentration, lithium deposition overpotential, voltage, SOC, and temperature all meet safety constraints; S4.2.6: No, then let the maximum boundary current I k，max is the maximum power current I k,sop , with a maximum current I k,sop Calculate the constraint state of different time periods Δt through the electrothermal coupling model and return to step S4.2.5. If yes, proceed to step S4.2.7; S4.2.7: Determine whether the maximum tolerance tol is met. The judgment expression is: ; ; in, is the maximum boundary current of the kth iteration, is the minimum boundary current of the kth iteration, is the current maximum current, tol is the maximum tolerance; If not, let the minimum boundary current I k，min Equal to the maximum power current I k,SOP , and return to step S4.2.5, If yes, go to step S4.2.8: S4.2.8: Iteration stops and the final maximum constant current I is calculated sop（t） , the expression is: ; S4.2.9: By the maximum constant current I sop（t） The minimum terminal voltage in the Δt time period is calculated with the electrothermal coupling model , and calculate the maximum charging power Maximum discharge power , the maximum charging power can be obtained by the maximum constant charging current at the current moment and the minimum voltage during Δt, and the maximum discharging power can be obtained by the maximum constant discharging current at the current moment and the minimum voltage during Δt, and the expression is: ; ; in, For the maximum charging power at this moment, For the maximum charging current at this moment, For this moment, the terminal voltage is For this moment, the discharge and charge power is, For the maximum charging current at this moment, is the minimum terminal voltage after calculating Δt.

[0026] In summary, this battery SOP rapid prediction method based on the electrochemical model quickly identified 21 electrochemical model parameters through a variable-scale multi-objective grey wolf optimization algorithm, and avoided the non-convergence problem in the optimization process by changing the input identification scale in the optimization process; through a multi-objective strategy, the proportion of fitness values ​​of various working conditions was selected by weight, avoiding the overfitting problem in parameter identification.

[0027] In addition, through Gaussian process regression, the relationship between SOP and its 95% confidence interval and voltage, SOC, and temperature is learned offline. When predicting SOP, the interval range of the binary method is shortened, so that the binary method can converge more quickly, accelerate the prediction of SOP, and enable SOP prediction to be used online.

[0028] It should be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0029] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for rapid prediction of battery SOP based on electrochemical model, characterized in that: The following steps are involved: S1: Simplify the P2D model into the e-SPM model and couple it with the thermal model to obtain the electrothermal coupling model; S2: The thermal parameters and electrochemical parameters of the electrothermal coupling model are identified separately by the variable-scale multi-objective grey wolf optimization algorithm; S3: Use the unscented Kalman filter as the state observer of the electrochemical model to observe the internal and external states of the battery; S4: Select surface lithium ion concentration, electrolyte concentration, lithium plating overpotential, voltage, SOC, and temperature as safety constraints for SOP, select the binary method to predict the SOP of the battery at different time scales, and select Gaussian process regression to accelerate the convergence speed of the binary method to predict the battery SOP.

2. A battery SOP rapid prediction method based on an electrochemical model according to claim 1, characterized in that, The step S2 is specifically: S2.1: Using 1C discharge and DST dynamic conditions as the target fitness function of the variable-scale multi-objective grey wolf optimization algorithm, the simulated voltage V of the electrothermal coupling model is obtained. sim and the actual voltage V exp The fitness value fv of the mean square error between is expressed as: ； Where N is the number of voltage samples collected, V exp is the actual voltage, V sim is the analog voltage; S2.2: Calculate the absolute value fc of the difference between the positive electrode capacity and the negative electrode capacity. The expression is: ； Where A is the electrode area, L + is the thickness of the positive electrode, L - Negative electrode thickness, is the positive electrode solid phase volume fraction, is the positive electrode solid phase volume fraction, is the maximum lithium ion concentration at the positive electrode, is the maximum lithium ion concentration of the negative electrode, F is the Faraday constant, SOL is the SOC of the single cell electrode, SOC is the remaining power of the single cell, is the value corresponding to the positive electrode of the single cell at 0, is the value corresponding to the negative electrode when the SOC of the single battery is 0, is the value corresponding to the positive electrode of the single cell at 100, is the value corresponding to the negative electrode of the single cell at 100; S2.3: The final fitness function fm of the electrothermal coupling model is obtained by weighted calculation, and the expression is: ； Among them, W1, W2 and W3 are the weights of different fitness functions, fv1 is the mean square error of 1C discharge condition, and fv2 is the mean square error of DST dynamic stress condition; S2.4: Use 1C discharge condition to identify temperature parameters and obtain the local root square error ft of temperature, which is expressed as: ； Where ft is the local root square error, T exp Refers to the experimentally measured temperature, T sim Refers to the simulated temperature.

3. A battery SOP rapid prediction method based on an electrochemical model according to claim 1, characterized in that: The internal and external states of the battery include voltage, SOC, surface lithium ion concentration, electrolyte concentration, and lithium deposition overpotential.

4. A battery SOP rapid prediction method based on an electrochemical model according to claim 1, characterized in that, The specific steps of step S4 are: S4.1: Select surface lithium ion concentration, electrolyte concentration, lithium deposition overpotential, voltage, SOC, and temperature as the safety constraints of the SOP. The expression is: ； ； ； ； ； ； in, and The maximum lithium insertion range of the positive and negative electrodes of the battery, is the maximum concentration of the positive and negative electrodes of the battery, is the surface lithium ion concentration of the positive and negative electrodes of the battery, is the lithium deposition overpotential, is the current battery SOC, is the minimum voltage of the battery, is the maximum voltage of the battery, is the current voltage of the battery, is the minimum temperature of the battery, is the maximum temperature of the battery, is the current temperature of the battery; S4.2: Select the dichotomy method to predict the SOP of the battery at different time scales; S4.3: Select Gaussian process regression for accelerated prediction of SOP.

5. A battery SOP rapid prediction method based on an electrochemical model according to claim 4, characterized in that: The specific steps of S4.2 are: S4.2.1: Set the maximum boundary current I 0，max Set to 20C, minimum boundary current I 0，min Set to 0C; S4.2.2: Let the initial maximum power current I 0，SOP Equal to the initial maximum boundary current I 0，max , the constraint state of different time periods Δt is calculated by using a constant current through an electrothermal coupling model; S4.2.3: Determine whether the six states of surface lithium ion concentration, electrolyte concentration, lithium deposition overpotential, voltage, SOC, and temperature all meet the safety constraints. If yes, the initial maximum power current I 0,SOP is the maximum constant current I in this state and this time period k,SOP , go to step S4.2.8, if not, update by binary search and go to step S4.2.4; S4.2.4: Let the maximum current I k,sop Equal to the maximum boundary current I k，max and the minimum boundary current I k，min half of the sum, taking the maximum current I k,sop The constraint state at different time periods Δt is calculated through the electrothermal coupling model; S4.2.5: Determine whether the six conditions of surface lithium ion concentration, electrolyte concentration, lithium deposition overpotential, voltage, SOC, and temperature all meet safety constraints; S4.2.6: No, then let the maximum boundary current I k，max is the maximum power current I k,sop , with a maximum current I k,sop Calculate the constraint state of different time periods Δt through the electrothermal coupling model and return to step S4.2.

5. If yes, proceed to step S4.2.7; S4.2.7: Determine whether the maximum tolerance tol is met. The judgment expression is: ； ； in, is the maximum boundary current of the kth iteration, is the minimum boundary current of the kth iteration, is the current maximum current, tol is the maximum tolerance; If not, let the minimum boundary current I k，min Equal to the maximum power current I k,SOP , and return to step S4.2.5, If yes, go to step S4.2.8: S4.2.8: Iteration stops and the final maximum constant current I is calculated sop（t） , the expression is: ； S4.2.9: By the maximum constant current I sop（t） The minimum terminal voltage in the Δt time period is calculated with the electrothermal coupling model , and calculate the maximum charging power Maximum discharge power , the expression is: ； ； in, For the maximum charging power at this moment, For the maximum charging current at this moment, For this moment, the terminal voltage is For this moment, the discharge and charge power is, For the maximum charging current at this moment, is the minimum terminal voltage after calculating Δt.

6. A battery SOP rapid prediction method based on an electrochemical model according to claim 4, characterized in that, The step S4.3 is specifically as follows: The DST dynamic stress condition was selected as the training set, and SOC, voltage, and temperature were used as inputs. The binary predicted SOP and the 95% confidence interval of the SOP were used as outputs for offline training. When predicting SOP under other working conditions, the 95% confidence interval is obtained through the offline model, and the interval is used as the current maximum and minimum current boundaries, which speeds up the convergence of the dichotomy method.

Images