Battery simulation management system of new energy electric vehicle teaching aid

Abstract

The invention provides a battery simulation management system for a new energy electric vehicle teaching aid, and the system comprises a dynamic scene data generation module, a thermoelectric coupling simulation module, and a simulation precision iteration module: the dynamic scene data generation module is used for obtaining the power fluctuation data of a driving scene and an environment temperature change sequence, and generating a dynamic scene data set; the thermoelectric coupling simulation module is used for generating thermoelectric coupling simulation data through an electrochemical model and thermal management interference analysis based on the dynamic scene data set; and the simulation precision iteration module is used for dynamically calibrating microscopic parameters and generating optimized battery state prediction data according to the deviation between the thermoelectric coupling simulation data and the output of the simulator. The system can simulate the characteristics of the battery under a complex driving condition, and improves the authenticity of battery simulation and the teaching demonstration effect.

Description

Technical Field

[0001] The present invention belongs to the technical field of new energy electric vehicle battery management system testing, and particularly relates to a battery simulation management system for new energy electric vehicle teaching aids. Background Art

[0002] In the battery simulation management system of new energy electric vehicle teaching aids, the battery response technology direction faces a unique challenge: how to accurately simulate the dynamic response of the battery to the superposition effect of micro power fluctuations and extreme temperature differences in complex driving scenarios. Specifically, the teaching aid needs to design a system to perform real-time simulation on the internal electrochemical state changes of the battery caused by rapid charge and discharge cycles when the driver frequently switches between acceleration and braking operations in a short period of time. In this scenario, the battery not only has to cope with the sharp fluctuations in power demand, but also has to consider the interference of thermal management on battery response when the external temperature rapidly changes from extremely low to extremely high. For example, when the vehicle starts in cold regions, the low-temperature performance of the battery decreases, while intense driving will cause the battery to quickly heat up. How can the battery management system capture the subtle differences in voltage unevenness and capacity attenuation between battery cells caused by temperature differences through the simulator?

[0003] The existing battery simulation management systems for new energy electric vehicle teaching aids are difficult to simulate the battery characteristics under complex driving conditions, which affects the teaching effect. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide a battery simulation management system for new energy electric vehicle teaching aids, which can simulate the battery characteristics under complex driving conditions and improve the battery simulation accuracy.

[0005] In a first aspect, the present application provides a battery simulation management system for new energy electric vehicle teaching aids, including a dynamic scenario data generation module, a thermoelectric coupling simulation module, and a simulation accuracy iteration module:

[0006] The dynamic scenario data generation module is configured to obtain the power fluctuation data and the environmental temperature change sequence of the driving scenario, and generate a dynamic scenario data set;

[0007] The thermoelectric coupling simulation module is configured to generate thermoelectric coupling simulation data based on the dynamic scenario data set through electrochemical model and thermal management interference analysis;

[0008] The simulation accuracy iteration module is configured to dynamically calibrate the microscopic parameters according to the deviation between the thermoelectric coupling simulation data and the output of the simulator, and generate optimized battery state prediction data.

[0009] In a possible embodiment, the dynamic scenario data generation module includes:

[0010] The power fluctuation acquisition unit is used to obtain short-term acceleration and braking power demand data and generate a power fluctuation curve;

[0011] The temperature sequence fusion unit is used to synchronize the power fluctuation curve and the rapid environmental temperature change sequence in time through a sliding window alignment algorithm to generate a dynamic scenario data set.

[0012] In a possible embodiment, the thermoelectric coupling simulation module includes:

[0013] The multi-dimensional matrix construction unit is used to perform normalization processing on the dynamic scenario data set and construct a multi-dimensional input matrix including power, temperature, and timestamp;

[0014] The electrochemical response unit is used to calculate the transient voltage distribution of the battery unit based on the multi-dimensional input matrix through a preset electrochemical model;

[0015] The thermal interference analysis unit is used to calculate the thermal management interference effect of the battery unit according to the environmental temperature change sequence and the heat conduction equation;

[0016] The coupling matrix generation unit is used to fuse the transient voltage distribution and the thermal management interference effect to generate thermoelectric coupling simulation data.

[0017] In a possible embodiment, the electrochemical response unit includes:

[0018] The lithium-ion concentration calculation sub-unit is used to solve the diffusion equation of dynamic stress coupling based on an improved pseudo-two-dimensional electrochemical model using the following formula to generate the concentration gradient distribution of lithium ions on the electrode surface:

[0019]

[0020] where c is the lithium-ion concentration, D is the diffusion coefficient, is the Laplace operator of the lithium-ion concentration, j is the local current density, F is the Faraday constant, β is the diffusion coefficient correction factor, σ is the stress coupling factor, ∈ is the electrode strain rate;

[0021] The polarization voltage mapping sub-unit is used to calculate the transient voltage difference through a dynamic activation energy model according to the concentration gradient distribution using the following formula:

[0022]

[0023] where V is the transient voltage difference, R is the gas constant, T is the absolute temperature, is the lithium-ion concentration on the electrode surface, is the lithium-ion concentration in the electrode bulk phase, γ is the activation energy correction parameter, is the exchange current density, j0 is the exchange current density, α is the reaction order;

[0024] A transient voltage generation subunit, configured to superimpose a transient voltage difference on the open-circuit voltage of the battery cell to generate a transient voltage distribution, where the open-circuit voltage is obtained by querying a preset state of charge-open circuit voltage mapping table.

[0025] In a possible embodiment, the simulation accuracy iteration module includes:

[0026] A deviation regression unit, configured to generate an accuracy adjustment parameter through a machine learning algorithm based on the deviation data between the thermoelectric coupling simulation data and the output of the simulator;

[0027] A microscopic calibration unit, configured to recalibrate the reaction rate and diffusion coefficient of the electrochemical model according to the accuracy adjustment parameter, where the reaction rate is used to characterize the embedding / delithiation reaction rate of lithium ions on the electrode surface, and the diffusion coefficient is used to characterize the migration ability of lithium ions in the electrode material;

[0028] A prediction data update unit, configured to generate battery state prediction data based on the reaction rate and diffusion coefficient.

[0029] In a possible embodiment, the microscopic calibration unit includes:

[0030] A spatio-temporal attention weight generation subunit, configured to generate a dynamic weight matrix through an attention mechanism according to the spatio-temporal correlation between the voltage unevenness feature and the capacity attenuation feature;

[0031] A non-linear parameter mapping subunit, configured to map the dynamic weight matrix to the adjustment amounts of the reaction rate and diffusion coefficient, where the adjustment amounts are used to calibrate the reaction rate and diffusion coefficient of the electrochemical model.

[0032] In a possible embodiment, the deviation regression unit includes:

[0033] An error calculation subunit, configured to calculate the deviation between the output of the simulator and the optimized battery state prediction data through the mean square error;

[0034] An instruction generation subunit, configured to generate a model recalibration instruction and trigger the prediction data update unit when the deviation exceeds a preset threshold.

[0035] In a second aspect, the present application further provides a battery simulation management method for a new energy electric vehicle teaching aid, including:

[0036] Obtaining the power fluctuation data and the environmental temperature change sequence of the driving scenario to generate a dynamic scenario data set;

[0037] Based on the dynamic scenario data set, generating thermoelectric coupling simulation data through an electrochemical model and thermal management interference analysis;

[0038] Dynamically calibrate microscopic parameters and generate optimized battery state prediction data based on the deviation between the thermoelectric coupling simulation data and the output of the simulator.

[0039] In a third aspect, the present application also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the battery simulation management method of the new energy electric vehicle teaching aid as described above.

[0040] In a fourth aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the battery simulation management method of the new energy electric vehicle teaching aid as described above.

[0041] The above battery simulation management system for a new energy electric vehicle teaching aid obtains power fluctuation data and ambient temperature change sequences of a driving scenario through a dynamic scenario data generation module, and generates a data set reflecting the dynamic characteristics of complex working conditions. Based on this data set, through the synergistic effect of an electrochemical model and thermal management interference analysis, simulation data integrating electrochemical response and temperature gradient effect is generated. According to the real-time deviation between the simulation data and the output of the actual simulator, microscopic parameters are dynamically calibrated and optimized battery state prediction data is generated. The above system can accurately simulate the dynamic response of the battery to power fluctuations and extreme temperature differences under complex driving conditions, solve the problem of insufficient simulation accuracy of traditional teaching aids in transient power switching and sudden temperature change scenarios, and thus improve the authenticity of battery simulation and the teaching demonstration effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0043] Figure 1 FIG. 1 is a schematic structural diagram of a battery simulation management system for a new energy electric vehicle teaching aid provided by an embodiment of the present invention;

[0044] Figure 2 FIG. 2 is a flowchart of a battery simulation management method for a new energy electric vehicle teaching aid provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] In order to make the objectives, technical solutions and advantages of the present application more clear, the following further details the present application in conjunction with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0046] First, a brief introduction is made to the nouns involved in the embodiments of this application.

[0047] The sliding window alignment algorithm is an algorithm widely used in sequence analysis. It slides a window of a fixed size over the target sequence. At each slide, the subsequence within the window is compared and analyzed with the reference sequence, and metrics such as similarity and matching degree are calculated to find the optimal alignment position. This algorithm can effectively process long sequence data and analyze time series, text sequences, etc. in other fields such as signal processing and data mining to achieve functions such as sequence pattern recognition and feature extraction, facilitating the development of related research and applications.

[0048] The electrochemical model is a mathematical model used to describe the internal electrochemical reaction process of a battery. It can accurately depict the relationship between the electrical performance and chemical reactions of the battery during charging and discharging. This model quantifies complex processes such as ion transport and charge transfer inside the battery through mathematical equations, covering key mechanisms such as electrode kinetics and electrolyte diffusion, and can effectively reflect the changes in battery characteristics such as voltage, current, and capacity over time and reaction progress.

[0049] Transient voltage refers to a short-term and rapidly changing voltage phenomenon that occurs in a circuit. When the circuit state suddenly changes, such as the connection or disconnection of a load or the switching of a power supply, transient voltage will be induced. In a battery system, transient voltage changes can reflect the rapid response of internal chemical reactions in the battery. For example, when an electric vehicle starts, accelerates, or brakes suddenly, the output voltage of the battery will show transient changes.

[0050] Based on the above noun explanations, the implementation environment of a battery simulation management system for a new energy electric vehicle teaching aid provided in the embodiments of this application is described. Exemplarily, this implementation environment includes: a battery simulator, sensors, and a processor. Among them, the battery simulator, as the core execution device, is used to simulate the charging and discharging characteristics of different battery types (such as lithium-ion batteries, solid-state batteries). Its output terminal is connected to the load circuit through a high-precision programmable power supply; the sensors can include current sensors, voltage sensors, and temperature sensors, which are deployed at the output terminal of the simulated battery and in the environmental temperature control device to collect power fluctuation data and temperature change sequences in real time and communicate with the processor through a bus; the processor includes, but is not limited to, a central processing unit, a multi-core processor, or an artificial intelligence chip, etc., which is not limited here.

[0051] Combined with the above noun explanations and implementation environment, the application scenarios of the embodiments of this application are described. The battery simulation management system for a new energy electric vehicle teaching aid provided in the embodiments of this application can be applied to the following scenarios including, but not limited to:

[0052] In the new energy vehicle experimental teaching courses in universities, teachers can use this system to simulate the switching between urban congestion conditions (frequent start and stop) and high-speed cruising conditions. For example, set the environmental temperature to rise suddenly from -20°C to 40°C, and at the same time superimpose a 10Hz high-frequency charge and discharge cycle. Students can observe in real time the voltage drop curve caused by the increase in battery internal resistance, and analyze the temperature balance effect after the thermal management system intervenes, so as to intuitively understand the thermal-electric co-control strategy of the BMS.

[0053] In the battery material R & D test platform, for new solid-state battery materials, researchers can simulate the lithium dendrite growth inhibition effect under fast charging by adjusting the parameters of the electrochemical model. The system outputs a three-dimensional distribution map of the surface concentration gradient of the electrode and the stress change curve, providing data support for material modification and reducing the cost of experimental trial and error.

[0054] Exemplarily, the battery simulation management system of a new energy electric vehicle teaching aid provided in the embodiments of the present application can also be applied to other application scenarios. Only examples are given here, and the specific application scenarios are not limited.

[0055] In an exemplary embodiment, as Figure 1 shown, a battery simulation management system 10 of a new energy electric vehicle teaching aid is provided. Taking the application of this system to the aforementioned battery simulator as an example, it can be understood that this system can also be realized through the interaction between the processor of the battery simulator and other processors / controllers / servers. In this embodiment, the system includes a scenario data generation module 11, a thermoelectric coupling simulation module 12, and a simulation accuracy iteration module 13:

[0056] The dynamic scenario data generation module 11 is used to obtain the power fluctuation data of the driving scenario and the environmental temperature change sequence, and generate a dynamic scenario data set.

[0057] Specifically, by obtaining the power fluctuation data in the driving scenario, including the current change curve corresponding to short-term acceleration and braking operations, and receiving the environmental temperature change sequence transmitted by the external temperature control device, complex driving conditions can be accurately restored, including the battery operating states under rapid acceleration, rapid braking, and different temperature environments, providing a real scenario reference for teaching and research.

[0058] The thermoelectric coupling simulation module 12 is used to generate thermoelectric coupling simulation data based on the dynamic scenario data set through electrochemical model and thermal management interference analysis.

[0059] Specifically, the electrochemical model is constructed based on the basic physical and chemical principles of the battery, and can accurately describe the electrochemical reaction process inside the battery. Combined with the thermal management interference analysis algorithm, it considers the heat dissipation and heat generation conditions of the battery under different working conditions. By using high-performance computing equipment to run the simulation program, through a series of iterative calculations, the generated thermoelectric coupling simulation data can take into account both the electrical characteristics and thermal characteristics of the battery, comprehensively reflecting the complex changes of the battery during actual operation. Compared with the traditional single-factor analysis model, it can more accurately reveal the law of battery performance changes and improve the reliability of the simulation results.

[0060] The simulation accuracy iteration module 13 is used to dynamically calibrate the microscopic parameters according to the deviation between the thermoelectric coupling simulation data and the output of the simulator, and generate optimized battery state prediction data.

[0061] Specifically, by comparing the thermoelectric coupling simulation data with the output data of the simulator, the deviation between the two is calculated. With the help of the intelligent optimization algorithm, the microscopic parameters in the electrochemical model are dynamically adjusted according to the deviation, and the optimization process is iterated repeatedly until the deviation reaches the preset accuracy standard. Finally, the optimized battery state prediction data is generated. Through the closed-loop feedback mechanism and dynamic parameter calibration, the problem of simulation distortion caused by the fixed model of traditional teaching aids is solved, significantly improving the real-time performance and accuracy of battery state prediction, and ensuring that the teaching demonstration results are highly consistent with the actual battery behavior.

[0062] The above battery simulation management system of a new energy electric vehicle teaching aid obtains the power fluctuation data and ambient temperature change sequence of the driving scenario through the dynamic scenario data generation module, and generates a data set reflecting the dynamic characteristics of complex working conditions. Based on the data set, through the synergistic effect of the electrochemical model and thermal management interference analysis, simulation data integrating electrochemical response and temperature gradient effect is generated. According to the real-time deviation between the simulation data and the output of the actual simulator, the microscopic parameters are dynamically calibrated and optimized battery state prediction data is generated. The above system can accurately simulate the dynamic response of the battery to power fluctuations and extreme temperature differences under complex driving conditions, solve the problem of insufficient simulation accuracy of traditional teaching aids in transient power switching and sudden temperature change scenarios, and thus improve the authenticity of battery simulation and the teaching demonstration effect.

[0063] In a possible embodiment, the dynamic scenario data generation module 11 includes:

[0064] The power fluctuation acquisition unit 111 is used to obtain the short-term acceleration and braking power demand data and generate a power fluctuation curve.

[0065] Specifically, the power demand data corresponding to the driver's short-term acceleration and braking operations can be collected in real time through the on-board current sensor and voltage sensor, and the instantaneous values of current and voltage can be recorded at a sampling frequency of not less than 1kHz. The power fluctuation curve with millisecond-level accuracy is generated through the power calculation formula. The power fluctuation curve contains key characteristic parameters, including peak power, valley power and change rate, which are used to characterize the violent fluctuation characteristics of transient loads in driving scenarios. Exemplarily, "short-term" can be defined as a single acceleration or braking operation lasting no more than 100ms, which is based on the vehicle electrical load transient response test conditions defined in the ISO 16750-2 standard.

[0066] The temperature sequence fusion unit 112 is used to synchronize the power fluctuation curve with the rapid change sequence of the ambient temperature through a sliding window alignment algorithm to generate the dynamic scene data set.

[0067] Specifically, the dynamic time warping (DTW) algorithm can be used to compensate for the time deviation of sensor acquisition, and the sliding window and dynamic time warping technology can be used to effectively eliminate the timing misalignment problem of multi-source sensor data, ensure strict synchronization of power and temperature changes, and improve the physical consistency of the simulation scene.

[0068] In a possible embodiment, the thermoelectric coupling simulation module 12 may include:

[0069] The multi-dimensional matrix construction unit 121 is used to normalize the dynamic scene data set and construct a multi-dimensional input matrix including power, temperature and time stamp.

[0070] Specifically, the Min-Max normalization method can be used to normalize the power and temperature values to eliminate the dimensional difference. The normalized data can be sorted by timestamp to construct a three-dimensional input matrix with the dimensions of time axis, power axis and temperature axis. The normalization and structured matrix construction solve the problems of inconsistent dimensionality and scattered storage of the original data.

[0071] The electrochemical response unit 122 is used to calculate the transient voltage distribution of the battery cell through a preset electrochemical model based on the multi-dimensional input matrix.

[0072] Exemplarily, a multidimensional input matrix can be input into a preset electrochemical model, which is based on the physical and chemical principles of batteries, such as the Nernst equation, the Butler-Volmer equation, etc., to describe the electrochemical reaction process inside the battery. The model calculates the transient voltage distribution of the battery cells at different times based on the power, time and other information in the input matrix through numerical calculation methods, such as the finite element method or the finite difference method. During the calculation process, the charge transfer, ion diffusion and other processes inside the battery are considered, and the transient voltage value of each battery cell at each time point is output.

[0073] A thermal interference analysis unit 123 is configured to calculate the thermal management interference effect of the battery cell according to the ambient temperature change sequence and the heat conduction equation.

[0074] Specifically, an ambient temperature change sequence is extracted from the dynamic scenario data set, combined with the heat conduction equation, and a numerical solution algorithm, such as the finite volume method, is used to calculate the thermal management interference effect of the battery cell. Considering the heat dissipation and heat generation conditions of the battery at different ambient temperatures, as well as the heat conduction process inside the battery, thermal interference-related data of each battery cell at different time points, such as temperature distribution changes and heat fluxes, are output.

[0075] A coupling matrix generation unit 124 is configured to fuse the transient voltage distribution and the thermal management interference effect to generate thermoelectric coupling simulation data.

[0076] Specifically, the coupling matrix generation unit organically fuses the data in both the electrical and thermal aspects. The generated thermoelectric coupling simulation data comprehensively and intuitively shows the mutual influence of the electrical and thermal characteristics of the battery at different times. Through the multi-physical field data fusion and dynamic compensation mechanism, the accurate coupling of the electrochemical response and the thermal interference effect is realized, significantly improving the simulation fidelity of the battery behavior under extreme conditions.

[0077] In a possible embodiment, the electrochemical response unit 122 may include:

[0078] A lithium ion concentration calculation sub-unit 1221 is configured to use the following formula to solve the diffusion equation of dynamic stress coupling based on an improved pseudo-two-dimensional electrochemical model, and generate the concentration gradient distribution of lithium ions on the electrode surface:

[0079]

[0080] where c is the lithium ion concentration, D is the diffusion coefficient, is the Laplace operator of the lithium ion concentration, j is the local current density, F is the Faraday constant, β is the diffusion coefficient correction factor, σ is the stress coupling factor, and ∈ is the electrode strain rate.

[0081] Specifically, by introducing the dynamic stress coupling term quantifying the influence of the mechanical deformation of the electrode on the lithium ion diffusion, the problem that the traditional model ignores the concentration distortion caused by the expansion / shrinkage of the battery is solved.

[0082] A polarization voltage mapping sub-unit 1222 is configured to use the following formula to calculate the transient voltage difference through a dynamic activation energy model according to the concentration gradient distribution:

[0083]

[0084] Wherein, V is the transient voltage difference, R is the gas constant, T is the absolute temperature, is the lithium-ion concentration on the electrode surface, is the lithium-ion concentration in the electrode bulk phase, γ is the activation energy correction parameter, is the exchange current density, j0 is the exchange current density, and α is the reaction order.

[0085] Specifically, the above method uses a dynamic activation energy model to accurately describe the non-linear mutation of the polarization voltage under high-rate charge and discharge, and solve the problem of the linear assumption deviation of the traditional Butler-Volmer equation at high current density.

[0086] The transient voltage generation subunit 1223 is used to superimpose the transient voltage difference on the open-circuit voltage of the battery cell to generate a transient voltage distribution, and the open-circuit voltage is obtained by querying a preset state of charge-open circuit voltage mapping table.

[0087] Specifically, through the state of charge-open circuit voltage dynamic mapping and transient difference compensation, the real-time high-precision prediction of the voltage distribution is realized, the defect that the traditional static open-circuit voltage model cannot reflect the voltage fluctuation under transient power impact is solved, the microscopic mechanism-level simulation of the battery voltage under transient power impact is realized, and the teaching demonstration and R & D test in the scenarios sensitive to high-rate charge and discharge and mechanical deformation are improved.

[0088] In a possible embodiment, the simulation accuracy iteration module 13 may include:

[0089] The deviation regression unit 131 is used to generate accuracy adjustment parameters through a machine learning algorithm based on the deviation data between the thermoelectric coupling simulation data and the output of the simulator.

[0090] Specifically, based on the thermoelectric coupling simulation data and the actual output data of the simulator, the deviation data between the two is calculated. The deviation data can be the difference in parameters such as voltage and temperature at each time point, and a suitable machine learning algorithm is selected, such as linear regression, decision tree regression, or neural network regression, etc. The deviation data is used as the input feature to initialize the machine learning model. Exemplarily, the support vector machine regression (SVR) algorithm can be used. With the deviation data as the input feature, the accuracy adjustment parameters are generated through kernel function mapping and hyperplane optimization. The above method adaptively learns the deviation law through a machine learning algorithm, replaces the traditional fixed threshold calibration strategy, solves the calibration failure problem caused by the non-linear coupling of parameters under complex working conditions, and improves the calibration efficiency.

[0091] The microscopic calibration unit 132 is used to recalibrate the reaction rate and diffusion coefficient of the electrochemical model according to the accuracy adjustment parameters. The reaction rate is used to characterize the insertion / extraction reaction rate of lithium ions on the electrode surface, and the diffusion coefficient is used to characterize the migration ability of lithium ions in the electrode material.

[0092] Specifically, these parameters can be updated by means of linear adjustment, non-linear mapping, etc. The updated reaction rate and diffusion coefficient will be applied to the electrochemical model to improve the simulation accuracy of the model for the actual behavior of the battery, achieve directional calibration of microscopic parameters, avoid model instability caused by global parameter adjustment, and reduce the simulation error.

[0093] The prediction data update unit 133 is used to generate battery state prediction data based on the reaction rate and diffusion coefficient.

[0094] Specifically, the calibrated reaction rate and diffusion coefficient are input into the electrochemical model, and the lithium ion diffusion equation and the charge conservation equation are solved again to generate optimized battery state prediction data. Exemplarily, an iterative convergence algorithm (such as Levenberg-Marquardt) can be used to verify the consistency between the prediction data and the output of the simulator until the mean square error (MSE) is less than a preset threshold. The optimized battery state prediction data can include spatio-temporal distribution maps of voltage, temperature, and SOC. In this embodiment, through machine learning-driven deviation regression, non-linear microscopic parameter calibration, and closed-loop iterative update, the battery simulation error under complex working conditions is reduced, and the authenticity of teaching demonstrations and the reliability of R & D tests are improved.

[0095] In a possible embodiment, the microscopic calibration unit 132 includes:

[0096] The spatio-temporal attention weight generation sub-unit 1321 is used to generate a dynamic weight matrix through an attention mechanism according to the spatio-temporal correlation between the voltage unevenness feature and the capacity attenuation feature.

[0097] Exemplarily, by analyzing the spatio-temporal correlation between the voltage unevenness feature (voltage difference between battery cells) and the capacity attenuation feature (cycle capacity attenuation rate), a dynamic weight matrix is generated using the multi-head attention mechanism. Specifically, the voltage unevenness feature is encoded as a query vector, the capacity attenuation feature is encoded as a key vector, and the time series convolution network is used to extract the time series dependence feature of the deviation data as a value vector. The scaled dot product attention is used to calculate the similarity between the query vector and the key vector, and after Softmax normalization, the value vector is weighted and aggregated to generate a dynamic weight matrix. This matrix is used to quantify the contribution weights of different time steps and spatial positions to parameter calibration, covering the coupling effect of voltage fluctuations and capacity attenuation of each unit within the battery pack. The above method captures long-range dependence relationships through the spatio-temporal attention mechanism, solves the problem of weight allocation deviation caused by traditional methods relying only on local features, and improves the self-adaptability of the calibration strategy to complex working conditions.

[0098] The non-linear parameter mapping sub-unit 1322 is used to map the dynamic weight matrix to the adjustment amounts of the reaction rate and diffusion coefficient, and the adjustment amounts are used to calibrate the reaction rate and diffusion coefficient of the electrochemical model.

[0099] Specifically, the dynamic weight matrix can be input into a pre-trained double-layer fully connected neural network, and the adjustment amounts of the reaction rate and the diffusion coefficient are generated through non-linear activation functions (such as the hyperbolic tangent function and the Sigmoid function). Among them, the hyperbolic tangent function restricts the adjustment amount of the reaction rate within the range of [-1, 1] to avoid parameter mutations; the Sigmoid function limits the adjustment amount of the diffusion coefficient to a [0, 1] scale factor to ensure the physical rationality of the diffusion ability. The calibrated parameters are updated in real time to the electrochemical model to drive high-precision simulation calculations.

[0100] In a possible embodiment, the deviation regression unit 131 includes:

[0101] An error calculation sub-unit 1311, configured to calculate the deviation between the simulator output and the optimized battery state prediction data through the mean square error.

[0102] Specifically, the mean square error can be used to calculate the deviation, which can quantitatively evaluate the difference between the simulator output and the optimized battery state prediction data. The mean square error comprehensively considers the error situations of all data points, avoids the abnormal influence of individual data points, and more comprehensively and objectively reflects the accuracy of the model prediction.

[0103] An instruction generation sub-unit 1312, configured to generate a model recalibration instruction and trigger the prediction data update unit when the deviation exceeds a preset threshold.

[0104] Specifically, by setting the preset threshold, the real-time monitoring of the model accuracy is realized. When the deviation exceeds the threshold, a model recalibration instruction can be generated in time and the prediction data update unit can be triggered, ensuring the accuracy and reliability of the battery state prediction data. The above method realizes the automation from error calculation to instruction generation and triggering, improves the working efficiency of the system, reduces the influence of human factors on model calibration, and ensures the consistency and accuracy of the calibration process.

[0105] In summary, the battery simulation management system of a new energy electric vehicle teaching aid provided by the embodiments of the present application generates a standardized multi-dimensional input matrix by collecting the power fluctuations and ambient temperature sequences of driving conditions in real time; analyzes the lithium-ion diffusion and polarization voltage distribution based on the electrochemical model, combines the unsteady heat conduction equation to quantify the dynamic influence of the temperature gradient on the battery internal resistance, and generates simulation data integrating electro-thermal interaction effects; analyzes the deviation between the simulation data and the output of the simulator through a machine learning algorithm, dynamically allocates calibration weights using a spatio-temporal attention mechanism, and adjusts the microscopic parameters of the electrochemical model through non-linear mapping constraints to achieve the directional optimization of the reaction rate and diffusion coefficient, generates high-fidelity battery state prediction data, and ensures the output consistency through closed-loop verification. The above technical solution can accurately simulate the dynamic response characteristics of the battery to power mutations and temperature sudden changes under complex driving conditions, and provides a battery behavior simulation platform with high precision and strong robustness for the teaching and research of new energy vehicles.

[0106] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be executed in turn or alternately with at least a part of other steps or steps or stages in other steps.

[0107] Based on the same inventive concept, the embodiments of the present application also provide a battery simulation management method for a new energy electric vehicle teaching aid for implementing the battery simulation management system of the new energy electric vehicle teaching aid involved above. The implementation solutions for solving problems provided by this method are similar to the implementation solutions described in the above method. Therefore, the specific limitations in one or more embodiments of the battery simulation management method for a new energy electric vehicle teaching aid provided below can refer to the limitations on the battery simulation management system of the new energy electric vehicle teaching aid in the above text, and will not be repeated here.

[0108] In an exemplary embodiment, as Figure 2 shown, a battery simulation management method for a new energy electric vehicle teaching aid is provided, including:

[0109] Step 101, obtain the power fluctuation data and ambient temperature change sequence of the driving scenario, and generate a dynamic scenario data set.

[0110] Step 102: Generate thermoelectric coupling simulation data based on the dynamic scenario data set through an electrochemical model and thermal management interference analysis.

[0111] Step 103: Dynamically calibrate the microscopic parameters based on the deviation between the thermoelectric coupling simulation data and the output of the simulator, and generate optimized battery state prediction data.

[0112] In a possible embodiment, obtain the power fluctuation data and the environmental temperature change sequence of the driving scenario, and generate a dynamic scenario data set, including:

[0113] Step 201: Obtain the short-term acceleration and braking power demand data, and generate a power fluctuation curve.

[0114] Step 202: Synchronize the power fluctuation curve and the environmental temperature rapid change sequence in time through a sliding window alignment algorithm, and generate a dynamic scenario data set.

[0115] In a possible embodiment, generate thermoelectric coupling simulation data based on the dynamic scenario data set through an electrochemical model and thermal management interference analysis, including:

[0116] Step 301: Normalize the dynamic scenario data set, and construct a multi-dimensional input matrix including power, temperature and time stamp.

[0117] Step 302: Based on the multi-dimensional input matrix, calculate the transient voltage distribution of the battery cell through a preset electrochemical model.

[0118] Step 303: Calculate the thermal management interference effect of the battery cell according to the environmental temperature change sequence and the heat conduction equation.

[0119] Step 304: Integrate the transient voltage distribution and the thermal management interference effect to generate thermoelectric coupling simulation data.

[0120] In a possible embodiment, calculate the transient voltage distribution of the battery cell through a preset electrochemical model based on the multi-dimensional input matrix, including:

[0121] Step 401: Use the following formula to solve the diffusion equation of dynamic stress coupling based on an improved pseudo-two-dimensional electrochemical model, and generate the concentration gradient distribution of lithium ions on the electrode surface:

[0122]

[0123] where c is the lithium ion concentration, D is the diffusion coefficient, is the Laplace operator of the lithium ion concentration, j is the local current density, F is the Faraday constant, β is the diffusion coefficient correction factor, σ is the stress coupling factor, and ∈ is the electrode strain rate.

[0124] Step 402, use the following formula to calculate the transient voltage difference through the dynamic activation energy model according to the concentration gradient distribution:

[0125]

[0126] where V is the transient voltage difference, R is the gas constant, T is the absolute temperature, is the lithium-ion concentration on the electrode surface, is the lithium-ion concentration in the electrode bulk phase, γ is the activation energy correction parameter, is the exchange current density, j0 is the exchange current density, and α is the reaction order.

[0127] Step 403, superimpose the transient voltage difference on the open-circuit voltage of the battery cell to generate a transient voltage distribution, and the open-circuit voltage is obtained by querying a preset state of charge-open circuit voltage mapping table.

[0128] In a possible embodiment, according to the deviation between the thermoelectric coupling simulation data and the output of the simulator, dynamically calibrate the microscopic parameters and generate optimized battery state prediction data, including:

[0129] Step 501, generate accuracy adjustment parameters through a machine learning algorithm based on the deviation data between the thermoelectric coupling simulation data and the output of the simulator.

[0130] Step 502, recalibrate the reaction rate and diffusion coefficient of the electrochemical model according to the accuracy adjustment parameters. The reaction rate is used to characterize the embedding / delithiation reaction rate of lithium ions on the electrode surface, and the diffusion coefficient is used to characterize the migration ability of lithium ions in the electrode material.

[0131] Step 503, generate battery state prediction data based on the reaction rate and diffusion coefficient.

[0132] In a possible embodiment, recalibrating the reaction rate and diffusion coefficient of the electrochemical model according to the accuracy adjustment parameters includes:

[0133] Step 601, generate a dynamic weight matrix through an attention mechanism according to the spatio-temporal correlation between the voltage unevenness feature and the capacity decay feature.

[0134] Step 602, map the dynamic weight matrix to the adjustment amounts of the reaction rate and diffusion coefficient, and the adjustment amounts are used to calibrate the reaction rate and diffusion coefficient of the electrochemical model.

[0135] In a possible embodiment, generating accuracy adjustment parameters through a machine learning algorithm based on the deviation data between the thermoelectric coupling simulation data and the output of the simulator includes:

[0136] Step 701, calculate the deviation between the output of the simulator and the optimized battery state prediction data through the mean square error.

[0137] Step 702: When the deviation exceeds a preset threshold, generate a model recalibration instruction and trigger the prediction data update unit.

[0138] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the battery simulation management method of the new energy electric vehicle teaching aid as described above are implemented.

[0139] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0140] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the partial descriptions of the method embodiments. The device embodiments described above are only illustrative. The components described as separate components may or may not be physically separated, and the components shown 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 modules can be selected according to actual needs to achieve the purpose of the present disclosure solution. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0141] The above embodiments only represent several implementation manners of the embodiments of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the embodiments of the application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the embodiments of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the embodiments of the present application.

Claims

1. A battery simulation management system for a new energy electric vehicle teaching aid, characterized in that, It includes a dynamic scenario data generation module, a thermoelectric coupling simulation module, and a simulation accuracy iteration module: The dynamic scenario data generation module is used to obtain the power fluctuation data and the environmental temperature change sequence of the driving scenario, and generate a dynamic scenario data set; The thermoelectric coupling simulation module is used to generate thermoelectric coupling simulation data based on the dynamic scenario data set through an electrochemical model and thermal management interference analysis; The simulation accuracy iteration module is used to dynamically calibrate microscopic parameters and generate optimized battery state prediction data according to the deviation between the thermoelectric coupling simulation data and the output of the simulator.

2. The method according to claim 1, characterized in that, The dynamic scenario data generation module includes: The power fluctuation acquisition unit is used to obtain the short-term acceleration and braking power demand data and generate a power fluctuation curve; The temperature sequence fusion unit is used to synchronize the power fluctuation curve and the environmental temperature rapid change sequence in time through a sliding window alignment algorithm to generate the dynamic scenario data set.

3. The system according to claim 1, wherein The thermoelectric coupling simulation module includes: The multi-dimensional matrix construction unit is used to normalize the dynamic scenario data set and construct a multi-dimensional input matrix including power, temperature, and time stamps; The electrochemical response unit is used to calculate the transient voltage distribution of the battery unit based on the multi-dimensional input matrix through a preset electrochemical model; The thermal interference analysis unit is used to calculate the thermal management interference effect of the battery unit according to the environmental temperature change sequence and the heat conduction equation; The coupling matrix generation unit is used to fuse the transient voltage distribution and the thermal management interference effect to generate thermoelectric coupling simulation data.

4. The system according to claim 3, wherein The electrochemical response unit includes: The lithium ion concentration calculation sub-unit is used to solve the diffusion equation of dynamic stress coupling based on an improved pseudo-two-dimensional electrochemical model using the following formula to generate the concentration gradient distribution of lithium ions on the electrode surface: where c is the lithium ion concentration, D is the diffusion coefficient, is the Laplace operator of the lithium ion concentration, j is the local current density, F is the Faraday constant, β is the diffusion coefficient correction factor, σ is the stress coupling factor, and ∈ is the electrode strain rate; The polarization voltage mapping sub-unit is used to calculate the transient voltage difference through a dynamic activation energy model according to the concentration gradient distribution using the following formula: wherein, V is the transient voltage difference, R is the gas constant, T is the absolute temperature, is the lithium ion concentration on the electrode surface, is the lithium ion concentration in the electrode bulk phase, γ is the activation energy correction parameter, is the exchange current density, j0 is the exchange current density, and α is the reaction order; The transient voltage generation sub-unit is used to superimpose the transient voltage difference on the open circuit voltage of the battery unit to generate the transient voltage distribution, and the open circuit voltage is obtained by querying a preset state of charge-open circuit voltage mapping table.

5. The system according to claim 1, characterized in that, The simulation accuracy iteration module includes: The deviation regression unit is used to generate accuracy adjustment parameters through a machine learning algorithm based on the deviation data between the thermoelectric coupling simulation data and the output of the simulator; The microscopic calibration unit is used to recalibrate the reaction rate and diffusion coefficient of the electrochemical model according to the accuracy adjustment parameters. The reaction rate is used to characterize the insertion / extraction reaction rate of lithium ions on the electrode surface, and the diffusion coefficient is used to characterize the migration ability of lithium ions in the electrode material; The prediction data update unit is used to generate the battery state prediction data based on the reaction rate and the diffusion coefficient.

6. The system according to claim 5, wherein The microscopic calibration unit includes: The spatio-temporal attention weight generation sub-unit is used to generate a dynamic weight matrix through an attention mechanism according to the spatio-temporal correlation of the voltage unevenness feature and the capacity attenuation feature; A non-linear parameter mapping sub-unit, configured to map the dynamic weight matrix to the adjustment amounts of the reaction rate and the diffusion coefficient, where the adjustment amounts are used to calibrate the reaction rate and the diffusion coefficient of the electro-chemical model.

7. The system according to claim 5, wherein The deviation regression unit includes: An error calculation sub-unit, configured to calculate the deviation between the simulator output and the optimized battery state prediction data by using the mean square error; An instruction generation sub-unit, configured to generate a model recalibration instruction and trigger the prediction data update unit when the deviation exceeds a preset threshold.

8. A battery simulation management method for a teaching aid of a new energy electric vehicle, characterized in that, The method includes: Obtaining power fluctuation data and an environmental temperature change sequence of a driving scenario to generate a dynamic scenario data set; Generating thermoelectric coupling simulation data based on the dynamic scenario data set through electro-chemical model and thermal management interference analysis; Dynamically calibrating microscopic parameters according to the deviation between the thermoelectric coupling simulation data and the simulator output, and generating optimized battery state prediction data.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the method according to claim 8 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the method according to claim 8 is implemented.

Images