Development method and device of battery management system, computer equipment and storage medium

Abstract

The invention relates to the technical field of batteries, and discloses a development method and device of a battery management system, computer equipment and a storage medium, the battery management system corresponds to a pre-constructed initial system model, and the initial system model is a simulation model constructed for a battery hardware part and a software part corresponding to the battery management system. If the battery management system has a demand change or a specified type of defect problem, tracing to the initial system model, and performing parameter updating on the initial system model to obtain an updated system model; and if the updated system model passes the verification of the test environment, deploying an execution control corresponding to a simulation model corresponding to the software part in the updated system model in a control chip of the battery management system. Through the development method taking the initial system model as the center, the problem tracing process is greatly simplified.

Description

Technical Field

[0001] The present application relates to the field of battery technology, and in particular to a method, device, computer equipment and storage medium for developing a battery management system. Background Art

[0002] The battery management system (BMS) is the core component of the battery pack, which is mainly responsible for ensuring the safe, stable and efficient operation of the battery pack.

[0003] In related technologies, the development of battery management systems adopts a waterfall model, with demand analysis, design, development, testing, and deployment progressing in a one-way, gradual manner. If problems occur during the development process, errors will gradually accumulate and may cause greater uncertainty in subsequent stages, making it difficult to trace the source of the problem. Therefore, it is urgent to propose a new development method for battery management systems. Summary of the invention

[0004] The present application provides a method, device, computer equipment and storage medium for developing a battery management system, which solves the technical problem of difficulty in tracing the source after a problem is discovered in the related technology, and achieves the technical effect of simplifying tracing the source after a problem is discovered.

[0005] In order to achieve the above objectives, the main technical solutions adopted in this application include:

[0006] In a first aspect, an embodiment of the present application provides a method for developing a battery management system, wherein the battery management system corresponds to a pre-built initial system model, and the initial system model is a simulation model constructed for a battery hardware part and a software part corresponding to the battery management system; the method comprises:

[0007] If there is a demand change or a specified type of defect problem for the battery management system, trace it back to the initial system model, and update the parameters of the initial system model to obtain an updated system model;

[0008] If the updated system model passes the verification of the test environment, the execution control corresponding to the simulation model corresponding to the software part in the updated system model is deployed in the control chip of the battery management system.

[0009] Optionally, the initial system model includes a battery simulation model corresponding to the battery hardware part and a prediction algorithm model corresponding to the software part; and updating parameters of the initial system model to obtain an updated system model includes:

[0010] Parameters of the battery simulation model and / or the prediction algorithm model in the initial system model are updated to obtain the updated system model.

[0011] Optionally, the battery simulation model in the initial system model is constructed in the following manner:

[0012] Obtain actual charge and discharge data of the actual battery pack and build an initial battery model;

[0013] Performing model-in-the-loop simulation on the initial battery model using actual charge and discharge data of the actual battery pack to obtain a model-in-the-loop simulation result;

[0014] The parameters of the initial battery model are adjusted according to the model-in-the-loop simulation result to obtain a battery simulation model in the initial system model.

[0015] Optionally, the prediction algorithm model in the initial system model is constructed in the following manner:

[0016] Build the initial algorithm model;

[0017] Using the battery simulation model to perform charge and discharge simulation, obtaining first simulation voltage data, first simulation current data, first simulation temperature data and first simulation management parameters;

[0018] Inputting the first simulation voltage data, the first simulation current data and the first simulation temperature data into the initial algorithm model for prediction to obtain a first battery management parameter;

[0019] The initial algorithm model is adjusted in parameters according to the first simulation management parameter and the first battery management parameter to obtain a prediction algorithm model corresponding to the software part.

[0020] Optionally, after obtaining the updated system model, the method further includes:

[0021] Determine actual battery management parameters of an actual battery pack during an actual charging and discharging process; wherein the actual battery pack is configured with a voltage sensor, a current sensor, and a temperature sensor;

[0022] Acquire voltage data collected by the voltage sensor, current data collected by the current sensor, and temperature data collected by the temperature sensor;

[0023] Inputting the voltage data, the current data and the temperature data into the prediction algorithm model for prediction to obtain a second battery management parameter;

[0024] The prediction algorithm model is updated according to the actual battery management parameter and the second battery management parameter.

[0025] Optionally, after obtaining the updated system model, the method further includes:

[0026] Using the battery simulation model to perform charge and discharge simulation, obtain second simulation voltage data, second simulation current data, second simulation temperature data and second simulation management parameters; wherein the second simulation voltage data, the second simulation current data and the second simulation temperature data are used to predict the second battery management parameters;

[0027] The prediction algorithm model is updated according to the second simulation management parameter and the second battery management parameter.

[0028] Optionally, the method further comprises:

[0029] If the updated system model fails to pass the verification of the test environment, continue to update parameters of the updated system model until it passes the verification of the test environment.

[0030] Optionally, if a specified type of defect occurs in the battery management system, the defect is traced back to the initial system model, and parameters of the initial system model are updated to obtain an updated system model, including:

[0031] If the accuracy of the prediction result of the prediction algorithm model exceeds the allowable accuracy range, trace back to the initial system model; wherein the initial system model includes the prediction algorithm model corresponding to the software part;

[0032] The prediction algorithm model in the initial system model is parameter updated to obtain the updated system model.

[0033] Optionally, if the battery management system has a demand change, tracing back to the initial system model, and updating the parameters of the initial system model to obtain an updated system model includes:

[0034] If there is a need to develop a new type of battery pack for the battery management system, the initial system model is determined in the existing system model; wherein the initial system model includes a battery simulation model corresponding to the battery hardware part and a prediction algorithm model corresponding to the software part;

[0035] Performing a model-in-the-loop simulation on the battery simulation model, and updating parameters of the battery simulation model based on the model-in-the-loop simulation to obtain an updated battery simulation model;

[0036] The updated battery simulation model is used to perform charge and discharge simulation on the prediction algorithm model, and the parameters of the prediction algorithm model are updated based on the charge and discharge simulation results to obtain an updated prediction algorithm model; wherein the updated system model includes the updated battery simulation model and the updated prediction algorithm model.

[0037] In a second aspect, an embodiment of the present application provides a development device for a battery management system, wherein the battery management system corresponds to a pre-built initial system model, and the initial system model is a simulation model constructed for a battery hardware part and a software part corresponding to the battery management system; the device comprises:

[0038] A traceability update module, used for tracing back to the initial system model if there is a demand change or a specified type of defect problem for the battery management system, and updating the parameters of the initial system model to obtain an updated system model;

[0039] A control deployment module is used to deploy the execution control corresponding to the prediction algorithm model of the software part in the updated system model in the control chip of the battery management system if the updated system model passes the verification of the test environment.

[0040] In a third aspect, an embodiment of the present application provides a computer device, including:

[0041] A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method described in any of the above embodiments by executing the computer instructions.

[0042] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to enable a computer to execute the method described in any of the above embodiments.

[0043] The development method of the battery management system provided in the embodiment of the present application, the battery management system corresponds to a pre-built initial system model, and the initial system model is a simulation model built for the battery hardware part and software part corresponding to the battery management system. If there is a demand change or a specified type of defect problem for the battery management system, trace it back to the initial system model, and update the parameters of the initial system model to obtain an updated system model; if the updated system model passes the verification of the test environment, the execution control corresponding to the simulation model corresponding to the software part in the updated system model is deployed in the control chip of the battery management system. During the entire development process from demand design, testing to maintenance, no matter what problems arise, they can be quickly traced back to the initial system model, and the problems can be quickly fixed by modifying the initial system model. It can be seen that the embodiment of the present application implements a development method centered on the initial system model, which greatly simplifies the process of tracing the source of the problem. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0045] Figure 1 A flow chart of a method for developing a battery management system provided in an embodiment of this specification;

[0046] Figure 2 A schematic diagram of an initial system model provided for the embodiments of this specification;

[0047] Figure 3 A flow chart of a method for developing a battery management system provided in an embodiment of this specification;

[0048] Figure 4a A flow chart of a method for developing a battery management system provided in an embodiment of this specification;

[0049] Figure 4b A schematic diagram of a system simulation model provided in an embodiment of this specification;

[0050] Figure 5 A flow chart of a method for developing a battery management system provided in an embodiment of this specification;

[0051] Figure 6 A flow chart of a method for developing a battery management system provided in an embodiment of this specification;

[0052] Figure 7a A flow chart of a method for developing a battery management system provided in an embodiment of this specification;

[0053] Figure 7b A schematic diagram of a verification process for modifying a specified type of defect provided in an embodiment of this specification;

[0054] Figure 8a A flow chart of a method for developing a battery management system provided in an embodiment of this specification;

[0055] Figure 8b A schematic diagram of a new requirement development verification process provided in the embodiments of this specification;

[0056] Fig. 9 A schematic diagram of a development device for a battery management system provided in an embodiment of this specification;

[0057] Fig.10 A schematic diagram of the structure of a computer device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0059] In the related art, the development process of the battery management system usually adopts the waterfall model, which is a one-way step-down development mode. The whole process is divided into stages such as demand analysis, design, implementation, testing, and deployment. The output of each stage is directly used as the input of the next stage. In this mode, the development team usually advances step by step in a predetermined order, and enters the next stage only after the work of each stage is completed. However, the waterfall development model has certain limitations, especially when facing complex systems such as battery management systems. If problems or errors occur during the development process, it may lead to increased uncertainty in the entire development chain. Since the development of each stage is carried out linearly, the feedback of the problem is often delayed, which makes it difficult to quickly locate the root cause of the problem when the problem is discovered. In particular, defects that occur in the design or implementation stage may gradually magnify in subsequent stages, and ultimately affect the overall stability and function of the system. In this case, the tracing of the problem often requires reverse tracing, and the developer needs to go back to the previous stage to review each work again, which not only consumes a lot of time and resources, but also may cause serious delays in the development progress. Therefore, in the development process of the battery management system, in the face of increasingly complex technical requirements and rapidly changing market environment, the limitations of the traditional waterfall development model in solving problems have become increasingly obvious.

[0060] Based on this, the present application provides a method for developing a battery management system, and the battery management system corresponds to a pre-built initial system model, and the initial system model is a simulation model built for the battery hardware part and software part corresponding to the battery management system. If there is a demand change or a specified type of defect problem for the battery management system, trace it back to the initial system model, and update the parameters of the initial system model to obtain an updated system model; if the updated system model passes the verification of the test environment, the execution control corresponding to the simulation model corresponding to the software part in the updated system model is deployed in the control chip of the battery management system. Through the development method centered on the initial system model, not only the process of tracing the source of the problem is greatly simplified, but also the efficiency of problem solving is significantly improved. This method can effectively shorten the development cycle, reduce the risks caused by tracing the source of the problem, and make the development process of the battery management system more controllable.

[0061] According to an embodiment of the present application, an embodiment of a method for developing a battery management system is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0062] See also Figure 1 In the development method of the battery management system provided in the embodiment of the present application, the battery management system corresponds to a pre-built initial system model, which is a simulation model built for the battery hardware part and software part corresponding to the battery management system. The steps of the development method include:

[0063] S110: If there is a demand change or a specified type of defect problem for the battery management system, trace it back to the initial system model, and update the parameters of the initial system model to obtain an updated system model.

[0064] S120: If the updated system model passes the verification of the test environment, the execution control corresponding to the simulation model corresponding to the software part in the updated system model is deployed in the control chip of the battery management system.

[0065] Among them, the initial system model includes a simulation model corresponding to the battery hardware part and a simulation model corresponding to the software part. The simulation model corresponding to the hardware part and the simulation model corresponding to the software part can be linked. The simulation model corresponding to the battery hardware part can output electrical signals, thermodynamic signals, etc., and the simulation model corresponding to the software part can implement the battery management algorithm, such as state estimation algorithm, charge and discharge control strategy, thermal management strategy, etc. The specified type defect problem can be a problem related to the initial system model parameters, or the accuracy of the output of the simulation model corresponding to the software part exceeds the allowable accuracy range.

[0066] In this embodiment, the requirement change for the battery management system may be the need to develop software required for a new type of battery hardware, which can be implemented by following the steps below:

[0067] 1) Update the simulation model of the battery hardware. First, conduct experiments to test the charge and discharge of the new type of battery hardware and record several sets of experimental data, including experimental data on electrical properties and thermodynamic properties. Then use the Model-In-the-Loop (MIL) mode to perform the same experimental process on the simulation model of the battery hardware in the initial system model. By constantly comparing the differences between the experimental data output by the simulation and the experimental data on the new type of battery hardware, the parameters in the simulation model of the battery hardware are gradually adjusted and optimized, and finally the accurate fitting of the model is achieved.

[0068] 2) Update the simulation model of the software part. Because the software part will have multiple functions, each function can correspond to a sub-model. According to the simulation model of the updated battery hardware part, update the parameters in each sub-model in turn. Taking the battery SOC estimation as an example, first connect the simulation model output of the battery hardware part with the input of the prediction algorithm sub-model. During the simulation process, the battery hardware part is charged and discharged, and the real SOC value of the battery simulation model is calculated by the integrator.

[0069] At the same time, the prediction algorithm model outputs the SOC prediction value. By comparing the difference between the SOC prediction value and the SOC real value, the parameters in the SOC prediction algorithm sub-model can be continuously adjusted and optimized to achieve the final accurate fit. After each sub-model parameter is updated, the simulation model of the updated software part can be obtained.

[0070] 3) Verify in a test environment. First, convert the simulation model of the updated software part into code through tools or manually write code, then compile it into execution control and embed it into the control chip. Next, connect the output of the new type of battery hardware to the control chip to ensure that the control chip can receive real-time data from the battery hardware.

[0071] During verification in a test environment, if each function passes verification and can effectively work with the hardware, the execution control can be deployed to the control chip of the battery management system and officially put into use.

[0072] In this embodiment, the requirements of the battery management system may be changed, or the characteristics of the existing battery hardware may be modified. At this point, it is necessary to evaluate the impact of these changes on the initial system model, which may involve adjustments in battery performance, charge and discharge characteristics, temperature changes, etc. Conduct corresponding experiments and simulations for these changes to ensure that the new hardware characteristics can be accurately reflected in the updated system model. You can first perform MIL simulation based on the experimental data of the modified battery hardware to update the simulation model of the battery hardware part; then, based on the update of the simulation model of the battery hardware part, further evaluate the impact on the simulation model of the software part, simulate the affected sub-models in turn, and update the parameters of the simulation model of the software part; after completing the update of the simulation model of the battery hardware and software parts, enter the test environment for verification.

[0073] In this embodiment, the demand change for the battery management system can also be a change in the control strategy of the battery hardware in the software. In this case, the simulation model of the battery hardware part in the initial system model usually does not need to be changed, but only the parameters of the sub-model related to the control strategy in the simulation model of the software part need to be updated. After the update is completed, the updated system model is verified to ensure that the new control strategy can run normally in the simulation environment and achieve the expected results. After the verification is passed, you can enter the actual test environment for further verification to ensure that it can run stably and effectively on real hardware.

[0074] In this embodiment, when verifying in the actual test environment, if there are problems related to the initial system model, it is necessary to adjust the relevant initial system model parameters. After the adjustment, first verify in the simulation environment to ensure that the problem is solved. After the simulation verification is passed, the simulation model of the modified software part is converted into code, the control is generated, and embedded in the actual test environment for verification. This process may be carried out multiple times until it is verified in the actual test environment to ensure that the performance and stability of the system meet the requirements.

[0075] In the development method of the battery management system in the above-mentioned embodiment, the battery management system corresponds to a pre-built initial system model, and the initial system model is a simulation model built for the battery hardware and software parts corresponding to the battery management system. If there is a demand change or a specified type of defect problem for the battery management system, trace it back to the initial system model, and update the parameters of the initial system model to obtain an updated system model; if the updated system model passes the verification of the test environment, the execution control corresponding to the simulation model corresponding to the software part in the updated system model is deployed in the control chip of the battery management system. Through the development method centered on the initial system model, not only the process of tracing the source of the problem is greatly simplified, but also the efficiency of problem solving is significantly improved. This method can effectively shorten the development cycle, reduce the risks caused by tracing the source of the problem, and make the development process of the battery management system more controllable.

[0076] In some embodiments, see Figure 2 The initial system model includes a battery simulation model corresponding to the battery hardware part and a prediction algorithm model corresponding to the software part; updating the parameters of the initial system model to obtain an updated system model includes: updating the parameters of the battery simulation model and / or the prediction algorithm model in the initial system model to obtain an updated system model.

[0077] Among them, the battery simulation model can be composed of an electrical characteristic model and a thermodynamic characteristic model, outputting parameters such as voltage, current and temperature in real time, and inputting these data into the prediction algorithm model for predicting the battery status, such as SOC, SOP, SOE, and SOH.

[0078] In this embodiment, when there is a demand change, such as a new type of battery with a change in physical specifications, a small increase in capacity, a small change in voltage range, etc., but the prediction algorithm is still applicable, the battery simulation model in the initial system model can be updated through MIL based on the data of the charge and discharge experiment of the new type of battery. The updated battery simulation model and the prediction algorithm model in the initial system model constitute the updated system model.

[0079] In this embodiment, when a specified type of defect problem occurs, such as when testing on certain batteries of the same type, the performance of the noise data is different from that of previously verified batteries, resulting in the insufficient accuracy of the prediction algorithm in certain scenarios, it is usually necessary to update the prediction algorithm model without updating the battery simulation model. The battery simulation model in the initial system model and the updated prediction algorithm model constitute the updated system model.

[0080] In this embodiment, when the physical specifications of the new type of battery change significantly and the prediction algorithm is no longer applicable, both the battery simulation model and the prediction algorithm model in the initial system model need to be updated with parameters to obtain an updated system model.

[0081] It is understandable that the updated system model needs to be verified in a simulation environment first to ensure that the prediction algorithm can run normally and achieve the expected results in the simulation environment, such as the prediction accuracy error is within 3%. Then enter the actual test environment for further verification to ensure that it can run stably and effectively on real hardware.

[0082] In the above embodiment, according to the specific situation of the demand change or the specified type of defect problem, the battery simulation model and / or the prediction algorithm model in the initial system model are updated with parameters to obtain an updated system model. The development method centered on the initial system model effectively shortens the development cycle and greatly simplifies the process of tracing the source of the problem.

[0083] In some embodiments, please refer to Figure 3 , the battery simulation model in the initial system model is constructed in the following way:

[0084] S310: Acquire actual charge and discharge data of an actual battery pack and construct an initial battery model.

[0085] S320: Perform model-in-the-loop simulation on the initial battery model using actual charge and discharge data of the actual battery pack to obtain a model-in-the-loop simulation result.

[0086] S330 , adjusting parameters of the initial battery model according to the model-in-the-loop simulation results to obtain a battery simulation model in the initial system model.

[0087] The actual charge and discharge data may be data collected during the charge and discharge experiment of the actual battery pack, including the charge and discharge current value, charge and discharge time length, voltage change, temperature change, etc. The initial battery model may include a battery electrical characteristic model and a thermodynamic model, which includes a set of undetermined battery characteristic parameters, such as capacitance, internal resistance, energy efficiency, heat generation efficiency, etc.

[0088] In this embodiment, when a new type of battery pack prediction algorithm development requirement is received, the battery pack can first be charged and discharged by a dual peak battery parameter test (HPPC) or a combination of a discharge peak battery parameter test and a charge peak battery parameter test (DPPC & CPPC), and several groups of experimental data can be recorded, including the current value of charge and discharge, the length of charge and discharge time, the voltage change, and the temperature change; then a model-in-the-loop simulation is performed in Matlab, and the above-mentioned charge and discharge experimental process is repeated on the initial battery model, and the voltage change, temperature change of the simulation output and the error of the corresponding real battery experimental data are compared, and the parameters of the model are continuously adjusted until the output result of the model reaches the expected standard, and a set of optimal battery characteristic parameters are obtained, such as capacitance, internal resistance, energy efficiency, heating efficiency, etc. The parameters of the initial battery model are adjusted by these obtained parameters to obtain a battery simulation model in the initial system model.

[0089] In the above embodiment, the actual charge and discharge data of the actual battery pack is first obtained, and the initial battery model is constructed; then, the initial battery model is simulated in the model-in-the-loop using the actual charge and discharge data of the actual battery pack to obtain the model-in-the-loop simulation result; finally, the parameters of the initial battery model are adjusted according to the model-in-the-loop simulation result to obtain the battery simulation model in the initial system model. This battery simulation model provides a solid foundation for the rapid development of the prediction algorithm.

[0090] In some embodiments, please refer to Figure 4a , the prediction algorithm model in the initial system model is constructed in the following way:

[0091] S410: construct an initial algorithm model.

[0092] S420, performing charge and discharge simulation using a battery simulation model to obtain first simulation voltage data, first simulation current data, first simulation temperature data, and first simulation management parameters.

[0093] S430: Input the first simulation voltage data, the first simulation current data and the first simulation temperature data into an initial algorithm model for prediction to obtain a first battery management parameter.

[0094] S440, adjusting the parameters of the initial algorithm model according to the first simulation management parameter and the first battery management parameter to obtain a prediction algorithm model corresponding to the software part.

[0095] Among them, the initial algorithm model cannot directly make accurate predictions, and it is necessary to fit several parameters according to the charge and discharge simulation data of the battery simulation model. For example, when using a Kalman filter to predict battery parameters, it is necessary to fit the parameters in the covariance matrix. The first simulation management parameter can be the state value of the battery simulation model at different times obtained according to the integrator connected to the battery simulation model, such as the real value of SOC, SOE, SOH, and SOP in the simulation. The first battery management parameter can be the state value of the battery simulation model predicted by the prediction algorithm model, such as the predicted value of SOC, SOE, SOH, and SOP in the simulation.

[0096] In this embodiment, please refer to Figure 4b , the initial system model includes a battery simulation model 401 and an initial algorithm model 402, wherein the battery simulation model 401 includes an electrical characteristic model 403 and a thermodynamic model 404. Develop a management parameter prediction algorithm for a new type of battery, connect the output end of the voltage, current and temperature data of the battery simulation model 401 corresponding to the new type of battery to the input end of the initial algorithm model 402, and the initial algorithm model 402 is also provided with an initial management parameter value. Use the battery simulation model 401 to charge and discharge, and obtain the first simulation voltage data, the first simulation current data, the first simulation temperature data and the first simulation management parameter; wherein the first simulation voltage data, the first simulation current data and the first simulation temperature data can be automatically input into the initial algorithm model 402, and the initial algorithm model 402 predicts based on these data and the values ​​of the initial management parameters to obtain the first battery management parameters. Then adjust the parameters of the initial algorithm model 402 according to the difference between the first battery management parameters and the first simulation management parameters to obtain the intermediate algorithm model. By repeating the above process, the parameters in the intermediate algorithm model can be continuously adjusted until the difference between the first battery management parameter and the first simulation management parameter reaches the expected standard, and a set of optimal parameters is obtained and applied to the model to obtain the prediction algorithm model corresponding to the software part.

[0097] In the above embodiment, an initial algorithm model is first constructed; then, a battery simulation model is used to perform charge and discharge simulation to obtain first simulation voltage data, first simulation current data, first simulation temperature data and first simulation management parameters; then, the first simulation voltage data, first simulation current data and first simulation temperature data are input into the initial algorithm model for prediction to obtain first battery management parameters; finally, the initial algorithm model is adjusted according to the first simulation management parameters and the first battery management parameters to quickly obtain the prediction algorithm model corresponding to the software part.

[0098] In some embodiments, please refer to Figure 5 , after obtaining the updated system model, the development method also includes:

[0099] S510: Determine actual battery management parameters of an actual battery pack during an actual charging and discharging process.

[0100] Among them, the actual battery pack is equipped with a voltage sensor, a current sensor and a temperature sensor.

[0101] S520: Acquire voltage data collected by the voltage sensor, current data collected by the current sensor, and temperature data collected by the temperature sensor.

[0102] S530: Input the voltage data, current data and temperature data into a prediction algorithm model for prediction to obtain a second battery management parameter.

[0103] S540: Update the parameters of the prediction algorithm model according to the actual battery management parameters and the second battery management parameters.

[0104] The actual battery management parameters can be the battery status data of the actual battery pack during the actual charging and discharging process, such as the real values ​​of SOC, SOE, SOH, and SOP. When the initial battery status data is known, the current actual battery management parameters can be obtained by calculation after a period of charging and discharging, for example:

[0105] △Q=∫ 0 t I(τ)dτ

[0106]

[0107] I(τ) is the charge or discharge current at time τ, t is the charge or discharge time, △Q is the charge change, C nominal is the nominal capacity of the battery, SOC 0 is the initial SOC value.

[0108] In this embodiment, after the prediction algorithm model is connected to the battery simulation model and verified, or after the battery simulation model is connected to the control chip and verified, it is also necessary to verify the performance of the prediction algorithm model when connected to the real hardware through hardware in the loop (HIL), that is, to verify in a verification environment where the prediction algorithm model is connected to the actual battery pack through a voltage sensor, a current sensor, and a temperature sensor. First, the actual battery pack is actually charged and discharged, and the prediction algorithm model obtains the voltage data collected by the voltage sensor, the current data collected by the current sensor, and the temperature data collected by the temperature sensor; then the prediction algorithm model predicts the actual battery management parameters according to the voltage data, the current data, the temperature data, and the initial values ​​of the actual battery management parameters of the actual battery pack to obtain the second battery management parameters, which are compared with the calculated actual battery management parameters; finally, the prediction algorithm model is adjusted according to the difference between the second battery management parameters and the actual battery management parameters to obtain the HIL intermediate prediction algorithm model. By repeating the above process, the parameters in the HIL intermediate prediction algorithm model can be continuously adjusted until the difference between the second battery management parameters and the actual battery management parameters reaches the expected standard, and a set of optimal parameters is obtained, and this set of parameters is used to update the parameters of the prediction algorithm model.

[0109] In the above embodiment, the actual battery management parameters of the actual battery pack during the actual charging and discharging process are first determined; then the voltage data collected by the voltage sensor, the current data collected by the current sensor, and the temperature data collected by the temperature sensor are obtained; then the voltage data, current data, and temperature data are input into the prediction algorithm model for prediction to obtain the second battery management parameters; finally, the prediction algorithm model is updated according to the actual battery management parameters and the second battery management parameters. The consistency between the prediction algorithm and the actual battery pack and sensor data is quickly verified through hardware-in-the-loop testing, ensuring the reliability and accuracy of the prediction algorithm.

[0110] In some embodiments, please refer to Figure 6 , after obtaining the updated system model, the battery management system development method also includes:

[0111] S610 , performing charge and discharge simulation using a battery simulation model to obtain second simulation voltage data, second simulation current data, second simulation temperature data, and second simulation management parameters.

[0112] S620: Update the parameters of the prediction algorithm model according to the second simulation management parameter and the second battery management parameter.

[0113] Among them, the second battery management parameter is obtained by predicting the second simulation voltage data, the second simulation current data and the second simulation temperature data through the execution control in the control chip, such as the predicted values ​​of SOC, SOE, SOH and SOP of the battery simulation model.

[0114] The second simulation management parameter may be a state value of the battery simulation model at different times obtained according to an integrator connected to the battery simulation model, such as real values ​​of SOC, SOE, SOH, and SOP in the simulation.

[0115] Specifically, after the prediction algorithm model is connected to the battery simulation model and verified, or after the prediction algorithm model is connected to the actual battery pack and sensor and verified, it is also necessary to verify the performance of the prediction algorithm control when it is running in the control chip through the processor in the loop (PIL), that is, the prediction algorithm model is converted into code, compiled into an execution control and embedded in the control chip, and the control chip is connected to the battery simulation model to verify the prediction algorithm. First, the battery simulation model is charged and discharged to obtain the second simulation voltage data, the second simulation current data, and the second simulation temperature data, which are input into the control chip; then the execution control obtains the second battery management parameter according to the second simulation voltage data, the second simulation current data, the second simulation temperature data and the initial value of the second battery management parameter; finally, the prediction algorithm model is adjusted according to the difference between the second battery management parameter and the second simulation management parameter to obtain the PIL intermediate prediction algorithm model. By repeating the above process, the parameters in the PIL intermediate prediction algorithm model can be continuously adjusted until the difference between the second battery management parameter and the second simulation management parameter reaches the expected standard, and a set of optimal parameters are obtained, and this set of parameters is used to update the parameters of the prediction algorithm model.

[0116] In the above embodiment, the battery simulation model is first used to perform charge and discharge simulation to obtain the second simulation voltage data, the second simulation current data, the second simulation temperature data and the second simulation management parameter; then the prediction algorithm model is updated according to the second simulation management parameter and the second battery management parameter. The consistency between the prediction algorithm and the control chip is quickly verified through the processor in the loop, ensuring the reliability and accuracy of the prediction algorithm.

[0117] In some embodiments, the method for developing a battery management system further includes: if the updated system model fails to pass the verification of the test environment, continuing to update parameters of the updated system model until it passes the verification of the test environment.

[0118] Specifically, if the updated system model fails to pass the verification of the test environment, and after analysis, it is found that it is a problem with the simulation model of the battery hardware part, for example, a certain characteristic performance of the battery hardware used in the test environment is different from the battery hardware used when the updated system model is obtained, in this case, the battery hardware model needs to be updated first; then, based on the update of the simulation model of the battery hardware part, the impact on the simulation model of the software part is further evaluated, the affected sub-models are simulated in turn, and the parameters of the simulation model of the software part are updated; after completing the update of the simulation model of the battery hardware and software parts, enter the test environment for verification. If the verification finds that the above problems are not solved, continue to repeat the process until the verification of the test environment is passed.

[0119] If the updated system model fails to pass the verification of the test environment, and after analysis it is found that it is a problem with the simulation model of the software part, for example, when testing on certain battery packs of the same type of battery, the performance of the noise data is different from that of the previously verified battery packs, resulting in insufficient accuracy of the prediction algorithm in certain scenarios, in this case, only the simulation model of the software part needs to be updated, and there is no need to update the simulation model of the battery hardware part, and then enter the test environment for verification. If the verification finds that the above problem has not been resolved, continue to repeat the process until the verification of the test environment is passed.

[0120] In some embodiments, please refer to Figure 7a If a specified type of defect occurs in the battery management system, the source is traced back to the initial system model, and the parameters of the initial system model are updated to obtain the updated system model, including:

[0121] S710: If the accuracy of the prediction result of the prediction algorithm model exceeds the allowable accuracy range, trace back to the initial system model.

[0122] Among them, the initial system model includes the prediction algorithm model corresponding to the software part;

[0123] S720: Update the parameters of the prediction algorithm model in the initial system model to obtain an updated system model.

[0124] Among them, the accuracy of the prediction result can be the degree of error between the predicted value and the actual value of the battery hardware management parameter, which is usually measured by some statistical indicators, such as mean square error, mean absolute error, etc.

[0125] For details, please refer to Figure 7b, if the accuracy of the prediction result of the prediction algorithm model exceeds the allowable accuracy range, for example, due to the insufficient accuracy of the sensor and the poor quality of the measurement data, the mean absolute error exceeds the preset threshold of 3%. In this case, the prediction algorithm model in the initial system model corresponding to the old execution control needs to be modified, such as adjusting the hyperparameters in the observation noise covariance matrix. The updated system model needs to be verified in the simulation environment first to ensure that the prediction algorithm can run normally in the simulation environment and achieve the expected effect. Then generate code from the model, compile it into an execution control and deploy it to the control chip for test environment verification. If the verification fails and it is a specified type of defect problem, it can be traced back to the updated system model, and the test environment verification is performed again after modification. Repeat the above process until it passes the verification in the test environment. After verification, the execution control can be updated to obtain a new execution control.

[0126] In the above embodiment, if the accuracy of the prediction result of the prediction algorithm model exceeds the allowable accuracy range, the initial system model is traced back; the parameters of the prediction algorithm model in the initial system model are updated to obtain an updated system model. The efficiency of problem solving is significantly improved through the tracing process centered on the initial system model.

[0127] In some embodiments, please refer to Figure 8a If the battery management system has a demand change, trace it back to the initial system model, and update the parameters of the initial system model to obtain the updated system model, including:

[0128] S810: If there is a need to develop a new type of battery pack for the battery management system, determine an initial system model in the existing system models.

[0129] S820: Perform model-in-the-loop simulation on the battery simulation model, and update parameters of the battery simulation model based on the model-in-the-loop simulation to obtain an updated battery simulation model.

[0130] S830, using the updated battery simulation model to perform charge and discharge simulation on the prediction algorithm model, and updating parameters of the prediction algorithm model based on the charge and discharge simulation results to obtain an updated prediction algorithm model.

[0131] The initial system model includes a battery simulation model corresponding to the battery hardware part and a prediction algorithm model corresponding to the software part. The updated system model includes an updated battery simulation model and an updated prediction algorithm model. The existing system model is a system model corresponding to the existing battery pack.

[0132] Specifically, see Figure 8bIf there is a need to develop a new type of battery pack for the battery management system, one can select one from multiple different system models of existing battery packs as the initial system model. For example, a system model with the same modeling method as the simulation model of the battery hardware part and a prediction algorithm model that also uses the same prediction algorithm can be selected.

[0133] Furthermore, the battery simulation model is simulated in the loop. First, the new type of battery pack is charged and discharged, and several groups of experimental data are recorded, including the current value, charge and discharge time, voltage change, and temperature change of the battery simulation model. Then, the model is simulated in Matlab. By repeating the above charge and discharge experimental process for the battery simulation model, the voltage change and temperature change of the simulation output are compared with the error of the corresponding real battery pack experimental data, and the parameters of the model are continuously adjusted until the output of the model reaches the expected standard, and a set of optimal battery characteristic parameters are obtained, such as capacitance, internal resistance, energy efficiency, heat generation efficiency, etc. The battery simulation model is adjusted by these parameters to obtain an updated battery simulation model.

[0134] Furthermore, the updated battery simulation model is used to perform charge and discharge simulation on the prediction algorithm model, and the prediction algorithm model may include prediction algorithm sub-models corresponding to SOC, SOE, SOH, SOP, etc. The parameters of each prediction algorithm sub-model can be updated in turn based on the charge and discharge simulation results. After the update is completed, the updated prediction algorithm model is obtained.

[0135] Furthermore, PIL and HIL simulation verification is required to ensure that the prediction algorithm can properly match the control chip, new battery pack hardware, and voltage sensors, current sensors, and temperature sensors. After the simulation verification is passed, the prediction algorithm model is converted into code, compiled into an execution control and embedded in the control chip, and verified in the test environment. If the verification fails and it is a defect of a specified type, it can be traced back to the updated system model, and the test environment verification is performed again after modification. The above process is repeated until the verification in the test environment is passed. After verification, the execution control can be updated and applied to the new type of battery pack.

[0136] In the above embodiment, firstly, the initial system model is determined in the existing system model in view of the development requirements of the new type of battery pack in the battery management system; then, the battery simulation model is simulated in the model-in-the-loop, and the parameters of the battery simulation model are updated based on the model-in-the-loop simulation to obtain an updated battery simulation model; finally, the updated battery simulation model is used to simulate the charge and discharge of the prediction algorithm model, and the parameters of the prediction algorithm model are updated based on the charge and discharge simulation results to obtain an updated prediction algorithm model. The development method centered on the initial system model can effectively shorten the development cycle and improve the development efficiency.

[0137] See also Fig. 9 In an embodiment of the present application, a development device 900 for a battery management system is further provided. The battery management system corresponds to a pre-built initial system model, which is a simulation model built for the battery hardware part and software part corresponding to the battery management system. The development device 900 for the battery management system includes:

[0138] The traceability update module 910 is used to trace the source to the initial system model if there is a demand change or a specified type of defect problem in the battery management system, and update the parameters of the initial system model to obtain an updated system model;

[0139] The control deployment module 920 is used to deploy the execution control corresponding to the prediction algorithm model of the software part of the updated system model in the control chip of the battery management system if the updated system model passes the verification of the test environment.

[0140] In some embodiments, the initial system model includes a battery simulation model corresponding to the battery hardware part and a prediction algorithm model corresponding to the software part; the parameters of the initial system model are updated to obtain an updated system model, and the traceability update module 910 is also used to update the parameters of the battery simulation model and / or the prediction algorithm model in the initial system model to obtain an updated system model.

[0141] In some embodiments, the battery management system development device 900 further includes:

[0142] An initial battery model building module is used to obtain actual charge and discharge data of an actual battery pack and build an initial battery model;

[0143] A model-in-the-loop simulation module is used to perform model-in-the-loop simulation on the initial battery model using actual charge and discharge data of an actual battery pack to obtain model-in-the-loop simulation results;

[0144] The parameter adjustment module is used to adjust the parameters of the initial battery model according to the model-in-the-loop simulation results to obtain the battery simulation model in the initial system model.

[0145] In some embodiments, the battery management system development device 900 further includes:

[0146] An initial algorithm model building module, used to build an initial algorithm model;

[0147] A charge and discharge simulation module, used to perform charge and discharge simulation using a battery simulation model to obtain first simulation voltage data, first simulation current data, first simulation temperature data and first simulation management parameters;

[0148] A parameter prediction module, used for inputting the first simulation voltage data, the first simulation current data and the first simulation temperature data into the initial algorithm model for prediction to obtain a first battery management parameter;

[0149] The parameter adjustment module is used to adjust the parameters of the initial algorithm model according to the first simulation management parameter and the first battery management parameter to obtain the prediction algorithm model corresponding to the software part.

[0150] In some embodiments, the battery management system development device 900 further includes:

[0151] An actual battery parameter determination module is used to determine the actual battery management parameters of the actual battery pack during the actual charging and discharging process; wherein the actual battery pack is configured with a voltage sensor, a current sensor and a temperature sensor;

[0152] A data acquisition module, used to acquire voltage data collected by a voltage sensor, current data collected by a current sensor, and temperature data collected by a temperature sensor;

[0153] A parameter prediction module, used for inputting voltage data, current data and temperature data into a prediction algorithm model for prediction to obtain a second battery management parameter;

[0154] The parameter updating module is used to update the parameters of the prediction algorithm model according to the actual battery management parameters and the second battery management parameters.

[0155] In some embodiments, the battery management system development device 900 further includes:

[0156] A simulation module, used to perform charge and discharge simulation using a battery simulation model to obtain second simulation voltage data, second simulation current data, second simulation temperature data, and second simulation management parameters; wherein the second simulation voltage data, second simulation current data, and second simulation temperature data are used to predict the second battery management parameters;

[0157] The parameter updating module is used to update the parameters of the prediction algorithm model according to the second simulation management parameter and the second battery management parameter.

[0158] In some embodiments, the battery management system development device 900 further includes:

[0159] The parameter continuous updating module is used to continue updating the parameters of the updated system model if the updated system model fails to pass the verification of the test environment until it passes the verification of the test environment.

[0160] In some embodiments, the traceability update module 910 is also used to trace back to the initial system model if the accuracy of the prediction result of the prediction algorithm model exceeds the allowable accuracy range; wherein the initial system model includes the prediction algorithm model corresponding to the software part; the parameters of the prediction algorithm model in the initial system model are updated to obtain an updated system model.

[0161] In some embodiments, the traceability update module 910 is also used to determine the initial system model in the existing system model if there is a need to develop a new type of battery pack for the battery management system; wherein the initial system model includes a battery simulation model corresponding to the battery hardware part and a prediction algorithm model corresponding to the software part; perform model-in-the-loop simulation on the battery simulation model, and update the parameters of the battery simulation model based on the model-in-the-loop simulation to obtain an updated battery simulation model; perform charge and discharge simulation on the prediction algorithm model using the updated battery simulation model, and update the parameters of the prediction algorithm model based on the charge and discharge simulation results to obtain an updated prediction algorithm model; wherein the updated system model includes an updated battery simulation model and an updated prediction algorithm model.

[0162] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0163] The development device of the battery management system in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0164] See also Fig.10 , Fig.10 is a schematic diagram of the structure of a computer device provided in an embodiment of the present application, such as Fig.10 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Fig.10A processor 10 is taken as an example.

[0165] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0166] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0167] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0168] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0169] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Fig.10 The example of connecting through bus is taken in the following.

[0170] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0171] The embodiment of the present application also provides a computer-readable storage medium. The above method according to the embodiment of the present application can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0172] The embodiment of the present application provides a computer program product, which includes computer instructions, which are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method of any embodiment of the present application.

[0173] Although the embodiments of the present application are described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations are all within the scope defined by the appended claims.

[0174] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0175] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0176] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0177] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0178] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0179] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0180] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity 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, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0181] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0182] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

[0183] Although the embodiments of the present application have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for developing a battery management system, characterized in that: The battery management system corresponds to a pre-built initial system model, and the initial system model is a simulation model built for the battery hardware part and software part corresponding to the battery management system; the method includes: If there is a demand change or a specified type of defect problem for the battery management system, trace it back to the initial system model, and update the parameters of the initial system model to obtain an updated system model; If the updated system model passes the verification of the test environment, the execution control corresponding to the simulation model corresponding to the software part in the updated system model is deployed in the control chip of the battery management system.

2. The method according to claim 1, characterized in that The initial system model includes a battery simulation model corresponding to the battery hardware part and a prediction algorithm model corresponding to the software part; the updating of parameters of the initial system model to obtain an updated system model includes: Parameters of the battery simulation model and / or the prediction algorithm model in the initial system model are updated to obtain the updated system model.

3. The method according to claim 2, characterized in that The battery simulation model in the initial system model is constructed in the following way: Obtain actual charge and discharge data of the actual battery pack and build an initial battery model; Performing model-in-the-loop simulation on the initial battery model using actual charge and discharge data of the actual battery pack to obtain a model-in-the-loop simulation result; The parameters of the initial battery model are adjusted according to the model-in-the-loop simulation result to obtain a battery simulation model in the initial system model.

4. The method according to claim 2, characterized in that: The prediction algorithm model in the initial system model is constructed in the following way: Build the initial algorithm model; Using the battery simulation model to perform charge and discharge simulation, obtaining first simulation voltage data, first simulation current data, first simulation temperature data and first simulation management parameters; Inputting the first simulation voltage data, the first simulation current data and the first simulation temperature data into the initial algorithm model for prediction to obtain a first battery management parameter; The initial algorithm model is adjusted in parameters according to the first simulation management parameter and the first battery management parameter to obtain a prediction algorithm model corresponding to the software part.

5. The method according to claim 2, characterized in that: After obtaining the updated system model, the method further includes: Determine actual battery management parameters of an actual battery pack during an actual charging and discharging process; wherein the actual battery pack is configured with a voltage sensor, a current sensor, and a temperature sensor; Acquire voltage data collected by the voltage sensor, current data collected by the current sensor, and temperature data collected by the temperature sensor; Inputting the voltage data, the current data and the temperature data into the prediction algorithm model for prediction to obtain a second battery management parameter; The prediction algorithm model is updated according to the actual battery management parameter and the second battery management parameter.

6. The method according to claim 2, characterized in that After obtaining the updated system model, the method further includes: Using the battery simulation model to perform charge and discharge simulation, obtain second simulation voltage data, second simulation current data, second simulation temperature data and second simulation management parameters; wherein the second simulation voltage data, the second simulation current data and the second simulation temperature data are used to predict the second battery management parameters; The prediction algorithm model is updated according to the second simulation management parameter and the second battery management parameter.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: If the updated system model fails to pass the verification of the test environment, continue to update parameters of the updated system model until it passes the verification of the test environment.

8. The method according to claim 1, characterized in that If a defect of a specified type occurs in the battery management system, the defect is traced back to the initial system model, and the parameters of the initial system model are updated to obtain an updated system model, including: If the accuracy of the prediction result of the prediction algorithm model exceeds the allowable accuracy range, trace back to the initial system model; wherein the initial system model includes the prediction algorithm model corresponding to the software part; The prediction algorithm model in the initial system model is parameter updated to obtain the updated system model.

9. The method according to claim 1, characterized in that: If the battery management system has a demand change, it is traced back to the initial system model, and the parameters of the initial system model are updated to obtain an updated system model, including: If there is a need to develop a new type of battery pack for the battery management system, the initial system model is determined in the existing system model; wherein the initial system model includes a battery simulation model corresponding to the battery hardware part and a prediction algorithm model corresponding to the software part; Performing a model-in-the-loop simulation on the battery simulation model, and updating parameters of the battery simulation model based on the model-in-the-loop simulation to obtain an updated battery simulation model; The updated battery simulation model is used to perform charge and discharge simulation on the prediction algorithm model, and the parameters of the prediction algorithm model are updated based on the charge and discharge simulation results to obtain an updated prediction algorithm model; wherein the updated system model includes the updated battery simulation model and the updated prediction algorithm model.

10. A battery management system development device, characterized in that: The battery management system corresponds to a pre-built initial system model, which is a simulation model built for the battery hardware part and software part corresponding to the battery management system; the device includes: A traceability update module, used for tracing back to the initial system model if there is a demand change or a specified type of defect problem for the battery management system, and updating the parameters of the initial system model to obtain an updated system model; A control deployment module is used to deploy the execution control corresponding to the prediction algorithm model of the software part in the updated system model in the control chip of the battery management system if the updated system model passes the verification of the test environment.

11. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 9 by executing the computer instructions.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 9.

Images