Battery management algorithm updating method and device, cloud server and related product

Abstract

The application relates to a battery management algorithm updating method and device, a cloud server and related products. The method comprises the following steps: a cloud server acquires a battery scene management algorithm model, and sends the battery scene management algorithm model to a vehicle; a reference battery management algorithm model of the vehicle is generated according to battery management algorithm running data, battery attribute data, vehicle working condition information and the battery scene management algorithm model; a target algorithm module that needs to be updated is determined according to the reference battery management algorithm model and a current battery management algorithm model, so as to update the target algorithm module according to the reference battery management algorithm model; the battery scene management algorithm model represents a battery management algorithm model of the same type as the battery model of the vehicle; the battery management algorithm running data is data obtained by running the current battery management algorithm model of the vehicle; and the algorithm modules under different management types in the battery management algorithm model of the vehicle adopt a plug-in type design.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of battery management, in particular to a battery management algorithm updating method and device, a cloud server and related products. BACKGROUND

[0002] A battery management system (BMS) is an important electronic system in a new energy vehicle or an energy storage system, and can implement various management of a battery in the new energy vehicle or the energy storage system based on an algorithm package.

[0003] The algorithm package in the BMS can be regarded as a battery management algorithm model, and the algorithm model corresponds to various algorithms including state of charge (SOC) estimation, state of health (SOH) estimation, battery balancing, and battery thermal management of the battery.

[0004] In related technologies, when the algorithm package in the BMS is updated, the algorithm package in the BMS cannot be updated as needed, which affects the practicability and reliability of the BMS. SUMMARY

[0005] Therefore, it is necessary to provide a battery management algorithm updating method, device, cloud server and related products to solve the above technical problems.

[0006] In a first aspect, an embodiment of the present application provides a battery management algorithm updating method applied to a cloud server, and the method comprises the following steps:

[0007] obtaining a battery scene management algorithm model and sending the battery scene management algorithm model to a vehicle; the battery scene management algorithm model represents a battery management algorithm model of the same type under the same battery model as that of the vehicle; battery management algorithm running data is data obtained by running a current battery management algorithm model of the vehicle; and algorithm modules under different management types in the battery management algorithm model of the vehicle adopt a plug-in design;

[0008] generating a reference battery management algorithm model of the vehicle according to the battery management algorithm running data of the vehicle, battery attribute data, vehicle working condition information, and the battery scene management algorithm model;

[0009] determining a target algorithm module to be updated according to the reference battery management algorithm model and the current battery management algorithm model;

[0010] updating the target algorithm module according to the reference battery management algorithm model.

[0011] In the embodiments of the present application, the algorithm modules in the battery management algorithm model under different management types are designed in a plug-in manner to reduce the strong correlation between the algorithms in the battery management algorithm model, decouple the algorithms, form independent algorithm modules, determine the target algorithm module that needs to be updated based on the reference battery management algorithm model and the current battery management algorithm model, thereby realizing targeted updating of the target algorithm module without updating the entire model, improving the flexibility of algorithm updating, realizing on-demand updating of part of the algorithm in the algorithm model, and accordingly improving the practicality and reliability of the BMS in battery management based on the updated algorithm model. Moreover, the battery management algorithm running data of the vehicle, the battery attribute data, and the vehicle working condition information constitute personalized data for the vehicle, the battery scenario management algorithm model for the same battery model is optimized based on the personalized data of the vehicle, the adaptability between the obtained reference battery management algorithm model and the vehicle is improved, and accordingly the personalization of algorithm updating is improved.

[0012] In one of the embodiments, obtaining the battery scenario management algorithm model comprises:

[0013] Obtaining battery management algorithm running data of a plurality of reference batteries and battery attribute data of each reference battery; the plurality of reference batteries represent batteries of the same battery model as the battery model in the vehicle;

[0014] Training the battery general management algorithm model based on the battery management algorithm running data of the plurality of reference batteries and the battery attribute data of each reference battery to obtain the battery scenario management algorithm model.

[0015] In the embodiments of the present application, the battery general management algorithm model is trained based on the battery management algorithm running data and the battery attribute data of the plurality of reference batteries of the same battery model as the battery model in the vehicle to realize distillation of the battery general management algorithm model, obtain the battery scenario management algorithm model matched with the battery model of the vehicle, and help improve the accuracy of the reference battery management algorithm model for the vehicle based on the battery scenario management algorithm model.

[0016] In one of the embodiments, determining the target algorithm module that needs to be updated based on the reference battery management algorithm model and the current battery management algorithm model comprises:

[0017] Simulating running of each algorithm module in the reference battery management algorithm model in the algorithm simulator to obtain reference performance evaluation results of the algorithm modules;

[0018] Simulating running of each algorithm module in the current battery management algorithm model in the algorithm simulator to obtain current performance evaluation results of the algorithm modules;

[0019] The target algorithm module is determined according to the reference performance evaluation result and the current performance evaluation result of each algorithm module.

[0020] In the embodiments of the present application, the algorithm modules in the reference battery management algorithm model and the current battery management algorithm model are respectively simulated to run on the cloud server, and the reference performance evaluation result and the current performance evaluation result of the corresponding algorithm modules are respectively obtained, so as to compare the performance evaluation results, determine the target algorithm module to be updated, and improve the accuracy of the determined target algorithm module from the performance point of view. Moreover, the simulation of the corresponding algorithm modules on the cloud server realizes the preposition of the algorithm running result, reduces the invalid update, and accordingly improves the algorithm update efficiency.

[0021] In one of the embodiments, the target algorithm module is determined according to the reference performance evaluation result and the current performance evaluation result of each algorithm module, including:

[0022] The reference performance evaluation result and the current performance evaluation result of each algorithm module are compared.

[0023] In the case that the reference performance evaluation result is better than the current performance evaluation result, the algorithm module is taken as the target algorithm module.

[0024] In one of the embodiments, before the target algorithm module is updated according to the reference battery management algorithm model, the above method further includes:

[0025] An algorithm update request is sent to a terminal device where the battery manager application program is located, and the algorithm update request is used to instruct the terminal device to push a reminding message in the battery manager application program to update the current battery management algorithm model.

[0026] In response to the algorithm update instruction sent by the terminal device, the step of updating the target algorithm module according to the reference battery management algorithm model is performed, and the algorithm update instruction is triggered by the user in the battery manager application program based on the reminding message.

[0027] In the embodiments of the present application, the reminding message pushed in the battery manager App is used to remind the user to trigger the algorithm update instruction in the battery manager App, so that the user can perform the algorithm update according to his own will, thereby improving the user experience and the transparency of the algorithm update, and the interaction between the algorithm update and the user is improved by triggering the algorithm update through the user operation of the battery manager App.

[0028] In one of the embodiments, the target algorithm module is updated according to the reference battery management algorithm model, including:

[0029] sending a target algorithm module in a reference battery management algorithm model to a vehicle; the vehicle is configured to update the target algorithm module in a current battery management algorithm model according to the received target algorithm module.

[0030] In one of the embodiments, before sending the target algorithm module in the reference battery management algorithm model to the vehicle, the method further comprises:

[0031] performing a communication handshake and security authentication with the vehicle;

[0032] in a case where the communication handshake and security authentication are successfully completed, performing the step of sending the target algorithm module in the reference battery management algorithm model to the vehicle.

[0033] In the embodiments of the present application, the communication handshake and security authentication between the cloud server and the vehicle are performed before the target algorithm module is sent to the vehicle, which can effectively block malicious attacks and data leakage, and improve the security of data transmission.

[0034] In a second aspect, the embodiments of the present application further provide a battery management algorithm updating method applied to a vehicle, and the method comprises:

[0035] sending battery management algorithm running data, battery attribute data, and vehicle working condition information of the vehicle to a cloud server; the battery management algorithm running data is data obtained by running a current battery management algorithm model of the vehicle; algorithm modules in the battery management algorithm model of the vehicle under different management types are designed in a plug-in manner;

[0036] updating a target algorithm module in the current battery management algorithm model; the target algorithm module is determined by the cloud server according to a reference battery management algorithm model of the vehicle and the current battery management algorithm model; the cloud server generates the reference battery management algorithm model of the vehicle by obtaining a battery scenario management algorithm model and sending the battery scenario management algorithm model to the vehicle, and according to the battery management algorithm running data, the battery attribute data, and the vehicle working condition information of the vehicle; the battery scenario management algorithm model represents a battery management algorithm model under the same type as the battery model of the vehicle.

[0037] In the embodiments of the present application, the algorithm modules in the battery management algorithm model under different management types are designed in a plug-in manner, the targeted update of the target algorithm module is realized without updating the entire model, the flexibility of algorithm updating is improved, the on-demand update of part of the algorithm in the algorithm model is realized, and based on the dynamic change of the personalized data sent by the vehicle to the cloud service, the dynamic and continuous update of the algorithm model can be realized accordingly to adapt to the vehicle working condition change (such as the change from high cold to high temperature) and the individual difference of the battery (such as the aging state of the battery), and the real-time performance and robustness of the algorithm model are enhanced.

[0038] In one of the embodiments, the updating of the target algorithm module in the current battery management algorithm model comprises:

[0039] receiving the program package of the target algorithm module sent by the cloud server;

[0040] storing the program package of the target algorithm module to the battery management algorithm storage area of the vehicle, and setting the program package of the original target algorithm module in the current battery management algorithm model as a backup program package, thereby completing the updating of the target algorithm module in the current battery management algorithm model of the vehicle.

[0041] In the embodiments of the present application, the program package of the original target algorithm module in the current battery management algorithm model is set as a backup program package, and the program package of the original target algorithm module and the received program package of the target algorithm module are stored at the same time, so that in the case of running failure of the received program package of the target algorithm module, the program package of the original target algorithm module is rolled back to run, thereby improving the reliability and stability of the BMS running.

[0042] In one of the embodiments, the above method further comprises:

[0043] detecting the running state of the target algorithm module in the current battery management algorithm model of the vehicle after the updating;

[0044] in the case that the running state of the target algorithm module meets the preset state condition, deleting the backup program package.

[0045] In the embodiments of the present application, in the case that the running state of the target algorithm module meets the preset state condition, the old backup program package is deleted, the storage space occupied by the backup program package is released at the same time the stability of the BMS running is improved, the vehicle-end storage resources are saved, and the resource utilization rate is improved.

[0046] In a third aspect, the embodiments of the present application further provide a battery management algorithm updating device applied to a cloud server, which comprises:

[0047] a first model module, configured to acquire a battery scene management algorithm model and send the battery scene management algorithm model to a vehicle; the battery scene management algorithm model represents a battery management algorithm model under the same model as the battery model of the vehicle; the battery management algorithm running data is data obtained by running the current battery management algorithm model of the vehicle; the algorithm modules under different management types in the battery management algorithm model of the vehicle adopt a plug-in type design;

[0048] a second model module, configured to generate a reference battery management algorithm model of the vehicle according to the battery management algorithm running data of the vehicle, battery attribute data, vehicle working condition information, and the battery scene management algorithm model;

[0049] A target determination module is configured to determine a target algorithm module that needs to be updated according to the reference battery management algorithm model and the current battery management algorithm model.

[0050] An algorithm updating module is configured to update the target algorithm module according to the reference battery management algorithm model.

[0051] In a fourth aspect, an embodiment of the present application further provides a cloud server, which comprises a memory and a processor, the memory stores a computer program, and the processor implements the steps of any of the battery management algorithm updating methods when executing the computer program.

[0052] In a fifth aspect, an embodiment of the present application further provides a vehicle, which comprises a memory and a processor, the memory stores a computer program, and the processor implements the steps of any of the battery management algorithm updating methods when executing the computer program.

[0053] In a sixth aspect, an embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the computer program implements the steps of any of the battery management algorithm updating methods when executed by a processor.

[0054] In a seventh aspect, an embodiment of the present application further provides a computer program product, which comprises a computer program, and the computer program implements the steps of any of the battery management algorithm updating methods when executed by a processor.

[0055] The above description is only a summary of the technical solutions of the present application, in order to make the technical means of the present application more clearly understood, and to be implemented according to the content of the description, and in order to make the above and other purposes, characteristics and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described. BRIEF DESCRIPTION OF DRAWINGS

[0056] Figure 1 An application environment diagram of the battery management algorithm updating method in an embodiment;

[0057] Figure 2 A flowchart of the battery management algorithm updating method in an embodiment;

[0058] Figure 3 A flowchart of obtaining the battery scene management algorithm model in an embodiment;

[0059] Figure 4 A flowchart of determining the target algorithm module in an embodiment;

[0060] Figure 5 A flowchart of determining the target algorithm module in another embodiment;

[0061] Figure 6Flowchart of the battery management algorithm updating method in another embodiment;

[0062] Figure 7 Flowchart of the battery management algorithm updating method in another embodiment;

[0063] Figure 8 Flowchart of the battery management algorithm updating method in another embodiment;

[0064] Figure 9 Flowchart of the target algorithm module updating in an embodiment;

[0065] Figure 10 Flowchart of the battery management algorithm updating method in another embodiment;

[0066] Figure 11 Flowchart of the battery management algorithm updating method in another embodiment;

[0067] Figure 12 Block diagram of the battery management algorithm updating device in an embodiment;

[0068] Figure 13 Block diagram of the battery management algorithm updating device in another embodiment. DETAILED DESCRIPTION

[0069] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application is further described in detail below with reference to 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 intended to limit the present application.

[0070] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application; the description and the drawings of the specification and the above-mentioned drawings are intended to cover not only the technical features of the present application, but also all technical equivalents thereof.

[0071] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase "in an embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily all directed to the same embodiment, or to a single alternative embodiment. It is explicitly contemplated that embodiments described herein can be combined with each other.

[0072] In the description of the embodiments of the present application, the term "and / or" is only to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone. In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two), unless otherwise explicitly specified.

[0073] The battery management system (BMS) is an important electronic system in a new energy vehicle or an energy storage system, and can implement various management of the battery in the new energy vehicle or the energy storage system based on an algorithm package.

[0074] The algorithm package in the BMS can be regarded as a battery management algorithm model, and the algorithm model corresponds to various algorithms including state of charge (SOC) estimation, state of health (SOH) estimation, battery balancing, and battery thermal management of the battery.

[0075] In the related art, when updating the algorithm package in the BMS, the algorithm package is usually updated by over-the-air (OTA) or local update through a controller area network (CAN) bus. However, whether it is OTA or CAN bus update, both essentially replace and update the entire algorithm package in the BMS. This results in large resource consumption, long update time, and even update failure during the algorithm update process. Moreover, it cannot meet the individual needs of different carrier devices (such as vehicles or energy storage systems), lacks the ability to update on demand, and the degree of refinement of algorithm model updating is low.

[0076] In addition, both OTA and CAN bus updates are static updates, and after updating, the algorithm model is not dynamically adjusted according to the working conditions or actual operation of the carrier device without human intervention, which reduces the adaptability between the algorithm model and the carrier device, and accordingly reduces the individualization and dynamic degree of algorithm model updating.

[0077] Therefore, the related art has the problem that the update of the battery management algorithm is not flexible enough, and the algorithm package in the BMS cannot be updated on demand, thereby affecting the practicality and reliability of the BMS.

[0078] The battery management algorithm updating method provided in the embodiments of the present application can be applied to, for example Figure 1The application environment shown. Among them, the cloud 102, the vehicle end 104 and the user end 106 communicate with each other through the network, forming an end-cloud collaborative system for updating the battery management algorithm of the vehicle end 104.

[0079] The vehicle end 104 is a vehicle, including a BMS and a battery, the BMS is used to obtain battery management algorithm running data obtained by the current battery management algorithm model of the vehicle running, and collect battery attribute data, the vehicle end 104 is also used to obtain vehicle working condition information of the vehicle, and send the battery management algorithm running data, battery attribute data, vehicle working condition information of the vehicle to the cloud 102.

[0080] The cloud 102 is a cloud server, used to receive the battery management algorithm running data, battery attribute data and vehicle working condition information of the vehicle sent by the vehicle end 104, and train a reference battery management algorithm model of the vehicle based on these data. The algorithm module under different management types in the battery management algorithm model of the vehicle adopts plug-in design. The cloud 102 can determine the target algorithm module to be updated according to the reference battery management algorithm model and the current battery management algorithm model, so as to update the target algorithm module according to the reference battery management algorithm model.

[0081] The user end 106 is a terminal device, installed with a battery manager application (Application, App). The cloud 102 can send an algorithm update request to the user end 106 before updating the target algorithm module, instructing the user end 106 to push a reminder message in the battery manager App to update the current battery management algorithm model of the vehicle end 104. The user can trigger an algorithm update instruction in the battery manager App based on the reminder message. The user end 106 sends the algorithm update instruction to the cloud 102, instructing the cloud 102 to send the target algorithm module in the reference battery management algorithm model to the vehicle end 104, and the vehicle end 104 updates the target algorithm module in the current battery management algorithm model according to the received target algorithm module.

[0082] The cloud 102 can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The user end 106 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers and the like.

[0083] Exemplarily, the communication between the cloud 102 and the vehicle end 104 can be realized through a remote database access (RDB) bus.

[0084] In one embodiment, the application provides a battery management algorithm updating method, which is applied to Figure 1 The cloud server in the above embodiment is taken as an example, asFigure 2 As shown, the method comprises the following steps:

[0085] S210, obtaining a battery scene management algorithm model, and sending the battery scene management algorithm model to the vehicle; the battery scene management algorithm model represents a battery management algorithm model under the same model as the battery model of the vehicle; the battery management algorithm running data is data obtained by running the current battery management algorithm model of the vehicle; the algorithm modules under different management types in the battery management algorithm model of the vehicle adopt plug-in design.

[0086] The battery scene management algorithm model corresponds to the battery model, and one battery model corresponds to one battery scene management algorithm model.

[0087] The battery management algorithm model is an algorithm package comprising multiple algorithms, and each algorithm corresponds to a management type. For example, the algorithms in the battery management algorithm model include SOC estimation, SOH estimation, battery balancing, battery thermal management, etc. The current battery management algorithm model is the battery management algorithm model currently stored by the vehicle. The algorithm modules under different management types in the battery management algorithm model of the vehicle adopt plug-in design, i.e., the algorithm modules are independent of each other, each algorithm module corresponds to an algorithm for realizing a management type, supports asynchronous updating, allows updating of specified algorithm modules in the algorithm model individually, and can effectively reduce resource waste and potential conflicts caused by overall updating.

[0088] Optionally, the cloud server can receive the battery management algorithm running data, the battery attribute data, and the vehicle working condition information of the vehicle sent by the vehicle, the battery attribute data reported by the vehicle includes the battery model, the cloud server can determine the battery scene management algorithm model corresponding to the battery model in the pre-stored multiple battery scene management algorithm models according to the battery model, and send the battery scene management algorithm model to the vehicle. The vehicle correspondingly receives the battery scene management algorithm model, and runs the battery scene management algorithm model as the current battery scene model.

[0089] S220, generating a reference battery management algorithm model of the vehicle according to the battery management algorithm running data, the battery attribute data, the vehicle working condition information, and the battery scene management algorithm model of the vehicle.

[0090] In the case where the vehicle runs the received battery scene management algorithm model as the current battery scene model, the battery management algorithm running data of the vehicle is data obtained by running the battery scene management algorithm model of the vehicle.

[0091] It should be noted that, since the battery management algorithm model includes algorithm models under different management types, i.e., includes multiple algorithms, running the battery management algorithm model can correspondingly obtain running data corresponding to each algorithm. Exemplarily, taking the SOC estimation module and the SOH estimation module included in the battery management algorithm model as examples, the obtained battery management algorithm running data includes the SOC estimation value and the SOH estimation value of the battery.

[0092] The battery attribute data can include at least one of battery usage data, battery mechanism data, and battery manufacturing quality data.

[0093] The battery usage data refers to various data generated in the process of using the battery, which can reflect the performance, state, and usage of the battery. Exemplarily, the battery usage data includes the charge / discharge parameters of the battery, such as the charge / discharge voltage, the charge / discharge current, the charge / discharge time, etc., can also include the power and capacity data of the battery, such as the remaining power and storage capacity of the battery, etc., and can also include the health state data of the battery, such as the battery content, the self-discharge rate, etc.

[0094] The battery mechanism data refers to data that can reflect the internal working principle, chemical reaction process, and related physical properties of the battery. Exemplarily, the battery mechanism data includes electrode material data, such as the type, composition, crystal structure, and particle size distribution of the electrode material, can also include reaction kinetics data, such as the chemical reaction rate, charge transfer coefficient, and diffusion coefficient inside the battery, can also include interface property data, such as the properties of the electrode / electrolyte interface, interface resistance, and interface capacitance, and can also include thermal property data, such as the heat generation rate, thermal conductivity, and specific heat capacity of the battery during the charge / discharge process.

[0095] The battery manufacturing quality data is a series of data used to measure the quality of the battery, evaluate whether the battery meets relevant standards and requirements, etc. Exemplarily, the battery manufacturing quality data includes appearance and size data, such as appearance defects and size accuracy, can also include raw material quality data, such as the purity and impurity content of raw materials, and the performance indicators of raw materials, and can also include manufacturing process data, such as production process parameters, etc.

[0096] The vehicle working condition information is used to represent the environment in which the vehicle is located. Exemplarily, the vehicle working condition information can include the location of the vehicle, such as the coordinate position, and the environmental temperature of the location.

[0097] In the case where the vehicle receives the battery scenario management algorithm model as the current battery scenario model, the battery management algorithm running data of the vehicle is the data obtained by running the battery scenario management algorithm model of the vehicle.

[0098] Optionally, after obtaining the battery scenario management algorithm model, the cloud server can further optimize and train the battery scenario management algorithm model by using the battery management algorithm running data, battery attribute data, and vehicle working condition information reported by the vehicle as training samples, to obtain a specific model for the vehicle, i.e., the reference battery management algorithm model.

[0099] S230, determining a target algorithm module that needs to be updated according to the reference battery management algorithm model and the current battery management algorithm model.

[0100] Optionally, the cloud server can also receive the current battery management algorithm model reported by the vehicle, to compare the performance of each algorithm module in the reference battery management algorithm model and the current battery management algorithm model, and determine the algorithm module that needs to be updated as the target algorithm module according to the performance comparison result.

[0101] Optionally, the cloud server can also receive the current battery management algorithm model reported by the vehicle, to compare the performance of each algorithm module in the reference battery management algorithm model and the current battery management algorithm model, and determine the algorithm module that needs to be updated as the target algorithm module according to the performance comparison result.

[0102] Optionally, the cloud server can also receive the current battery management algorithm model reported by the vehicle, to compare the performance of each algorithm module in the reference battery management algorithm model and the current battery management algorithm model, and determine the algorithm module that needs to be updated as the target algorithm module according to the performance comparison result.

[0103] S240, updating the target algorithm module according to the reference battery management algorithm model.

[0104] Optionally, after obtaining the target algorithm module that needs to be updated, the cloud server can send the target algorithm module in the reference battery management algorithm model to the vehicle, so that the vehicle updates the target algorithm module in the current battery management algorithm model according to the received target algorithm module.

[0105] In the embodiments of the present application, the cloud server obtains a battery scene management algorithm model, and sends the battery scene management algorithm model to the vehicle. According to the battery management algorithm running data, the battery attribute data, the vehicle working condition information of the vehicle, and the battery scene management algorithm model, a reference battery management algorithm model of the vehicle is generated. According to the reference battery management algorithm model and the current battery management algorithm model, a target algorithm module to be updated is determined, so as to update the target algorithm module according to the reference battery management algorithm model. The battery scene management algorithm model represents a battery management algorithm model of the same type under the same battery model as that of the vehicle. The battery management algorithm running data is data obtained by running the current battery management algorithm model of the vehicle. The algorithm modules under different management types in the battery management algorithm model are designed in a plug-in manner. In the above method, the algorithm modules under different management types in the battery management algorithm model are designed in a plug-in manner, which reduces the strong correlation between the algorithms in the battery management algorithm model, decouples the algorithms, forms independent algorithm modules, and determines the target algorithm module to be updated based on the reference battery management algorithm model and the current battery management algorithm model, thereby realizing targeted updating of the target algorithm module without updating the entire model, improving the flexibility of algorithm updating, realizing on-demand updating of part of the algorithm model, and accordingly improving the practicality and reliability of the BMS in battery management based on the updated algorithm model. In addition, the battery management algorithm running data, the battery attribute data, and the vehicle working condition information of the vehicle constitute personalized data for the vehicle. The battery scene management algorithm model of the same battery model is optimized based on the personalized data of the vehicle, which improves the adaptability between the obtained reference battery management algorithm model and the vehicle, and accordingly improves the personalization of algorithm updating.

[0106] To obtain the battery scene management algorithm model, in one of the embodiments, as shown in Figure 3 the above S210, the battery scene management algorithm model is obtained, including:

[0107] S310, obtaining battery management algorithm running data of a plurality of reference batteries and battery attribute data of each reference battery; the plurality of reference batteries represent batteries of the same type as the battery type of the vehicle.

[0108] In addition to the vehicle in the embodiment, the cloud server can also communicate with a plurality of other vehicles. Some of the plurality of other vehicles include batteries of the same type as the battery type of the vehicle, i.e., reference batteries.

[0109] Optionally, the cloud server can filter the battery management algorithm running data and the battery attribute data corresponding to the reference batteries according to the battery type from the battery management algorithm running data and the battery attribute data reported by the plurality of vehicles.

[0110] S320, training the battery general management algorithm model according to the battery management algorithm running data of the plurality of reference batteries and the battery attribute data of each reference battery, to obtain the battery scenario management algorithm model.

[0111] The battery general management algorithm model is a battery management algorithm model trained based on a large amount of battery attribute data. The large amount of battery attribute data includes battery attribute data of multiple battery models.

[0112] Optionally, after obtaining the battery management algorithm running data and the battery attribute data of each reference battery, the cloud server can train the battery general management algorithm model by taking the battery management algorithm running data and the battery attribute data of each reference battery as training samples, iteratively update the model parameters to reduce the loss function value, and obtain the battery scenario management algorithm model corresponding to the battery model of the vehicle after model optimization and verification.

[0113] In the embodiments of the present application, the battery management algorithm running data of the plurality of reference batteries and the battery attribute data of each reference battery are obtained, and the battery general management algorithm model is trained according to the battery management algorithm running data of the plurality of reference batteries and the battery attribute data of each reference battery, to obtain the battery scenario management algorithm model. The plurality of reference batteries represent batteries of the same model as the battery model in the vehicle. In the above method, the battery general management algorithm model is trained based on the battery management algorithm running data and the battery attribute data of the plurality of reference batteries of the same model as the battery model in the vehicle, to realize distillation of the battery general management algorithm model, and obtain the battery scenario management algorithm model matching the battery model of the vehicle, which helps to improve the accuracy of the reference battery management algorithm model for the vehicle based on the battery scenario management algorithm model.

[0114] In the case where it is determined that the target algorithm module needs to be updated, in one of the embodiments, as shown in Figure 4 S230, determining the target algorithm module that needs to be updated according to the reference battery management algorithm model and the current battery management algorithm model, includes:

[0115] S410, simulating the running of each algorithm module in the reference battery management algorithm model in the algorithm simulator to obtain the reference performance evaluation result of each algorithm module.

[0116] The algorithm simulator is a kind of software tool or system, which has an algorithm running environment built in, and can be used to simulate and analyze the behavior and performance of the algorithm.

[0117] Optionally, for each algorithm module in the reference battery management algorithm model, the cloud server can put the algorithm module into the algorithm running environment in the algorithm simulator to simulate running the algorithm processing process corresponding to the algorithm module in the algorithm running environment, obtain a processing result, and determine a performance evaluation result of the algorithm model based on the processing result, denoted as a reference performance evaluation result. The reference battery management algorithm model includes multiple algorithm models, and the reference performance evaluation result of each algorithm module can be obtained accordingly.

[0118] S420, simulate running each algorithm module in the current battery management algorithm model in the algorithm simulator to obtain a current performance evaluation result of each algorithm module.

[0119] Optionally, similar to the reference battery management algorithm model, for each algorithm module in the current battery management algorithm model, the cloud server can put the algorithm module into the algorithm running environment in the algorithm simulator to simulate running the algorithm processing process corresponding to the algorithm module in the algorithm running environment, obtain a processing result, and determine a performance evaluation result of the algorithm model based on the processing result, denoted as a current performance evaluation result. The current battery management algorithm model includes multiple algorithm models, and the current performance evaluation result of each algorithm module can be obtained accordingly.

[0120] S430, determine a target algorithm module according to the reference performance evaluation result and the current performance evaluation result of each algorithm module.

[0121] Optionally, after obtaining the reference performance evaluation result and the current performance evaluation result of each algorithm module, the cloud server can compare the reference performance evaluation result and the current performance evaluation result of each algorithm module to determine a target algorithm module that needs to be updated according to the comparison result.

[0122] In an optional embodiment, as shown in Figure 5 S430, determine a target algorithm module according to the reference performance evaluation result and the current performance evaluation result of each algorithm module, includes:

[0123] S510, compare the reference performance evaluation result and the current performance evaluation result for each algorithm module.

[0124] The reference battery management algorithm model and the current battery management algorithm model include the same algorithm modules. The reference performance evaluation result and the current performance evaluation result include performance evaluation parameters of the algorithm modules.

[0125] Optionally, for each algorithm module included in the reference battery management algorithm model and the current battery management algorithm model, the cloud server can compare the reference performance evaluation parameter and the current performance evaluation parameter corresponding to the algorithm module to determine the advantages and disadvantages of the reference performance evaluation result and the current performance evaluation result according to the comparison result.

[0126] In an optional embodiment, in the case that the performance evaluation result includes a single performance evaluation parameter of the algorithm module, the reference performance evaluation result and the current performance evaluation result can be determined by comparing the performance evaluation parameter in the reference performance evaluation result (i.e., the reference performance evaluation parameter) and the performance evaluation parameter in the current performance evaluation result (i.e., the current performance evaluation parameter). For example, in the case that the performance evaluation parameter includes the algorithm running time, if the reference algorithm running time of the algorithm module is less than the current algorithm running time, it is determined that the reference performance evaluation result of the algorithm module is better than the current performance evaluation result; in the case that the reference algorithm running time is equal to the current algorithm running time, it is determined that the reference performance evaluation result of the algorithm module is equivalent to the current performance evaluation result; in the case that the reference algorithm running time of the algorithm module is greater than the current algorithm running time, it is determined that the current performance evaluation result of the algorithm module is better than the reference performance evaluation result. Alternatively, in the case that the performance evaluation parameter includes the algorithm accuracy, if the reference algorithm accuracy of the algorithm module is greater than the current algorithm accuracy, it is determined that the reference performance evaluation result of the algorithm module is better than the current performance evaluation result; in the case that the reference algorithm accuracy is equal to the current algorithm accuracy, it is determined that the reference performance evaluation result of the algorithm module is equivalent to the current performance evaluation result; in the case that the reference algorithm accuracy of the algorithm module is less than the current algorithm accuracy, it is determined that the current performance evaluation result of the algorithm module is better than the reference performance evaluation result.

[0127] In another optional embodiment, in the case that the performance evaluation result includes multiple performance evaluation parameters of the algorithm module, the reference performance evaluation result and the current performance evaluation result can be determined by comparing the performance evaluation parameters between the reference performance evaluation result and the current performance evaluation result. For example, in the case that the reference performance evaluation result is determined to have more performance evaluation parameters that are better than the performance evaluation parameters in the current performance evaluation result based on the comparison results of the performance evaluation parameters, it is determined that the reference performance evaluation result of the algorithm module is better than the current performance evaluation result; in the case that the reference performance evaluation result is equivalent to the current performance evaluation result, it is determined that the reference performance evaluation result of the algorithm module is equivalent to the current performance evaluation result; in the case that the current performance evaluation result is determined to have more performance evaluation parameters that are better than the performance evaluation parameters in the reference performance evaluation result based on the comparison results of the performance evaluation parameters, it is determined that the current performance evaluation result of the algorithm module is better than the reference performance evaluation result. Alternatively, in the case that the reference performance evaluation result is determined to have all performance evaluation parameters that are better than the performance evaluation parameters in the current performance evaluation result based on the comparison results of the performance evaluation parameters, it is determined that the reference performance evaluation result of the algorithm module is better than the current performance evaluation result.

[0128] Exemplarily, in the case that the reference performance evaluation result of the algorithm module is better than the current performance evaluation result in the case that the performance evaluation parameter in the reference performance evaluation result is more superior than the performance evaluation parameter in the current performance evaluation result, the performance evaluation result includes three performance evaluation parameters A, B and C, and at least two of A and C in the reference performance evaluation result are superior to the current performance evaluation result, it is determined that the reference performance evaluation result of the algorithm module is better than the current performance evaluation result.

[0129] In another optional embodiment, in the case that the reference performance evaluation result includes multiple performance evaluation parameters, the scores of the performance evaluation parameters can also be quantitatively obtained, and the performance evaluation value of the corresponding algorithm module is determined through the score weighting manner, and then the reference performance evaluation result and the current performance evaluation result of the algorithm module are compared to determine the superiority and inferiority. For example, in the case that the reference performance evaluation value of the algorithm module is greater than the current performance evaluation value, it is determined that the reference performance evaluation result of the algorithm module is better than the current performance evaluation result; in the case of equality, it is determined that the reference performance evaluation result of the algorithm module is equivalent to the current performance evaluation result; in the case that the reference performance evaluation value of the algorithm module is less than the current performance evaluation value, it is determined that the current performance evaluation result of the algorithm module is better than the reference performance evaluation result.

[0130] S520, in the case that the reference performance evaluation result is better than the current performance evaluation result, the algorithm module is taken as the target algorithm module.

[0131] Optionally, after obtaining the performance comparison result of each algorithm module, for each algorithm module, the cloud server determines that the reference performance evaluation result of the algorithm module is better than the current performance evaluation result, and then the algorithm module is taken as the target algorithm module to be updated.

[0132] Exemplarily, continuing to take the case that the reference battery management algorithm model and the current battery management algorithm model both include the SOC estimation module and the SOH estimation module as an example, in the case that the reference performance evaluation result of the SOC estimation module is better than the current performance evaluation result, the SOC estimation module is taken as the target algorithm module; in the case that the reference performance evaluation result of the SOH estimation module is better than the current performance evaluation result, the SOH estimation module is taken as the target algorithm module; in the case that the reference performance evaluation result of the SOC estimation module is better than the current performance evaluation result and the reference performance evaluation result of the SOH estimation module is better than the current performance evaluation result, the SOC estimation module and the SOH estimation module are both taken as the target algorithm module.

[0133] In the embodiments of the present application, each algorithm module in the reference battery management algorithm model is simulated to run in the algorithm simulator to obtain reference performance evaluation results of each algorithm module, and each algorithm module in the current battery management algorithm model is simulated to run in the algorithm simulator to obtain current performance evaluation results of each algorithm module, so that the target algorithm module is determined according to the reference performance evaluation results and the current performance evaluation results of each algorithm module. In the above method, the algorithm modules in the reference battery management algorithm model and the current battery management algorithm model are simulated to run in the cloud server respectively, and the reference performance evaluation results and the current performance evaluation results of the corresponding algorithm modules are obtained respectively, so that the performance evaluation results are compared to determine the target algorithm module that needs to be updated. From the performance point of view, the accuracy of the determined target algorithm module is improved, and the algorithm running results are pre-processed by simulating the corresponding algorithm modules in the cloud server, which reduces invalid updates and improves the algorithm update efficiency accordingly.

[0134] In practical applications, the user can trigger the update of the target algorithm module by operating the battery manager App. Based on this, in one of the embodiments, as shown in Figure 6 Before the step S240 of updating the target algorithm module according to the reference battery management algorithm model, the method further includes:

[0135] S610, sending an algorithm update request to a terminal device where the battery manager application program is located; the algorithm update request is used to instruct the terminal device to push a reminder message in the battery manager application program to update the current battery management algorithm model.

[0136] The reminder message is used to remind the user to operate the battery manager App to send an algorithm update instruction to the cloud server to instruct the cloud server to update the target algorithm module.

[0137] Optionally, after the target algorithm module is determined, the cloud server can send an algorithm update request to the terminal device where the battery manager App is located to remind the user to perform the algorithm update operation in the battery manager App.

[0138] S620, in response to the algorithm update instruction sent by the terminal device, performing the step of updating the target algorithm module according to the reference battery management algorithm model; the algorithm update instruction is triggered by the user in the battery manager application program based on the reminder message.

[0139] It should be noted that after the reminder message indicating the algorithm update is pushed in the battery manager App, the user can operate the battery manager App on the terminal device to obtain user permission, so as to trigger the terminal device to send an algorithm update instruction to the cloud server. The user can also operate the battery manager App to ignore the reminder message, and the terminal device does not send an algorithm update instruction to the cloud server accordingly.

[0140] Optionally, in the case that the user operates the terminal device to trigger the terminal device to send the algorithm update instruction to the cloud server, the cloud server correspondingly receives the algorithm update instruction sent by the terminal device, and in response to the algorithm update instruction, executes the step S240 of updating the target algorithm module according to the reference battery management algorithm model.

[0141] In the embodiments of the present application, the algorithm update request is sent to the terminal device where the battery management application program is located, so as to respond to the algorithm update instruction sent by the terminal device and execute the step of updating the target algorithm module according to the reference battery management algorithm model; the algorithm update request is used to instruct the terminal device to push a reminder message for updating the current battery management algorithm model in the battery management application program; the algorithm update instruction is triggered by the user in the battery management application program based on the reminder message; in the above method, the reminder message pushed in the battery management App is used to remind the user to trigger the algorithm update instruction in the battery management App, so that the user can update the algorithm according to his own will, thereby improving the user experience and the transparency of the algorithm update, and the interaction between the algorithm update and the user is improved by triggering the algorithm update through the user operation of the battery management App.

[0142] The target algorithm module is updated, which actually updates the target algorithm module in the current battery management algorithm model in the vehicle. Based on this, in one of the embodiments, the step S240 of updating the target algorithm module according to the reference battery management algorithm model includes:

[0143] The target algorithm module in the reference battery management algorithm model is sent to the vehicle; the vehicle is used to update the target algorithm module in the current battery management algorithm model according to the received target algorithm module.

[0144] Optionally, after determining the target algorithm module that needs to be updated, the cloud server can send the target algorithm module in the reference battery management algorithm model to the vehicle, so that the vehicle updates the target algorithm module in the current battery management algorithm model according to the received target algorithm module.

[0145] For example, the cloud server can send the program package of the target algorithm module in the reference battery management algorithm model to the vehicle, and the vehicle can replace the program package of the target algorithm module in the current battery management algorithm model with the received program package of the target algorithm module, so as to update the target algorithm module.

[0146] In order to improve the communication security, in one of the embodiments, as shown in Figure 7 Before the target algorithm module in the reference battery management algorithm model is sent to the vehicle, the method further includes:

[0147] S710, performing a communication handshake and security authentication with the vehicle.

[0148] The communication handshake and security authentication are important mechanisms for ensuring the secure and reliable transmission of data between two ends in a network environment. The communication handshake is a series of interactive processes between the two ends of data transmission when establishing a communication connection, aiming to ensure that the two ends can correctly establish a connection and prepare for subsequent data transmission. The security authentication is to verify the authenticity and legality of the two ends through a series of technical means, and to ensure the security of data in the communication process.

[0149] Optionally, the cloud server can first perform a communication handshake with the vehicle through the RDB to establish a communication connection, and then perform a security authentication after the communication connection is established.

[0150] Exemplarily, the process of the communication handshake is as follows:

[0151] When the vehicle starts or needs to communicate with the cloud server, the vehicle sends a connection request including vehicle information to the cloud server. After receiving the connection request sent by the vehicle, the cloud server parses the connection request to determine whether the connection request meets the requirements, and sends a response message to the vehicle to inform the vehicle that its connection request has been received to prepare for the next communication negotiation in the case of meeting the requirements. The vehicle and the cloud server negotiate the communication parameters, and after the negotiation is completed, a logical communication connection is established between the vehicle and the cloud server. At this time, the communication handshake is completed, and the vehicle and the cloud server can start data transmission.

[0152] The vehicle information can include vehicle identification or communication protocol version, etc. The negotiated communication parameters can include encryption method of communication, data transmission format or interval time of heartbeat packet, etc.

[0153] Exemplarily, the process of the security authentication is as follows:

[0154] The vehicle sends an authentication request containing vehicle identity information to the cloud, which can include the vehicle's VIN code, a unique identifier of the vehicle, or a digital certificate, etc. After receiving the authentication request, the cloud server will verify the legality of the vehicle identity information by comparing it with the records in the background database or using the services of the authentication center. In order to let the vehicle confirm that the cloud server it communicates with is legal, the cloud server will also provide its own identity proof, such as a digital certificate, to the vehicle. The vehicle will verify the validity of the cloud server's digital certificate, including whether the digital certificate is issued by a trusted certificate authority and whether it is within the valid period, etc. In the case that both sides pass the identity authentication, the vehicle and the cloud server will jointly generate a session key. This session key is used to encrypt and decrypt all transmitted data in this communication session to ensure the confidentiality and integrity of the data. Subsequent communication data will be encrypted and transmitted using this session key until the end of this communication session.

[0155] It should be noted that the data transmission between the cloud server and the vehicle supports breakpoint continuation, so that the algorithm model update can still be completed when the network environment is poor, which can correspondingly improve the success rate of the update and user satisfaction.

[0156] S720, in the case that the communication handshake and security authentication between the cloud server and the vehicle are successfully completed, the step of sending the target algorithm module in the reference battery management algorithm model to the vehicle is performed.

[0157] Optionally, the cloud server can detect whether the communication handshake and security authentication between itself and the vehicle are successfully completed, and in the case of successful completion, the step of sending the target algorithm module in the reference battery management algorithm model to the vehicle is performed.

[0158] Exemplarily, in the case that the cloud server detects that the communication handshake and security authentication between itself and the vehicle are not successfully completed, it can simultaneously send prompt information to the battery manager App on the terminal device that the communication connection between the vehicle and the cloud server has failed, so as to remind the user to troubleshoot the connection failure.

[0159] It should be noted that not only the communication handshake and security authentication are performed before the cloud server sends the target algorithm module to the vehicle, but also the communication handshake and security authentication are performed before each communication between the cloud server and the vehicle, such as before sending data.

[0160] The embodiment of the application performs the step of sending the target algorithm module in the reference battery management algorithm model to the vehicle after performing communication handshake and security authentication with the vehicle before sending the target algorithm module in the reference battery management algorithm model to the vehicle, so that the step of sending the target algorithm module in the reference battery management algorithm model to the vehicle is performed when the communication handshake and security authentication are successfully completed.

[0161] In one embodiment, the battery management algorithm updating method provided by the embodiment of the application is applied to a vehicle in Figure 1 For example, as shown in Figure 8 The method comprises the following steps:

[0162] S810, sending battery management algorithm running data, battery attribute data and vehicle working condition information of the vehicle to the cloud server; the battery management algorithm running data is data obtained by running the current battery management algorithm model of the vehicle; the algorithm modules in the battery management algorithm model of the vehicle under different management types adopt plug-in design.

[0163] Optionally, the vehicle can obtain the battery management algorithm running data and the battery attribute data of the vehicle through the BMS, determine the location of the vehicle through a positioning module such as a global positioning system (GPS) combined with map data, obtain the environmental temperature of the location through the Internet, and send the location of the vehicle and the environmental temperature of the location as the vehicle working condition information to the cloud server together with the battery management algorithm running data and the battery attribute data for the cloud server to determine the target algorithm module to be updated.

[0164] For example, the vehicle can periodically send the battery management algorithm running data, the battery attribute data and the vehicle working condition information of the vehicle to the cloud server for the cloud server to periodically update the current battery management algorithm model in the vehicle.

[0165] It should be noted that the current battery management algorithm model in the vehicle can be a battery general management algorithm model, a battery scene management algorithm model for a battery model, or a reference battery management algorithm model for the vehicle obtained after the previous update. When the vehicle is shipped, the cloud server can download the battery general management algorithm model corresponding to the initial BMS algorithm package to the vehicle through a burning device.

[0166] S820, updating the target algorithm module in the current battery management algorithm model; the target algorithm module is determined by the cloud server according to the reference battery management algorithm model and the current battery management algorithm model of the vehicle; the cloud server generates the reference battery management algorithm model of the vehicle by obtaining the battery scene management algorithm model and sending the battery scene management algorithm model to the vehicle, and according to the battery management algorithm running data, the battery attribute data and the vehicle working condition information of the vehicle; the battery scene management algorithm model represents the battery management algorithm model of the same type under the same type as the battery model of the vehicle.

[0167] Optionally, the vehicle receives the target algorithm module in the reference battery management algorithm model sent by the cloud server, to update the target algorithm module in the current battery management algorithm model according to the received target algorithm module,

[0168] Illustratively, the vehicle can directly replace the target algorithm module in the current battery management algorithm model with the received target algorithm module. The vehicle can also detect its own vehicle running state, to update the target algorithm module in the current battery management algorithm model in the case that the vehicle running state is normal / safe. For example, the vehicle running state is a stop state, or the corresponding target algorithm module is not running, it is determined that the vehicle running state is normal / safe; otherwise, it is not. In this way, the interference of algorithm model update on vehicle running can be effectively reduced, thereby improving the safety of vehicle running and user experience.

[0169] The specific process of determining the target algorithm module that needs to be updated by the cloud server is described in the foregoing embodiment of the battery management algorithm updating method applied to the cloud server, and will not be repeated here.

[0170] In the embodiments of the present application, the vehicle sends battery management algorithm running data, battery attribute data, and vehicle working condition information to the cloud server, and updates a target algorithm module in the current battery management algorithm model; the battery management algorithm running data is data obtained by running the current battery management algorithm model of the vehicle; the algorithm modules under different management types in the battery management algorithm model of the vehicle are designed in a plug-in manner; the target algorithm module is determined by the cloud server according to a reference battery management algorithm model and the current battery management algorithm model of the vehicle; the cloud server acquires a battery scenario management algorithm model, sends the battery scenario management algorithm model to the vehicle, and generates a reference battery management algorithm model of the vehicle according to the battery management algorithm running data, the battery attribute data, and the vehicle working condition information of the vehicle; the battery scenario management algorithm model represents a battery management algorithm model under the same type as the battery model of the vehicle; in the above method, the algorithm modules under different management types in the battery management algorithm model are designed in a plug-in manner, the targeted update of the target algorithm module is realized without updating the entire model, the flexibility of algorithm update is improved, the on-demand update of part of the algorithm in the algorithm model is realized, and based on the dynamic change of the personalized data sent by the vehicle to the cloud service, the dynamic and continuous update of the algorithm model can be realized accordingly to adapt to the change of the vehicle working condition (such as the change from high cold to high temperature) and the individual difference of the battery (such as the aging state of the battery), and the real-time performance and robustness of the algorithm model are improved.

[0171] The update of the target algorithm module is essentially the update of the program package of the target algorithm module. Therefore, in one of the embodiments, as shown in Figure 9 the update of the target algorithm module in the current battery management algorithm model in S820 includes:

[0172] S910, receiving the program package of the target algorithm module sent by the cloud server.

[0173] Optionally, the vehicle can receive the program package of the target algorithm package in the reference battery management algorithm model sent by the cloud server.

[0174] S920, storing the program package of the target algorithm module to the battery management algorithm storage area of the vehicle, and setting the program package of the original target algorithm module in the current battery management algorithm model as a backup program package, to complete the update of the target algorithm module in the current battery management algorithm model of the vehicle.

[0175] Optionally, the vehicle stores the received program package of the target algorithm module into the battery management algorithm storage area of the vehicle, and adds a backup label to the program package of the original target algorithm module in the current battery management algorithm model to set the program package of the original target algorithm module as a backup program package, so that the received program package of the target algorithm module and the program package of the original target algorithm module in the current battery management algorithm model are stored in the battery management algorithm storage area of the vehicle at the same time, and the updating of the target algorithm module in the current battery management algorithm model of the vehicle is completed.

[0176] It should be noted that, in the case that the vehicle runs the current battery management algorithm model, the program package of the algorithm module without the backup label is preferentially run, and in the case of failure (such as updating failure or algorithm incompatibility), the program package of the algorithm module with the backup label is rolled back to run.

[0177] In the embodiments of the present application, the program package of the target algorithm module sent by the cloud server is received, and the program package of the target algorithm module is stored into the battery management algorithm storage area of the vehicle, and the program package of the original target algorithm module in the current battery management algorithm model is set as a backup program package, and the updating of the target algorithm module in the current battery management algorithm model of the vehicle is completed; in the above method, the program package of the original target algorithm module in the current battery management algorithm model is set as a backup program package, and the original target algorithm module and the received target algorithm module are stored at the same time, so that in the case of running failure of the received target algorithm module, the original target algorithm module is rolled back to run, and the reliability and stability of the BMS running are improved.

[0178] In order to save storage resources, in one of the embodiments, as shown in Figure 10 the above method further comprises:

[0179] S1010, detecting the running state of the target algorithm module in the current battery management algorithm model of the vehicle after updating.

[0180] The running state of the target algorithm module is used to represent whether the target algorithm module runs normally or not.

[0181] Optionally, the vehicle can collect the battery parameters of the battery managed by the target algorithm module through the BMS in the case of running the target algorithm module in the current battery management algorithm model, so as to determine the running state of the target algorithm module according to the battery parameters.

[0182] For example, in the case that the battery parameters meet the preset range, it is determined that the running state of the target algorithm module is normal, otherwise, in the case that the battery parameters do not meet the preset range, it is determined that the running state of the target algorithm module is abnormal.

[0183] S1020, in a case where the running state of the target algorithm module meets the preset state condition, deleting the backup program package.

[0184] Optionally, after obtaining the running state of the target algorithm module, the vehicle can compare the running state of the target algorithm module with the preset state condition to determine whether to delete the backup program package according to a comparison result.

[0185] Exemplarily, the preset state condition includes a preset time length for maintaining a normal running state. In a case where the vehicle detects that the running state of the target algorithm module is normal, the vehicle further records a continuous time length of the normal running state, and in a case where the continuous time length is greater than the preset time length, it is determined that the running state of the target algorithm module meets the preset state condition, and the program package of the original target algorithm module in the current battery management algorithm model of the vehicle, i.e., the backup program package, is deleted accordingly.

[0186] It should be noted that in a case where the running state of the target algorithm module does not meet the preset state condition, the vehicle end can delete the program package of the target algorithm module sent by the cloud server, eliminate the backup label of the program package of the original target algorithm module, and also can synchronously feed back prompt information of algorithm update failure to the battery manager App on the terminal device. Exemplarily, continuing to take the case where the preset state condition includes a preset time length for maintaining a normal running state as an example, in a case where the vehicle detects the continuous time length of the target algorithm module maintaining the normal running state, and the continuous time length is less than or equal to the preset time length, it is determined that the running state of the target algorithm module does not meet the preset state condition.

[0187] In the embodiments of the present application, the running state of the target algorithm module in the current battery management algorithm model of the updated vehicle is detected, so that the backup program package is deleted in a case where the running state of the target algorithm module meets the preset state condition; in the above method, the old backup program package is deleted in a case where it is determined that the running state of the target algorithm module meets the preset state condition, which improves the stability of the BMS, releases the storage space occupied by the backup program package, saves the storage resources of the vehicle end, and improves the resource utilization.

[0188] In order to facilitate the understanding of those skilled in the art, the battery management algorithm updating method provided by the present application is described in detail as follows, as shown in the following figure, the method can include: Figure 11

[0189] S1101, obtaining battery management algorithm running data of a plurality of reference batteries and battery attribute data of each reference battery; the plurality of reference batteries represent batteries with the same battery model as the battery model in the vehicle; the battery management algorithm running data is data obtained by running the current battery management algorithm model of the vehicle;

[0190] ​S1102, training a battery general management algorithm model according to battery management algorithm running data of the plurality of reference batteries and battery attribute data of each reference battery, to obtain a battery scenario management algorithm model; the algorithm modules under different management types in the battery management algorithm model of the vehicle adopt a plug-in type design;

[0191] S1103, sending the battery scenario management algorithm model to the vehicle;

[0192] S1104, generating a reference battery management algorithm model of the vehicle according to battery management algorithm running data, battery attribute data, vehicle working condition information of the vehicle, and the battery scenario management algorithm model;

[0193] S1105, simulating running each algorithm module in the reference battery management algorithm model in an algorithm simulator to obtain a reference performance evaluation result of each algorithm module;

[0194] S1106, simulating running each algorithm module in the current battery management algorithm model in the algorithm simulator to obtain a current performance evaluation result of each algorithm module;

[0195] S1107, comparing the reference performance evaluation result and the current performance evaluation result for each algorithm module;

[0196] S1108, in a case where the reference performance evaluation result is better than the current performance evaluation result, taking the algorithm module as a target algorithm module to be updated;

[0197] S1109, sending an algorithm update request to a terminal device where the battery housekeeper application program is located; the algorithm update request is used to instruct the terminal device to push a reminding message for updating the current battery management algorithm model in the battery housekeeper application program;

[0198] S1110, in response to an algorithm update instruction sent by the terminal device, performing communication handshake and security authentication with the vehicle;

[0199] S1111, in a case where the communication handshake and the security authentication are successfully completed, sending the target algorithm module in the reference battery management algorithm model to the vehicle; the vehicle is used to update the target algorithm module in the current battery management algorithm model according to the received target algorithm module.

[0200] It should be noted that the description in S1101-S1111 above can refer to the related description in the above embodiments, and the effects are similar, and the present embodiment will not be repeated here.

[0201] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0202] In one embodiment, such as Figure 12 As shown, a battery management algorithm update device is provided, applied to a cloud server, including: a first model module 1201, a second model module 1202, a target determination module 1203, and an algorithm update module 1204; wherein:

[0203] The first model module 1201 is used to obtain the battery scenario management algorithm model and send the battery scenario management algorithm model to the vehicle; the battery scenario management algorithm model represents the battery management algorithm model under the same model as the vehicle's battery model; the battery management algorithm running data is the data obtained by running the current battery management algorithm model on the vehicle; the algorithm modules under different management types in the vehicle's battery management algorithm model adopt a plug-in design;

[0204] The second model module 1202 is used to generate a reference battery management algorithm model for the vehicle based on the vehicle's battery management algorithm operation data, battery attribute data, vehicle operating condition information, and battery scenario management algorithm model.

[0205] The target determination module 1203 is used to determine the target algorithm module that needs to be updated based on the reference battery management algorithm model and the current battery management algorithm model;

[0206] The algorithm update module 1204 is used to update the target algorithm module according to the reference battery management algorithm model.

[0207] The aforementioned battery management algorithm update device is used to implement any of the battery management algorithm update methods applied to the cloud server. For details of the process, please refer to the foregoing embodiments, which will not be repeated here.

[0208] In one embodiment, such as Figure 13 As shown, a battery management algorithm update device is provided for use in a vehicle, including: a data reporting module 1301 and a target update module 1302; wherein:

[0209] The data reporting module 1301 is configured to send battery management algorithm running data, battery attribute data, and vehicle working condition information of the vehicle to a cloud server; the battery management algorithm running data is data obtained by running a current battery management algorithm model of the vehicle; algorithm modules under different management types in the battery management algorithm model of the vehicle are designed in a plug-in manner.

[0210] The target updating module 1302 is configured to update a target algorithm module in the current battery management algorithm model; the target algorithm module is determined by the cloud server according to a reference battery management algorithm model and the current battery management algorithm model of the vehicle; the cloud server acquires a battery scenario management algorithm model, sends the battery scenario management algorithm model to the vehicle, and generates the reference battery management algorithm model of the vehicle according to the battery management algorithm running data, the battery attribute data, and the vehicle working condition information of the vehicle; the battery scenario management algorithm model represents a battery management algorithm model under the same type as the battery model of the vehicle.

[0211] The battery management algorithm updating apparatus described above is configured to implement any one of the battery management algorithm updating methods applied to the vehicle, and the specific process is described in the foregoing embodiments, which will not be described here again.

[0212] Each module in the battery management algorithm updating apparatus described above can be implemented by software, hardware, or a combination thereof in whole or in part. Each module described above can be embedded in or independent of a processor in a computer device in a hardware form, or can be stored in a memory in a computer device in a software form, so as to be called and executed by a processor to perform the operations corresponding to each module.

[0213] In one embodiment, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program. The computer program is executed by a processor to implement the steps of any one of the battery management algorithm updating methods described above.

[0214] In one embodiment, a computer program product is provided, and the computer program product includes a computer program. The computer program is executed by a processor to implement the steps of any one of the battery management algorithm updating methods described above.

[0215] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0216] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0217] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A battery management algorithm update method, characterized by, The method applied to a cloud server comprises: obtaining a battery scenario management algorithm model and sending the battery scenario management algorithm model to a vehicle; the battery scenario management algorithm model represents a battery management algorithm model of the same type as a battery model of the vehicle; the battery management algorithm running data is data obtained by running a current battery management algorithm model of the vehicle; the battery management algorithm model of the vehicle adopts a plug-in design for algorithm modules of different management types; the battery management algorithm model comprises a plurality of algorithm modules, each algorithm module corresponding to an algorithm of a management type; generating a reference battery management algorithm model of the vehicle according to the battery management algorithm running data of the vehicle, battery attribute data, vehicle working condition information and the battery scenario management algorithm model; simulating running of each algorithm module in the reference battery management algorithm model in an algorithm simulator to obtain a reference performance evaluation result of each algorithm module; simulating running of each algorithm module in the current battery management algorithm model in the algorithm simulator to obtain a current performance evaluation result of each algorithm module; determining a target algorithm module to be updated according to the reference performance evaluation result and the current performance evaluation result of each algorithm module; sending the target algorithm module in the reference battery management algorithm model to the vehicle; the vehicle is configured to update the target algorithm module in the current battery management algorithm model according to the received target algorithm module.

2. The method of claim 1, wherein, The method comprises: obtaining battery management algorithm running data of a plurality of reference batteries and battery attribute data of each reference battery; the plurality of reference batteries represent batteries of the same type as a battery type of the vehicle; training a battery universal management algorithm model according to the battery management algorithm running data of the plurality of reference batteries and the battery attribute data of each reference battery to obtain the battery scenario management algorithm model.

3. The method of claim 1, wherein, The method comprises: comparing the reference performance evaluation result and the current performance evaluation result for each algorithm module; in a case where the reference performance evaluation result is better than the current performance evaluation result, regarding the algorithm module as the target algorithm module.

4. The method according to claim 1 or 2, characterized in that, Before the step of updating the target algorithm module according to the reference battery management algorithm model, the method further comprises: sending an algorithm update request to a terminal device where a battery manager application is located; the algorithm update request is configured to instruct the terminal device to push a prompt message for updating the current battery management algorithm model in the battery manager application; in response to an algorithm update instruction sent by the terminal device, performing the step of updating the target algorithm module according to the reference battery management algorithm model; the algorithm update instruction is triggered by a user in the battery manager application based on the prompt message.

5. The method according to claim 1 or 2, characterized in that, Before the step of sending the target algorithm module in the reference battery management algorithm model to the vehicle, the method further comprises: communicating a handshake and security authentication with the vehicle; in the case of successful completion of the communication handshake and security authentication, performing the step of sending the target algorithm module in the reference battery management algorithm model to the vehicle.

6. A battery management algorithm update method, characterized by, The method is applied to a vehicle, and the method comprises: sending, to a cloud server, battery management algorithm running data, battery attribute data, and vehicle working condition information of the vehicle; the battery management algorithm running data is data obtained by running a current battery management algorithm model of the vehicle; algorithm modules in the battery management algorithm model of the vehicle under different management types are designed in a plug-in manner; the battery management algorithm model comprises a plurality of algorithm modules, and each algorithm module corresponds to an algorithm of a management type; receiving a target algorithm module sent by the cloud server, and updating a target algorithm module in the current battery management algorithm model according to the received target algorithm module; the target algorithm module is determined according to reference performance evaluation results of each algorithm module in a reference battery management algorithm model obtained by simulating running each algorithm module in the reference battery management algorithm model in an algorithm simulator and current performance evaluation results of each algorithm module in the current battery management algorithm model obtained by simulating running each algorithm module in the current battery management algorithm model in the algorithm simulator; the cloud server obtains a battery scenario management algorithm model, sends the battery scenario management algorithm model to the vehicle, and generates a reference battery management algorithm model of the vehicle according to the battery management algorithm running data, the battery attribute data, and the vehicle working condition information of the vehicle; the battery scenario management algorithm model represents a battery management algorithm model of the same type as the battery model of the vehicle.

7. The method of claim 6, wherein, The updating of the target algorithm module in the current battery management algorithm model according to the received target algorithm module comprises: receiving a program package of the target algorithm module sent by the cloud server; storing the program package of the target algorithm module to a battery management algorithm storage area of the vehicle, setting a program package of an original target algorithm module in the current battery management algorithm model as a backup program package, and completing the updating of the target algorithm module in the current battery management algorithm model of the vehicle.

8. The method of claim 7, wherein, The method further comprises: detecting a running state of the target algorithm module in the current battery management algorithm model of the vehicle after the updating; in the case that the running state of the target algorithm module meets a preset state condition, deleting the backup program package.

9. A battery management algorithm updating apparatus characterized by comprising: The device is applied to a cloud server, and the device comprises: The first model module is configured to obtain a battery scenario management algorithm model and send the battery scenario management algorithm model to a vehicle; the battery scenario management algorithm model represents a battery management algorithm model of a same type as a battery type of the vehicle; the battery management algorithm running data is data obtained by running a current battery management algorithm model of the vehicle; algorithm modules of different management types in the battery management algorithm model of the vehicle adopt a plug-in design; the battery management algorithm model includes a plurality of algorithm modules, and each algorithm module corresponds to an algorithm of a management type; The second model module is configured to generate a reference battery management algorithm model of the vehicle according to the battery management algorithm running data of the vehicle, battery attribute data, vehicle working condition information, and the battery scenario management algorithm model; The target determination module is configured to simulate running of each algorithm module in the reference battery management algorithm model in an algorithm simulator to obtain reference performance evaluation results of the algorithm modules; simulate running of each algorithm module in the current battery management algorithm model in the algorithm simulator to obtain current performance evaluation results of the algorithm modules; and determine target algorithm modules that need to be updated according to the reference performance evaluation results and the current performance evaluation results of the algorithm modules. The algorithm update module is configured to send the target algorithm modules in the reference battery management algorithm model to the vehicle; and the vehicle is configured to update the target algorithm modules in the current battery management algorithm model according to the received target algorithm modules. 10.A cloud server, comprising a memory and a processor, wherein the memory stores a computer program, and the cloud server is characterized in that, The processor implements the steps of the method of any one of claims 1 to 5 when executing the computer program.

11. A vehicle comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor implements the steps of the method of any one of claims 6 to 8 when executing the computer program.

12. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 8.

13. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 8.

Images