CN113189495B - A method, device and electronic device for predicting battery health status - Google Patents

Abstract

The application provides a battery health state prediction method, a battery health state prediction device and electronic equipment, wherein the method comprises the steps of collecting real-time operation parameters of a battery of an electric vehicle under preset driving conditions according to preset sampling conditions; acquiring target operation parameters of the electric vehicle in each preset voltage range according to the real-time operation parameters; predicting battery health states of the batteries respectively corresponding to each preset voltage range according to the target operation parameters by utilizing a trained deep learning model; according to the battery health status respectively corresponding to the batteries in each preset voltage range, the target battery health status of the batteries is determined, and the battery health status prediction method based on artificial intelligence disclosed by the application can realize accurate battery health status prediction.

Description

A method, device and electronic device for predicting battery health status

Technical Field

The present invention relates to the field of batteries, and in particular to a method, device and electronic equipment for predicting the health status of a battery.

Background technique

With the development of technology, electric vehicles are increasingly widely used. In order to ensure the safety and reliability of the battery management system (BMS) of electric vehicles, the robustness and efficiency of battery-related algorithms must be guaranteed. Since the state of health algorithm (SOH) has a great influence on battery operation (such as fast charging protocol), state of charge (SOC) and state of power (SOP), it is the most critical algorithm among all battery-related algorithms. Battery capacity and resistance are often regarded as battery health indicators. The prior art usually uses rate performance testing (RPT) to directly measure the capacity and DC resistance (DCR) of the battery. This method is to fully charge and discharge the battery and apply a pulse to the battery at a certain SOC (such as 50%). However, the method of estimating the SOH value by fully discharging or charging the battery cannot be applied to electric vehicles. Therefore, a new method is needed to estimate the battery capacity and resistance of electric vehicles using the collected partial charge and discharge operation data. There are two types of SOH estimation methods in the prior art: model-based methods and data-driven methods.

Due to the complexity of the degradation mechanism of lithium-ion batteries, it is very difficult to find a reliable physical model to predict the SOH of the battery under various storage and cycling conditions. Physics-based models also involve a large number of nonlinear partial differential equation systems, which makes these models unsuitable for in-vehicle applications. Therefore, SOH estimation methods based on semi-empirical calendars and cycle life models are more popular. In order to find the correlation between battery capacity and DC resistance (DCR) with time, energy throughput, SOC and temperature, it is necessary to perform reference performance tests (RPTs) regularly during life testing and collect a large amount of storage and cycling data. However, the physical model obtained by applying this method may be limited to driving scenarios that are very similar to the test conditions.

Another model-based approach is based on state/parameter observer design, where the SOH is predicted as parameters of a state-space model through adaptive algorithms such as numerical filtering. A commonly used state-space model in the prior art is the equivalent circuit model (ECM), where the battery is represented as a simple resistor-capacitor circuit network. While these online monitoring methods have the major advantage of a closed-loop nature, overly simplified state-space models such as ECMs will result in significant unmodeled dynamics, making the resulting SOH estimates inaccurate.

Summary of the invention

In order to solve the deficiencies of the prior art, the main purpose of the present invention is to provide a method, device and electronic device for predicting the health status of a battery to solve the above technical problems.

In order to achieve the above object, the present invention provides a method for predicting a battery health state in a first aspect, the method comprising:

According to preset sampling conditions, real-time operating parameters of the battery of the electric vehicle under preset driving conditions are collected;

According to the real-time operating parameters, obtaining target operating parameters of the electric vehicle within each preset voltage range;

Using the trained deep learning model, predicting the battery health status corresponding to each preset voltage range of the battery according to the target operating parameters;

The target battery health state of the battery is determined according to the battery health states corresponding to the battery in each preset voltage range.

In some embodiments, the real-time operating parameters include the real-time current, real-time voltage and real-time temperature of the battery;

The step of obtaining the target operating parameters of the electric vehicle within each preset voltage range according to the real-time operating parameters includes:

Obtaining the real-time current, real-time voltage and real-time temperature corresponding to the battery within each preset voltage range;

Determine, according to the real-time current, real-time voltage and real-time temperature, the average current, average voltage, average resistance and average temperature corresponding to the battery within each of the preset voltage ranges;

Determining, according to the real-time current, a total throughput of the battery corresponding to each of the preset voltage ranges;

The target operating parameter is determined according to the total throughput, the average current, the average voltage, the average resistance, and the average temperature.

In some embodiments, the method further includes a training process of the deep learning model, wherein the training process includes:

Acquiring a historical data set, the historical data set comprising measured historical operating parameters of a battery of the electric vehicle within a preset voltage range under the preset driving condition;

According to a preset division rule, the historical data set is divided into a training data set and a test data set;

Using the training data set to train an initial deep learning model;

The trained initial deep learning model is tested using the test data set, and when the test result meets a preset condition, the trained initial deep learning model is determined to be a trained deep learning model.

In some embodiments, determining the target battery health state of the battery according to the battery health state corresponding to each preset voltage range of the battery includes:

The target health state of the battery is determined according to the predicted battery health states corresponding to each preset voltage range and the preset weight value corresponding to each preset voltage range.

In some embodiments, the method comprises:

When the target health status does not meet the preset conditions, it is determined that the battery is abnormal and an alarm signal is issued.

In some embodiments, the method comprises:

generating a measurement record including the target battery health status and generation time;

receiving a battery health status query request from a user, wherein the request includes a request time;

When the difference between the request time and the generation time of the measurement record does not exceed a preset time threshold, the target battery health status is returned to the user.

In a second aspect, the present application provides a device for predicting a battery health state, the device comprising:

A collection module, used to collect real-time operating parameters of the battery of the electric vehicle under preset driving conditions according to preset sampling conditions;

An acquisition module, used for acquiring target operating parameters of the electric vehicle within each preset voltage range according to the real-time operating parameters;

A prediction module, configured to predict the battery health status corresponding to each preset voltage range of the battery according to the target operating parameters by using a trained deep learning model;

The judgment module is used to determine the target battery health state of the battery according to the battery health state corresponding to each preset voltage range of the battery.

In some embodiments, the real-time operating parameters include the real-time current, real-time voltage and real-time temperature of the battery, and the acquisition module can also be used to obtain the real-time current, real-time voltage and real-time temperature corresponding to the battery in each of the preset voltage ranges; determine the average current, average voltage, average resistance and average temperature corresponding to the battery in each of the preset voltage ranges according to the real-time current, real-time voltage and real-time temperature; determine the total throughput corresponding to the battery in each of the preset voltage ranges according to the real-time current; determine the target operating parameters according to the total throughput, the average current, the average voltage, the average resistance and the average temperature.

In a third aspect, the present application provides a computer-readable storage medium storing computer instructions, characterized in that when the computer instructions are executed on a processing component of a computer, the processing component executes the steps of the method described above.

In a fourth aspect, the present application provides an electronic device, the electronic device comprising:

one or more processors;

and a memory associated with the one or more processors, the memory being used to store program instructions, the program instructions when read and executed by the one or more processors performing the following operations:

According to preset sampling conditions, real-time operating parameters of the battery of the electric vehicle under preset driving conditions are collected;

According to the real-time operating parameters, obtaining target operating parameters of the electric vehicle within each preset voltage range;

Using the trained deep learning model, predicting the battery health status corresponding to each preset voltage range of the battery according to the target operating parameters;

The target battery health state of the battery is determined according to the battery health states corresponding to the battery in each preset voltage range.

The beneficial effects achieved by the present invention are:

The present application proposes a method for predicting a battery health state, comprising collecting real-time operating parameters of a battery of an electric vehicle under preset driving conditions according to preset sampling conditions; obtaining target operating parameters of the electric vehicle within each preset voltage range according to the real-time operating parameters; predicting the battery health states corresponding to each preset voltage range of the battery according to the target operating parameters using a trained deep learning model; and determining the target battery health state of the battery according to the battery health states corresponding to each preset voltage range. The artificial intelligence-based battery health state prediction method disclosed in the present application can simulate and predict the battery health state in the corresponding driving scenario more accurately and realistically because the deep learning model can be trained according to the real driving data of the vehicle, thereby avoiding the disadvantage that the physical model can only be applied to driving scenarios that are very similar to the test conditions. Moreover, the deep learning model trained with a large amount of data sets is more accurate in prediction results than the prediction methods such as the equivalent circuit model in the prior art, and can achieve accurate prediction of the battery health state.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

FIG1 is a deep learning model prediction flow chart provided in an embodiment of the present application;

FIG2 is a flow chart of a method provided in an embodiment of the present application;

FIG3 is a structural diagram of a device provided in an embodiment of the present application;

FIG4 is a structural diagram of an electronic device provided in an embodiment of the present application;

FIG. 5 is a schematic diagram of battery operating parameters of an electric vehicle provided in an embodiment of the present application.

Detailed ways

In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

As described in the background technology, the two types of battery health status assessment methods used in the prior art have different shortcomings. In order to solve the above technical problems, this application proposes a battery health status prediction method, which not only solves the shortcomings of the physical model that can only be applied to driving scenarios that are very similar to the test conditions, but also avoids the problem that the equivalent circuit model and other methods lead to significant unmodeled dynamics, making the generated SOH estimate inaccurate.

Embodiment 1

Specifically, in order to implement the battery health status prediction method disclosed in the present application, it is necessary to train the deep learning model in advance. The training process of the model includes:

S1. Obtain a historical data sample set and divide it into a training sample set and a test sample set;

The historical data sample set can be data collected from real vehicle driving scenarios, including the operating parameters of the vehicle under corresponding driving conditions and the corresponding battery health status. Due to the empirical nature of the data-driven method, a large amount of battery life data, i.e., historical samples, is essential for training, verifying and testing the neural network proposed in this application. The historical samples are obtained through charge/discharge/storage tests and reference performance tests (RPTs), respectively. The test for obtaining life data starts with the initial RPT, that is, measuring the capacity and DCR of a new battery at 25°C. The battery is then stored at a certain temperature and SOC (storage test), or continuously cycled for 2-4 weeks under certain charge and discharge conditions (cycling test). Subsequently, a second RPT is performed to track the battery capacity and DCR, and then the battery is stored or cycled again for 2-4 weeks in order to obtain sufficient historical samples of the battery.

Preferably, 70% of the historical samples can be divided into training samples and 30% of the historical samples can be divided into test samples. Allocating 30% of the data to testing can significantly reduce the risk of overfitting, thereby enhancing the robustness of the algorithm for online BMS applications.

Each historical sample includes [I _avg ，V _avg ，T _avg ，R _avg ，T _avg ， Where I _avg represents the average current of the battery under the corresponding voltage range and driving conditions, V _avg represents the average voltage of the battery under the corresponding voltage range and driving conditions, R _avg represents the average resistance of the battery under the corresponding voltage range and driving conditions, T _avg represents the average temperature of the battery under the corresponding voltage range and driving conditions, Indicates the total throughput of the battery in the corresponding voltage range and driving conditions, that is, the total throughput can be calculated based on the real-time current and the duration of the preset voltage range. Specifically, the average resistance RK corresponding to the historical sample K can be calculated according to the formula/> if |I _k+1 -I _k |＞C/10, where VK+1 represents the average voltage corresponding to historical sample K+1, I _K+1 represents the average current corresponding to historical sample K+1, V _K represents the average voltage corresponding to historical sample K, I _K represents the average current corresponding to historical sample K, and C represents a preset constant.

S2. Use the training sample set to train the preset deep learning model;

Specifically, during training, 60% of the training samples in the training sample set can be used to train the deep learning model, 20% of the training samples can be used to verify the deep learning model, and 20% of the training samples can be used to test the deep learning model. Preferably, the MATLAB deep learning toolbox can be used to train, verify and test the deep learning model.

The corresponding battery capacity and DC impedance DCR may also be set in each sample of the training sample set and the test sample set for model learning, so that subsequent models may also predict the battery capacity and DC impedance of the battery according to the target operating parameters.

S3. Use the test sample set to test the deep learning model, and when the test result meets the preset conditions, determine that the deep learning model is a trained deep learning model.

Specifically, after obtaining the trained deep learning model, the operating parameters and corresponding battery health status collected in the actual driving scenario of the vehicle can be used to further train the deep learning model to improve the actual prediction effect of the model.

In one embodiment, the vehicle can interact with the deep learning model deployed in the cloud, and upload the collected real-time operating parameters to the deep learning model so that the deep learning model can predict and ultimately generate the corresponding battery health status and return it to the vehicle. The deep learning model deployed in the cloud can be further trained based on the operating parameters of a large number of vehicles under real driving conditions to improve the accuracy of the deep learning model.

After obtaining the trained deep learning model, as shown in FIG1 , the process of applying the battery health state prediction method disclosed in the present application to predict the battery health state includes:

Step 1: Collecting real-time operating parameters of the electric vehicle under preset driving conditions;

The real-time operating parameters include the real-time current, real-time voltage, real-time resistance, real-time temperature and real-time throughput of the battery, wherein the real-time resistance can be calculated based on the real-time current and real-time voltage.

Step 2, determining the average current, average voltage, average resistance and average temperature of the battery within each preset voltage range according to the real-time current, real-time voltage, real-time resistance and real-time temperature;

FIG5 shows the time range time corresponding to when the electric vehicle is in a driving state and the voltage of the battery is in the preset voltage range R1, R2 and R3, and the real-time current Current, real-time voltage Voltage and real-time temperature Temperature corresponding to each time range. According to the real-time current, real-time voltage and real-time temperature, the average current, average voltage and average temperature of the battery in the time range corresponding to R1, R2 and R3 can be obtained respectively. At the same time, the corresponding average voltage can be calculated according to the real-time current and real-time voltage. According to the real-time current and the time range of the preset voltage range, the total throughput of the battery in the corresponding voltage range can also be calculated.

According to the total throughput, the average current, the average voltage, the average resistance and the average temperature, a target operating parameter corresponding to each preset voltage range may be generated.

Step 3: using the trained deep learning model to predict the battery health status corresponding to each preset voltage range of the battery according to the target operating parameters;

Specifically, the predicted battery health state SOH is defined based on the battery capacity and DC resistance DCR, that is:

Where SOH _C and SOH _R represent the SOH based on capacity and SOH based on DC resistance, respectively.

Step 4: determining a target health state of the battery according to the predicted battery health states corresponding to each preset voltage range and the preset weight value corresponding to each preset voltage range;

Specifically, when the target health status does not meet the preset conditions, the cloud or the vehicle's on-board terminal can send an alarm signal to the user through the on-board display device or through the on-board audio device and other devices, so that the user can repair or replace the battery in time to avoid safety hazards and affect the mileage.

Specifically, the open circuit voltage OCV and current of the battery can also be measured after the vehicle stops running for a long enough time. According to the preset open circuit voltage and state of charge SOC lookup table, the state of charge corresponding to the open circuit voltage can be determined, and then according to the formula Wherein I represents current, t ₂ and t ₁ represent the acquisition moments of OCV ₂ and OCV ₁ respectively, SOC ₂ (OCV ₂ ) represents the SOC ₂ reading determined according to the lookup table, and SOC ₁ (OCV ₁ ) represents the SOC ₁ reading determined according to the lookup table.

Get the battery health status.

At the same time, a health status measurement record including the target battery health status and the generation time can be generated. When a battery health status query request is subsequently received from the user of the vehicle and the difference between the request time and the generation time of the query request does not exceed the preset time threshold, the target battery health status can be returned to the user for reference.

Based on the battery health status prediction method disclosed in the present application, the vehicle can obtain a more accurate battery health status (SOH) prediction result, so as to further evaluate the state of charge SOC and battery power state SOP, which have a key impact on battery life, based on the SOH.

Embodiment 2

Corresponding to the above embodiment, as shown in FIG2 , the present application discloses a method for predicting a battery health state, the method comprising:

210. According to preset sampling conditions, collect real-time operating parameters of the battery of the electric vehicle under preset driving conditions;

220. Acquire target operating parameters of the electric vehicle within each preset voltage range according to the real-time operating parameters;

Preferably, the real-time operating parameters include the real-time current, real-time voltage and real-time temperature of the battery; and obtaining the target operating parameters of the electric vehicle within each preset voltage range according to the real-time operating parameters includes:

221. Obtain the real-time current, real-time voltage and real-time temperature corresponding to each battery within the preset voltage range;

222. Determine, according to the real-time current, real-time voltage and real-time temperature, the average current, average voltage, average resistance and average temperature corresponding to the battery within each of the preset voltage ranges;

223. Determine, according to the real-time current, a total throughput of the battery corresponding to each of the preset voltage ranges;

224. Determine the target operating parameter according to the total throughput, the average current, the average voltage, the average resistance, and the average temperature.

230. Using the trained deep learning model, predicting the battery health status corresponding to each preset voltage range of the battery according to the target operating parameter;

240. Determine a target battery health state of the battery according to the battery health states corresponding to the battery in each preset voltage range.

Preferably, determining the target battery health state of the battery according to the battery health state corresponding to each preset voltage range of the battery includes:

241. Determine a target health state of the battery according to the predicted battery health states corresponding to each preset voltage range and a preset weight value corresponding to each preset voltage range.

Preferably, the method further includes a training process of the deep learning model, and the training process includes:

250. Obtain a historical data set, the historical data set comprising measured historical operating parameters of a battery of the electric vehicle within a preset voltage range under the preset driving condition;

251. Divide the historical data set into a training data set and a test data set according to a preset division rule;

252. Train an initial deep learning model using the training data set;

253. Use the test data set to test the trained initial deep learning model. When the test result meets a preset condition, determine that the trained initial deep learning model is a trained deep learning model.

Preferably, the method comprises:

260. When the target health status does not meet the preset conditions, determine that the battery is abnormal and send an alarm signal.

Preferably, the method comprises:

270. Generate a measurement record including the target battery health status and generation time;

271. Receive a battery health status query request from a user, where the request includes a request time;

272. When the difference between the request time and the generation time of the measurement record does not exceed a preset time threshold, return the target battery health status to the user.

Embodiment 3

Corresponding to all the above embodiments, as shown in FIG3 , the present application provides a device for predicting a battery health state, the device comprising:

The collection module 310 is used to collect real-time operating parameters of the battery of the electric vehicle under preset driving conditions according to preset sampling conditions;

An acquisition module 320, configured to acquire a target operating parameter of the electric vehicle within each preset voltage range according to the real-time operating parameter;

A prediction module 330, configured to predict the battery health status corresponding to each preset voltage range of the battery according to the target operating parameters by using a trained deep learning model;

The determination module 340 is configured to determine a target battery health state of the battery according to the battery health states corresponding to the battery in each preset voltage range.

Preferably, the real-time operating parameters include the real-time current, real-time voltage and real-time temperature of the battery, and the acquisition module 320 can also be used to obtain the real-time current, real-time voltage and real-time temperature corresponding to the battery in each of the preset voltage ranges; determine the average current, average voltage, average resistance and average temperature corresponding to the battery in each of the preset voltage ranges according to the real-time current, real-time voltage and real-time temperature; determine the total throughput corresponding to the battery in each of the preset voltage ranges according to the real-time current; determine the target operating parameters according to the total throughput, the average current, the average voltage, the average resistance and the average temperature.

Preferably, the device includes a training module for acquiring a historical data set, wherein the historical data set includes measured historical operating parameters of the battery of the electric vehicle within a preset voltage range under the preset driving conditions; dividing the historical data set into a training data set and a test data set according to a preset division rule; training the deep learning model using the training data set; testing the deep learning model using the test data set, and when the test result meets the preset conditions, determining that the deep learning model is a trained deep learning model.

Preferably, the judgment module 340 can also be used to determine the target health state of the battery according to the predicted battery health states corresponding to each preset voltage range and the preset weight value corresponding to each preset voltage range.

Preferably, the device further comprises an alarm module for determining that the battery is abnormal and issuing an alarm signal when the target health status does not satisfy a preset condition.

Preferably, the device also includes a processing module for generating a measurement record including the target battery health status and generation time; receiving a battery health status query request issued by a user, the request including the request time; when the difference between the request time and the generation time of the measurement record does not exceed a preset time threshold, returning the target battery health status to the user.

Embodiment 4

Corresponding to the above method and device, an embodiment of the present application provides an electronic device, including:

One or more processors; and a memory associated with the one or more processors, the memory being used to store program instructions, the program instructions when read and executed by the one or more processors, performing the following operations:

According to preset sampling conditions, real-time operating parameters of the battery of the electric vehicle under preset driving conditions are collected;

According to the real-time operating parameters, obtaining target operating parameters of the electric vehicle within each preset voltage range;

Using the trained deep learning model, predicting the battery health status corresponding to each preset voltage range of the battery according to the target operating parameters;

The target battery health state of the battery is determined according to the battery health states corresponding to the battery in each preset voltage range.

4 exemplarily shows the architecture of the electronic device, which may include a processor 1510, a video display adapter 1511, a disk drive 1512, an input/output interface 1513, a network interface 1514, and a memory 1520. The processor 1510, the video display adapter 1511, the disk drive 1512, the input/output interface 1513, the network interface 1514, and the memory 1520 may be communicatively connected via a communication bus 1530.

Among them, the processor 1510 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solution provided in this application.

The memory 1520 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1520 can store an operating system 1521 for controlling the operation of the electronic device 1500, and a basic input and output system (BIOS) 1522 for controlling the low-level operation of the electronic device 1500. In addition, a web browser 1523, a data storage manager 1524, and an icon font processing system 1525, etc. can also be stored. The above-mentioned icon font processing system 1525 can be an application program that specifically implements the operations of the aforementioned steps in the embodiment of the present application. In short, when the technical solution provided by the present application is implemented by software or firmware, the relevant program code is stored in the memory 1520 and is called and executed by the processor 1510. The input/output interface 1513 is used to connect the input/output module to realize information input and output. The input/output/module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. Input devices may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and output devices may include a display, a speaker, a vibrator, an indicator light, etc.

The network interface 1514 is used to connect to a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

The bus 1530 comprises a pathway for transmitting information between the various components of the device (eg, the processor 1510, the video display adapter 1511, the disk drive 1512, the input/output interface 1513, the network interface 1514, and the memory 1520).

In addition, the electronic device 1500 can also obtain information on specific collection conditions from the virtual resource object collection condition information database 1541 for use in condition judgment, etc.

It should be noted that, although the above device only shows a processor 1510, a video display adapter 1511, a disk drive 1512, an input/output interface 1513, a network interface 1514, a memory 1520, a bus 1530, etc., in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include components necessary for implementing the solution of the present application, and does not necessarily include all the components shown in the figure.

It can be seen from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM/RAM, a disk, an optical disk, etc., including several instructions for enabling a computer device (which can be a personal computer, a cloud server, or a network device, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (8)

1. A method for predicting a battery health state, characterized in that the method comprises: According to preset sampling conditions, real-time operating parameters of the battery of the electric vehicle under preset driving conditions are collected; According to the real-time operating parameters, obtaining target operating parameters of the electric vehicle within each preset voltage range; Using the trained deep learning model, predicting the battery health status corresponding to each preset voltage range of the battery according to the target operating parameters; Determining a target health state of the battery according to the predicted battery health states corresponding to each preset voltage range and a preset weight value corresponding to each preset voltage range; The training process of the deep learning model includes: Acquiring a historical data set, the historical data set comprising measured historical operating parameters of a battery of the electric vehicle within a preset voltage range under the preset driving condition; According to a preset division rule, the historical data set is divided into a training data set and a test data set; Using the training data set to train an initial deep learning model; Using the test data set to test the trained initial deep learning model, when the test result meets the preset conditions, determining that the trained initial deep learning model is a trained deep learning model, and deploying the trained deep learning model to the cloud; The real-time operating parameters of the batteries of multiple electric vehicles under the preset driving conditions are transmitted to the trained deep learning model for training to obtain a final trained deep learning model. 2. The prediction method according to claim 1, characterized in that the real-time operating parameters include the real-time current, real-time voltage and real-time temperature of the battery; The step of obtaining the target operating parameters of the electric vehicle within each preset voltage range according to the real-time operating parameters includes: Obtaining the real-time current, real-time voltage and real-time temperature corresponding to the battery within each preset voltage range; Determine, according to the real-time current, real-time voltage and real-time temperature, the average current, average voltage, average resistance and average temperature corresponding to the battery within each of the preset voltage ranges; Determining, according to the real-time current, a total throughput of the battery corresponding to each of the preset voltage ranges; The target operating parameter is determined according to the total throughput, the average current, the average voltage, the average resistance, and the average temperature. 3. The prediction method according to claim 1 or 2, characterized in that the method comprises: When the target health status does not meet the preset conditions, it is determined that the battery is abnormal and an alarm signal is issued. 4. The prediction method according to claim 1 or 2, characterized in that the method comprises: generating a measurement record including the target health status and the time of generation; receiving a battery health status query request from a user, wherein the request includes a request time; When the difference between the request time and the generation time of the measurement record does not exceed a preset time threshold, the target health status is returned to the user. 5. A device for predicting battery health status, characterized in that the device comprises: A collection module, used to collect real-time operating parameters of the battery of the electric vehicle under preset driving conditions according to preset sampling conditions; An acquisition module, used for acquiring target operating parameters of the electric vehicle within each preset voltage range according to the real-time operating parameters; A prediction module, configured to predict the battery health status corresponding to each preset voltage range of the battery according to the target operating parameters by using a trained deep learning model; A judgment module, used to determine a target health state of the battery according to the predicted battery health states corresponding to each preset voltage range and a preset weight value corresponding to each preset voltage range; The training process of the deep learning model includes: Acquiring a historical data set, the historical data set comprising measured historical operating parameters of a battery of the electric vehicle within a preset voltage range under the preset driving condition; According to a preset division rule, the historical data set is divided into a training data set and a test data set; Using the training data set to train an initial deep learning model; Using the test data set to test the trained initial deep learning model, when the test result meets the preset conditions, determining that the trained initial deep learning model is a trained deep learning model; and deploying the trained deep learning model to the cloud; The real-time operating parameters of the batteries of multiple electric vehicles under the preset driving conditions are transmitted to the trained deep learning model for training to obtain a final trained deep learning model. 6. The prediction device according to claim 5 is characterized in that the real-time operating parameters include the real-time current, real-time voltage and real-time temperature of the battery, and the acquisition module can also be used to obtain the real-time current, real-time voltage and real-time temperature corresponding to the battery in each of the preset voltage ranges; determine the average current, average voltage, average resistance and average temperature corresponding to the battery in each of the preset voltage ranges according to the real-time current, real-time voltage and real-time temperature; determine the total throughput corresponding to the battery in each of the preset voltage ranges according to the real-time current; determine the target operating parameters according to the total throughput, the average current, the average voltage, the average resistance and the average temperature. 7. A computer-readable storage medium storing computer instructions, characterized in that when the computer instructions are executed on a processing component of a computer, the processing component is caused to execute the steps of any one of the methods of claims 1-4. 8. An electronic device, characterized in that the electronic device comprises: one or more processors; and a memory associated with the one or more processors, the memory being used to store program instructions, the program instructions when read and executed by the one or more processors performing the following operations: According to preset sampling conditions, real-time operating parameters of the battery of the electric vehicle under preset driving conditions are collected; According to the real-time operating parameters, obtaining target operating parameters of the electric vehicle within each preset voltage range; Using the trained deep learning model, predicting the battery health status corresponding to each preset voltage range of the battery according to the target operating parameters; Determining a target health state of the battery according to the predicted battery health states corresponding to each preset voltage range and a preset weight value corresponding to each preset voltage range; The training process of the deep learning model includes: Acquiring a historical data set, the historical data set comprising measured historical operating parameters of a battery of the electric vehicle within a preset voltage range under the preset driving condition; According to a preset division rule, the historical data set is divided into a training data set and a test data set; Using the training data set to train an initial deep learning model; Using the test data set to test the trained initial deep learning model, when the test result meets the preset conditions, determining that the trained initial deep learning model is a trained deep learning model; and deploying the trained deep learning model to the cloud; The real-time operating parameters of the batteries of multiple electric vehicles under the preset driving conditions are transmitted to the trained deep learning model for training to obtain a final trained deep learning model.