Battery state of charge prediction method and related device

Abstract

The embodiment of the invention provides a battery state-of-charge prediction method and a related device, and relates to the technical field of batteries, the method comprises the following steps: obtaining state data of a battery, the state data comprising a first voltage, a first current and a first expansion force when the battery works at the current moment; and predicting the state of charge of the battery according to the state data. Through the method, the accuracy of estimating the state of charge of the battery can be effectively improved.

Description

Technical Field

[0001] The present application relates to the field of battery technology, and in particular to a battery state of charge prediction method and related devices. Background Art

[0002] A battery's state of charge (SOC) refers to the ratio of its remaining capacity to its fully charged capacity, reflecting the battery's true state of charge. Accurately estimating the battery's SOC can assist users with relevant operations. For example, for new energy vehicles, accurately estimating the battery's SOC can aid in route planning.

[0003] In related technologies, the SOC of a battery can be estimated by using a discharge method, an internal resistance method, an open circuit voltage method, and the like. However, the accuracy of the SOC estimation using the above methods is relatively poor. Summary of the Invention

[0004] The embodiments of the present application provide a battery state of charge prediction method and related devices, which can effectively improve the accuracy of SOC estimation.

[0005] In a first aspect, an embodiment of the present application provides a battery state of charge prediction method, comprising:

[0006] Acquire battery status data, where the status data includes a first voltage, a first current, and a first expansion force of the battery when it is currently operating;

[0007] The state of charge of the battery is predicted based on the state data.

[0008] In some embodiments, predicting the state of charge of the battery based on the state data includes:

[0009] The state data is processed using a pre-built state of charge prediction model to obtain a predicted state of charge of the battery.

[0010] In some embodiments, the state of charge prediction model includes: a regression sub-model and a Kalman filter sub-model; the state data is processed using the pre-built state of charge prediction model to obtain the predicted state of charge of the battery, including:

[0011] Inputting the first voltage and the first current into the regression sub-model to obtain a first predicted expansion force output by the regression sub-model, wherein the regression sub-model is a model obtained by iteratively training an initial regression sub-model based on a training data set, wherein the training data set includes: multiple sets of state data collected during battery operation, each set of the state data including the second voltage, the second current, and the second expansion force of the battery;

[0012] The first predicted expansion force and the first expansion force are processed using the Kalman filter sub-model to obtain the predicted state of charge.

[0013] In some embodiments, processing the predicted expansion force and the expansion force using the Kalman filter sub-model to obtain the predicted state of charge includes:

[0014] Processing the first predicted expansion force and the first expansion force using a Kalman gain to obtain an observation value at a current moment;

[0015] Based on the state quantity predicted by the Kalman filter sub-model at the previous moment and the observation quantity, the state of charge predicted at the current moment is obtained; the state quantity predicted at the previous moment includes the state of charge predicted at the previous moment.

[0016] In some embodiments, after obtaining the predicted state of charge at the current moment, the method further includes:

[0017] The Kalman gain is updated according to the state of charge predicted at the current moment and the state quantity predicted at the previous moment.

[0018] In some embodiments, the training data set is a data set obtained by preprocessing the multiple sets of status data, and the preprocessing includes at least one of the following:

[0019] Normalization or standardization, data cleaning.

[0020] In a second aspect, an embodiment of the present application provides a battery state of charge prediction system, comprising:

[0021] a first sensor, configured to obtain battery status data, the status data including a first voltage, a first current, and a first expansion force of the battery during operation at a current moment;

[0022] The first prediction device is used to predict the state of charge of the battery according to the state data.

[0023] In a third aspect, an embodiment of the present application provides a method for predicting the state of charge of a vehicle battery, comprising:

[0024] Acquiring status data of the vehicle battery, the status data including voltage, current, and expansion force of the vehicle battery during operation at a current moment;

[0025] predicting a state of charge of the vehicle battery based on the state data;

[0026] A predicted state of charge of the vehicle battery is displayed.

[0027] In a fourth aspect, an embodiment of the present application provides a vehicle battery state of charge prediction system, comprising:

[0028] a second sensor for acquiring status data of the vehicle battery, the status data including voltage, current, and expansion force of the vehicle battery during operation at a current moment;

[0029] a second prediction device for predicting the state of charge of the vehicle battery based on the state data;

[0030] A display device is used to display the predicted state of charge of the vehicle battery.

[0031] In a fifth aspect, the present application provides an electronic device, comprising: a memory and a processor;

[0032] The memory is used to store computer instructions; the processor is used to execute the computer instructions stored in the memory to implement the method of any one of the first aspect or the third aspect.

[0033] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the method of any one of the first aspect or the third aspect.

[0034] In a fifth aspect, the present application provides a computer program product, comprising a computer program, which implements the method of any one of the first aspect or the third aspect when executed by a processor.

[0035] In a sixth aspect, the present application provides a vehicle, in which the vehicle battery state of charge prediction system as shown in the third aspect is provided.

[0036] The present application provides a battery state-of-charge prediction method and related apparatus. By acquiring battery status data, including the battery's current operating first voltage, first current, and first expansion force, the method predicts the battery's state of charge based on the status data. This method can effectively improve the accuracy of battery state-of-charge prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A schematic diagram of a scenario provided in an embodiment of the present application;

[0038] Figure 2 A schematic diagram of a battery state of charge prediction method provided in an embodiment of the present application Figure 1 ;

[0039] Figure 3 A schematic diagram of a process for training a regression sub-model provided in an embodiment of the present application;

[0040] Figure 4A schematic diagram of a battery status data acquisition device provided in an embodiment of the present application;

[0041] Figure 5 A schematic diagram of a battery state of charge prediction method provided in an embodiment of the present application Figure 2 ;

[0042] Figure 6 A schematic diagram of a battery state of charge prediction model provided in an embodiment of the present application;

[0043] Figure 7 A schematic diagram of the structure of a battery state of charge prediction system provided in an embodiment of the present application;

[0044] Figure 8 A flow chart of a method for predicting the state of charge of a vehicle battery provided in an embodiment of the present application;

[0045] Figure 9 A schematic diagram of the structure of a vehicle battery state of charge prediction system provided in an embodiment of the present application;

[0046] Figure 10 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0047] Figure 11 A schematic structural diagram of a vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0049] In the embodiments of the present application, words such as "first" and "second" are used to distinguish between identical or similar items with substantially the same functions and effects, and do not limit their order. Those skilled in the art will understand that words such as "first" and "second" do not limit the quantity or execution order, and words such as "first" and "second" do not necessarily mean different.

[0050] It should be noted that in the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described in this application as "exemplary" or "for example" should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0051] The battery's SOC reflects the battery's true state of charge. Accurately estimating the battery's SOC can assist users with relevant operations. For example, for new energy vehicles, accurately estimating the battery's SOC can help users plan routes.

[0052] Among the current traditional methods, the SOC of the battery can be estimated by using a discharge method, an internal resistance method, an open circuit voltage method, etc. However, the accuracy of the SOC estimation by the above methods is relatively poor.

[0053] In related technologies, there is also a method of predicting SOC by combining extended Kalman filtering and voltage method. However, this method essentially uses the SOC-OCV (open circuit voltage) curve of the battery cell. However, there is a long blank in the SOC-OCV curve of the battery cell, which makes it difficult to identify SOC from OCV and the accuracy is not high.

[0054] In view of this, an embodiment of the present application provides an SOC prediction method and related devices, which can effectively improve the accuracy of SOC prediction by collecting the expansion force of the voltage and current of the battery during operation, and inputting the expansion force of the voltage and current into a constructed SOC prediction model including a regression sub-model and a Kalman filter model to predict the SOC of the battery.

[0055] The following specific embodiments are used to describe in detail the technical solution of the present application and how the technical solution of the present application solves the above technical problems. The following specific embodiments can be implemented independently or in combination with each other. For the same or similar concepts or processes, some embodiments may not be described in detail.

[0056] Figure 1 This is a schematic diagram of an application scenario of an embodiment of the present application, such as Figure 1 As shown, it includes a battery 1, a sensor 2, a sensor 3 and a prediction device 4.

[0057] The sensor 2 is used to collect the voltage and current of the battery during operation. The battery voltage may refer to the terminal voltage during operation, i.e., the potential difference between the positive and negative electrodes of the battery when current flows through the circuit. The battery current may refer to the discharge current of the battery.

[0058] In some embodiments, the sensor 2 may include a voltage sensor and a current sensor, or may be a sensor capable of measuring current and voltage.

[0059] The sensor 3 is used to detect the expansion force of the battery 1 during operation. The expansion force generally refers to the mechanical stress generated by volume changes caused by internal chemical reactions during the battery's charge and discharge processes. For example, during charging, lithium ions embed into the electrode material, causing the electrode material to expand, while during discharge, lithium ions de-intercalate and contract. For example, the sensor 3 may be a thin-film sensor.

[0060] In some embodiments, the sensor 2 and the sensor 3 may be integrated into the battery 1 or deployed outside the battery 2 , which is not limited in this embodiment of the present application.

[0061] The prediction device 4 may be a platform with data analysis and processing capabilities. For example, when the battery 1 is a power battery of a new energy vehicle, the prediction device 4 may be a battery management system (BMS) of the new energy vehicle.

[0062] In some embodiments, the prediction device 4 predefines a trained SOC prediction model. When the prediction device 4 obtains the data collected by the sensors 2 and 3, it can use the SOC prediction model to process the obtained data to obtain the predicted battery SOC.

[0063] Below Figure 1 Based on the embodiment shown, Figure 1 The prediction device is the execution body, and the battery state of charge prediction method provided in the embodiment of the present application is described.

[0064] Figure 2 Schematic diagram of the process of the battery state of charge prediction method provided in the embodiment of the application Figure 1 ,like Figure 2 As shown, the steps include:

[0065] S201. Acquire battery status data, where the status data includes a first voltage, a first current, and a first expansion force of the battery when it is currently operating.

[0066] In some embodiments, as Figure 1As shown, when the battery is operating, sensor 2 and sensor 3 can collect the first current, first voltage, and first expansion force of battery 1 at each moment during operation in real time. Each moment can be a pre-set sampling time for battery 1 (for example, sampling the battery once every second), or can be determined based on the sampling frequency of sensor 2 and sensor 3. The present embodiment does not limit the process of battery sampling.

[0067] When the sensor 2 and the sensor 3 collect the status data of the battery at the current moment, the status data can be sent to the prediction device 4 .

[0068] S202: Predict the state of charge of the battery according to the state data.

[0069] In some embodiments, when the prediction device obtains the state data, it can use a pre-built state-of-charge prediction model for predicting the state of charge of the battery to process the state data to obtain the predicted state of charge of the battery at the current moment.

[0070] In some embodiments, the state of charge prediction model includes: a regression sub-model and a Kalman filter sub-model.

[0071] A regression model is a statistical model used to study the relationship between dependent and independent variables. It describes and predicts the changing trend of the dependent variable with the independent variable by constructing a mathematical model.

[0072] Among them, the regression sub-model described in the embodiment of the present application can adopt a support vector machine (SVM) model, a gradient boosting regression model, a decision tree regression model, etc. The embodiment of the present application does not limit the type of the regression sub-model.

[0073] The Kalman filter is a recursive algorithm used to estimate the state of a dynamic system. It uses observational data as input to optimally estimate the state of the system. Because the observational data includes the effects of noise and interference in the system, optimal estimation can also be viewed as a filtering process.

[0074] The Kalman filter sub-model in the embodiment of the present application may be a data model constructed based on Kalman filtering. Optionally, since there may be a nonlinear relationship between the state of charge and the state data, the Kalman filter sub-model in the embodiment of the present application may be a data model constructed based on extended Kalman filtering.

[0075] In some embodiments, the regression sub-model included in the state of charge prediction model can be a model obtained by training an initial regression sub-model based on a training data set, wherein the training data set may include multiple sets of status data collected by the battery during operation, and any set of the status data includes the second voltage, second current, and second expansion force of the battery.

[0076] When the prediction device obtains the current state data of the battery, it can input the state data into the state of charge prediction model to obtain the currently predicted state of charge of the battery.

[0077] The battery state of charge prediction method provided in the embodiment of the present application collects the voltage, current and expansion force of the battery, and processes the above data using a pre-built state of charge prediction model to obtain a predicted state of charge, which can effectively improve the accuracy of the battery state of charge prediction.

[0078] exist Figure 2 Based on the illustrated embodiment, the specific process of how the embodiment of the present application predicts the battery state of charge is described below.

[0079] For ease of understanding, the process of training the regression model based on the training data set is first described. The execution subject of the embodiment of the present application can be a data processing platform with model training capabilities.

[0080] Figure 3 A flow chart of a regression model training process provided in an embodiment of the present application is as follows: Figure 3 Shown, including:

[0081] S301: Input the second voltage and the second current in each set of state data included in the training data set into the initial regression sub-model to obtain a second predicted expansion force.

[0082] In some embodiments, the training data set includes multiple sets of state data, and each set of state data includes the second voltage, the second current, and the second expansion force of the battery.

[0083] For example, Figure 4 An embodiment of the present application provides a device for obtaining the battery status data, which includes a test fixture (consisting of three plywood plates), an expansion force sensor, and a current and voltage sensor.

[0084] Three clamping plates are fastened with bolts to clamp the expansion force sensor and the battery cell, respectively. A current and voltage sensor is connected to the battery. The battery is charged or discharged. The current and voltage sensors record the second current and second voltage of the battery during the discharge or charge process, and the expansion force sensor records the second expansion force during the discharge or charge process, thereby obtaining the training dataset.

[0085] When the data processing platform obtains each set of status data, the second voltage and second current of the battery in each set of status data can be input into the initial regression sub-model to obtain the second predicted expansion force corresponding to each set of status data output by the initial regression sub-model.

[0086] Optionally, in order to further improve the training effect of the initial regression sub-model, when the training data set is obtained, the training data set may be preprocessed to improve the training effect.

[0087] For example, the state data of each group in the training data set is normalized or standardized to avoid the influence of different data dimensions.

[0088] For example, data cleaning is performed on the status data of each group in the training data set, wherein the data cleaning includes processing missing data, processing outliers, deduplication processing, etc. Data cleaning can effectively improve the accuracy of the training data set and reduce the impact of abnormal data.

[0089] S302: Obtain a loss function value according to the second predicted expansion force and the second expansion force corresponding to each set of state data.

[0090] In some embodiments, a mean-square error (MSE) function may be used as the loss function.

[0091] For example, when the second predicted expansion force corresponding to each set of state data is obtained, the corresponding loss function value can be obtained in the following manner:

[0092]

[0093] Wherein, n is the number of groups of state data, F1 is the predicted second expansion force, and F2 is the second expansion force.

[0094] It should be understood that the data processing platform can also use other loss functions to obtain the corresponding loss function value. For example, the embodiment of the present application does not limit the type of loss function.

[0095] S303: If the loss function value is not within a preset range, the parameters in the regression sub-model are updated.

[0096] In some embodiments, when the data processing platform obtains the loss function value, it can determine whether the loss function value is within the preset loss function value range. If it is, it is determined that the current regression sub-model meets the requirements. If it is not within the preset loss function value range, the parameters in the regression sub-model can be updated according to pre-defined parameter adjustment rules.

[0097] S304: Training the initial regression sub-model after parameter update according to the data set to obtain a new loss function value.

[0098] S305. Iterate the process of obtaining a new loss function value until a preset number of iterations is reached or the new loss function value is within a preset range.

[0099] After updating the parameters of the regression sub-model, the data processing platform can re-input the dataset into the updated regression sub-model to obtain a new loss function and determine whether the new loss function is within a preset range. If so, model training ends. If not, the parameters of the regression sub-model are updated again, and the process of obtaining the loss function value based on the regression sub-model with updated parameters is repeated. The above process of obtaining the loss function value and updating the parameters of the regression sub-model is iteratively executed until the preset number of iterations is reached or the new loss function value is within the preset range, completing the training of the regression sub-model.

[0100] Optionally, to further improve the training effect of the model, when the number of iterations reaches a preset number of iterations, if the obtained loss function value is still not within the preset range, new training data can be added for training.

[0101] In some embodiments, when training the regression sub-model, the training data set can be divided into a training set and a test set. When a converged model cannot be trained based on the training set, the regression sub-model can be further trained using cross-validation to improve the training effect of the model.

[0102] The training method of the regression sub-model provided in the embodiment of the present application trains the regression sub-model by collecting the state data of the battery during the working process, so that the regression sub-model can accurately predict the expansion force corresponding to the battery based on the input current and voltage data.

[0103] Based on the above embodiments, Figure 5 The specific process of how to predict the battery state of charge in the embodiment of the present application is described.

[0104] Figure 5 A flow chart of a method for predicting the state of charge of a battery provided in an embodiment of the present application is shown in FIG. Figure 5Shown, including:

[0105] S501: Input the first voltage and the first current into the regression sub-model to obtain a first predicted expansion force output by the regression sub-model.

[0106] For example, Figure 6 As shown, the prediction device can input the obtained first voltage and the first current into a Figure 5 In the regression sub-model trained in the illustrated embodiment, a first predicted expansion force output by the regression sub-model is obtained.

[0107] S502: Use the Kalman filter sub-model to process the first predicted expansion force and the first expansion force to obtain the predicted state of charge.

[0108] In some embodiments, after the prediction device obtains the first predicted expansion force, the first predicted expansion force and the first expansion force input value can be input into the Kalman filter model, and the state value can be updated and recursively calculated through the Kalman filter model to obtain the predicted state of charge of the battery at the current moment.

[0109] In some embodiments, the specific process of updating and recursively performing the state value through the Kalman filter model to obtain the predicted state of charge of the battery at the current moment can be as follows:

[0110] Exemplarily, the first predicted expansion force and the first expansion force are processed using the Kalman gain to obtain the observation quantity at the current moment; based on the state quantity predicted by the Kalman filter sub-model at the previous moment and the observation quantity, the charge state predicted at the current moment is obtained; the state quantity predicted at the previous moment includes the charge state predicted at the previous moment.

[0111] Among them, the predicted state of charge can satisfy the following formula:

[0112] X upd =X pre +K*(F ob -F pre )

[0113] Among them, X upd is the predicted battery state at the current moment, X pre is the state of the battery at the last moment, K is the Kalman gain, F ob is the first expansion force, F pre This is the first predicted expansion force output by the regression sub-model.

[0114] Among them, the state quantity X is a 2*1 order matrix composed of the charge state and the expansion force, K*(F ob -F pre) is the observed value at the current moment obtained based on the expansion force.

[0115] At the initial moment, X pre The state of charge included in the above equation may be the state of charge calculated based on the current and voltage at the initial moment of acquisition (for example, using the ampere-hour integration method), X pre The expansion force included in is the actual measured expansion force.

[0116] The Kalman gain can satisfy the following formula:

[0117] K=P_pre*C , *(C*P_pre*C , +R) -1

[0118] Among them, P_pre is the covariance matrix of the previous moment, C is the state transfer matrix, C , is the transposed matrix of the state transfer matrix, and R is the noise variance matrix.

[0119] At the initial moment, the noise variance matrix R can be determined based on the collected state data according to prior knowledge, and the covariance matrix P and the state transfer matrix C can be set based on prior knowledge.

[0120] In some embodiments, each time the state of charge is estimated, the Kalman gain needs to be updated based on the estimation result (prediction result) at the previous moment and the prediction result at the current moment to ensure the accuracy of the next estimation.

[0121] In some embodiments, the Kalman gain may be updated by updating the covariance matrix P and the state transition matrix C simultaneously.

[0122] In some embodiments, the state transition matrix C may be updated as follows:

[0123] Perform a 6th-order Taylor expansion on the state transfer matrix C and retain only the linear terms to obtain the state equation of the system as follows:

[0124] C = [C1-1];

[0125] C1=a*SOC_pre^6+b*SOC_pre^5+c*SOC_pre^4+d*SOC_pre^3+e*SOC_pr e^2+f*SOC_pre+g

[0126] Among them, ag is the parameter to be identified, which can be obtained based on the measured state data, and SOC_pre is the state of charge predicted at the previous moment.

[0127] The covariance matrix can be updated as follows:

[0128] P_update = P_pre - K*C*P_pre

[0129] Among them, P_update is the updated covariance matrix, P_pre is the covariance matrix of the previous round, K is the Kalman gain of the previous round, and C is the state transfer matrix of the previous round.

[0130] As can be seen from the above formula, the Kalman filter equation operates in a recursive "prediction-correction" process, meaning that each is derived from the other. For example, the formula for predicting the state of charge (SOC) uses the previous filtered value to derive the current predicted value, which in turn is used for the next prediction. Therefore, the Kalman filter does not require the storage of any observation data, which significantly improves prediction speed.

[0131] In summary, the battery state of charge prediction method provided in the embodiment of the present application, through the joint action of the trained regression sub-model and the Kalman filter model, iteratively calculates the collected battery state data, and can achieve accurate estimation of the battery state of charge.

[0132] Based on the above embodiments, an embodiment of the present application further provides a battery state of charge estimation system.

[0133] Figure 7 A structural diagram of a battery state of charge estimation system 70 provided in an embodiment of the present application is shown as follows: Figure 7 Shown, including:

[0134] The first sensor 701 is used to obtain status data of the battery, where the status data includes a first voltage, a first current, and a first expansion force of the battery during operation at a current moment.

[0135] Optionally, the first sensor 701 may include: Figure 1 The sensor 2 shown is used to collect the first voltage and the first current of the battery, and the sensor 3 is used to collect the first expansion force.

[0136] The first prediction device 702 is configured to predict the state of charge of the battery according to the state data.

[0137] In some embodiments, the first prediction device 702 is further configured to process the state data using a pre-built state of charge prediction model to obtain a predicted state of charge of the battery.

[0138] In some embodiments, the state of charge prediction model includes: a regression sub-model and a Kalman filter sub-model. The first prediction device 702 is further used to input the first voltage and the first current into the regression sub-model to obtain a first predicted expansion force output by the regression sub-model. The regression sub-model is a model obtained by iteratively training the initial regression sub-model based on a training data set. The training data set includes: multiple groups of status data collected by the battery during operation, any group of the status data includes the second voltage, second current and second expansion force of the battery; the first predicted expansion force and the first expansion force are processed using the Kalman filter sub-model to obtain the predicted state of charge.

[0139] In some embodiments, the first prediction device 702 is further used to process the first predicted expansion force and the first expansion force using the Kalman gain to obtain the observation quantity at the current moment; based on the state quantity predicted by the Kalman filter sub-model at the previous moment, and the observation quantity, the charge state predicted at the current moment is obtained; the state quantity predicted at the previous moment includes the charge state predicted at the previous moment.

[0140] In some embodiments, the first prediction device 702 is further configured to update the Kalman gain according to the state of charge predicted at the current moment and the state quantity predicted at the previous moment.

[0141] The battery state of charge estimation system provided in the embodiment of the present application can execute the battery state of charge prediction method provided in any of the above embodiments, and its principles and technical effects are similar, which will not be repeated here.

[0142] In some embodiments, the present application also provides a method for predicting the state of charge of a vehicle battery.

[0143] Figure 8 This is a flow chart of a method for predicting the state of charge of a vehicle battery provided in an embodiment of the present application. The execution subject of the embodiment of the present application may be the battery management system of the vehicle, the control system of the vehicle, etc., and the embodiment of the present application does not limit this. Figure 8 As shown, the steps include:

[0144] S801. Acquire status data of the vehicle battery, where the status data includes voltage, current, and expansion force of the vehicle battery during operation at a current moment.

[0145] S802: Predict the state of charge of the vehicle battery according to the state data.

[0146] The implementation method of steps S801 and S802 in the embodiment of the present application is the same as Figure 2-Figure 6The specific implementation methods of the corresponding steps in are similar and will not be repeated here.

[0147] S803: Display the predicted state of charge of the vehicle battery.

[0148] In some embodiments, after predicting the state of charge of the vehicle battery, the vehicle's battery management system (for example) can display the predicted state of charge of the vehicle battery through the vehicle's display device (for example, the vehicle's central control screen) so as to understand the vehicle's current state of charge.

[0149] The vehicle battery state of charge prediction method provided in the embodiment of the present application can quickly and accurately predict the current state of charge of the vehicle battery to help users perform operations such as route planning, thereby avoiding deviations in charge state estimation that affect the user's car experience.

[0150] An embodiment of the present application also provides a vehicle battery state of charge prediction system.

[0151] Figure 9 The structural diagram of a vehicle battery state of charge prediction system 90 provided in this application is as follows: Figure 9 Shown, including:

[0152] The second sensor 901 is used to obtain status data of the vehicle battery, where the status data includes the voltage, current and expansion force of the vehicle battery when it is working at the current moment.

[0153] The second sensor 901 may be a sensor deployed in a vehicle battery for collecting the voltage and current of the battery, and a sensor for collecting the expansion force.

[0154] The second prediction device 902 is used to predict the state of charge of the vehicle battery based on the state data.

[0155] The second prediction device 902 may be a battery management system of the vehicle, a control system of the vehicle, etc.

[0156] The display device 903 is used to display the predicted state of charge of the vehicle battery.

[0157] The display device 903 may be a central control center of a vehicle, etc.

[0158] The vehicle battery state of charge prediction system provided in the embodiment of the present application can execute the vehicle battery state of charge prediction method provided in the above embodiment. Its principles and technical effects are similar and will not be repeated here.

[0159] An embodiment of the present application also provides an electronic device.

[0160] Figure 10 This is a structural diagram of the electronic device 100 provided in an embodiment of the present application, as shown in FIG. Figure 10 As shown, it includes: a transceiver 1001, a processor 1002, and a memory 1003.

[0161] The processor 1002 executes the computer-executable instructions stored in the memory, so that the processor 1002 implements the solution in the above embodiment. The processor 1002 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0162] The memory 1003 is connected to the processor 1002 via a system bus and communicates with the processor 1002. The memory 1003 is used to store computer program instructions.

[0163] The transceiver 1001 may be configured to obtain battery status data and / or output a predicted battery state of charge.

[0164] Optionally, the electronic device 100 may further include a communication interface to communicate and interact with an external or internal device through the communication interface. The external device may be, for example, a client (e.g., a mobile phone, a tablet). In a specific implementation, if the communication interface, the memory 1003, and the processor 1002 are implemented independently, the communication interface, the memory 1003, and the processor 1002 may be interconnected via a bus and communicate with each other.

[0165] The system bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, among others. The system bus can be divided into an address bus, a data bus, a control bus, and so on. For ease of illustration, the figure shows only one thick line, but this does not imply that there is only one bus or only one type of bus. Transceivers are used to enable communication between the database access device and other computers (e.g., clients, read-write libraries, and read-only libraries). Memory may include random access memory (RAM) and non-volatile memory.

[0166] Optionally, in a specific implementation, if the communication interface, memory 1003 and processor 1002 are integrated on a chip, the communication interface, memory 1003 and processor 1002 can complete communication through an internal interface.

[0167] An embodiment of the present application also provides a vehicle.

[0168] Figure 11 A schematic diagram of the structure of a vehicle is provided for the embodiment of the present application, such as Figure 11 As shown, the vehicle is provided with the vehicle battery state of charge prediction system described in any of the aforementioned embodiments.

[0169] In an embodiment of the present application, a computer-readable storage medium is further provided, on which a computer program is stored. When the computer program is executed by a processor, the technical solution of the above-mentioned vehicle battery state of charge prediction method or the battery state of charge prediction method embodiment is implemented. The implementation principle and technical effect are similar and will not be repeated here.

[0170] In one possible implementation, a computer-readable medium may include random access memory (RAM), read-only memory (ROM), compact disc read-only memory (CD-ROM) or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium designed to carry or store the desired program code in the form of instructions or data structures and accessible by a computer. Moreover, any connection is appropriately referred to as a computer-readable medium. For example, if a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL) or wireless technologies (such as infrared, radio and microwave) are used to transmit software from a website, server or other remote source, the coaxial cable, fiber optic cable, twisted pair, DSL or wireless technologies such as infrared, radio and microwave are included in the definition of medium. Disk and disc as used herein include optical disc, laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc, where disks typically reproduce data magnetically, while optical discs reproduce data optically using lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0171] A computer program product is also provided in an embodiment of the present application, including a computer program. When the computer program is executed by a processor, it implements the technical solution of the above-mentioned vehicle battery state of charge prediction method or battery state of charge prediction method embodiment. Its implementation principle and technical effects are similar and will not be repeated here.

[0172] In the specific implementation of the above-mentioned terminal device or server, it should be understood that the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of the present application can be directly implemented as a hardware processor, or can be implemented by a combination of hardware and software modules in the processor.

[0173] Those skilled in the art will appreciate that all or part of the steps of any of the above method embodiments may be accomplished by hardware associated with program instructions. The aforementioned program may be stored in a computer-readable storage medium, and when the program is executed, all or part of the steps of the above method embodiments are executed.

[0174] If the technical solution of the present application is implemented in the form of software and sold or used as a product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the technical solution of the present application can be embodied in the form of a software product, and the computer software product is stored in a storage medium and includes a computer program or several instructions. The computer software product enables a computer device (which can be a personal computer, server, network device or similar electronic device) to perform all or part of the steps of the method described in the embodiment of the present application.

[0175] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all optional embodiments, and the actions and modules involved are not necessarily required by this application.

[0176] It should be further noted that, although the various steps in the flowchart are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps may be performed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily performed at the same time, but may be performed at different times. The execution order of these sub-steps or stages is not necessarily to be performed in sequence, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0177] It should be understood that the above-described device embodiments are merely illustrative, and the device of the present application may also be implemented in other ways. For example, the division of units / modules in the above-described embodiments is merely a logical functional division, and actual implementations may employ other division methods. For example, multiple units, modules, or components may be combined or integrated into another system, or some features may be omitted or not implemented.

[0178] In addition, unless otherwise specified, the functional units / modules in the various embodiments of the present application may be integrated into a single unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The aforementioned integrated units / modules may be implemented in the form of hardware or software program modules.

[0179] If the integrated unit / module is implemented in hardware, the hardware may be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. Unless otherwise specified, the processor may be any appropriate hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC. Unless otherwise specified, the storage unit may be any appropriate magnetic storage medium or magneto-optical storage medium, such as resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), hybrid memory cube (HMC), etc.

[0180] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes a number of instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0181] In the above embodiments, the description of each embodiment has its own emphasis. For parts not described in detail in a particular embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined in any way. To keep the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0182] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for predicting battery state of charge, characterized in that: include: Acquire battery status data, where the status data includes a first voltage, a first current, and a first expansion force of the battery when it is currently operating; The state of charge of the battery is predicted based on the state data.

2. The method according to claim 1, characterized in that The predicting the state of charge of the battery according to the state data includes: The state data is processed using a pre-built state of charge prediction model to obtain a predicted state of charge of the battery.

3. The method according to claim 2, characterized in that The state of charge prediction model includes: a regression sub-model and a Kalman filter sub-model; the state data is processed using the pre-built state of charge prediction model to obtain the predicted state of charge of the battery, including: Inputting the first voltage and the first current into the regression sub-model to obtain a first predicted expansion force output by the regression sub-model, wherein the regression sub-model is a model obtained by iteratively training an initial regression sub-model based on a training data set, wherein the training data set includes: multiple sets of state data collected during battery operation, each set of the state data including the second voltage, the second current, and the second expansion force of the battery; The first predicted expansion force and the first expansion force are processed using the Kalman filter sub-model to obtain the predicted state of charge.

4. The method according to claim 3, characterized in that The using the Kalman filter sub-model to process the predicted expansion force and the expansion force to obtain the predicted state of charge includes: Processing the first predicted expansion force and the first expansion force using a Kalman gain to obtain an observation value at a current moment; Based on the state quantity predicted by the Kalman filter sub-model at the previous moment and the observation quantity, the state of charge predicted at the current moment is obtained; the state quantity predicted at the previous moment includes the state of charge predicted at the previous moment.

5. The method according to claim 4, characterized in that After obtaining the predicted state of charge at the current moment, the method further includes: The Kalman gain is updated according to the state of charge predicted at the current moment and the state quantity predicted at the previous moment.

6. The method according to claim 3, characterized in that The training data set is a data set obtained by preprocessing the multiple sets of status data, wherein the preprocessing includes at least one of the following: Normalization or standardization, data cleaning.

7. A battery state of charge prediction system, characterized in that: include: a first sensor, configured to obtain battery status data, the status data including a first voltage, a first current, and a first expansion force of the battery during operation at a current moment; The first prediction device is used to predict the state of charge of the battery according to the state data.

8. A method for predicting the state of charge of a vehicle battery, characterized in that: include: Acquiring status data of the vehicle battery, the status data including voltage, current, and expansion force of the vehicle battery during operation at a current moment; predicting a state of charge of the vehicle battery based on the state data; A predicted state of charge of the vehicle battery is displayed.

9. A vehicle battery state of charge prediction system, characterized in that: include: a second sensor for acquiring status data of the vehicle battery, the status data including voltage, current, and expansion force of the vehicle battery during operation at a current moment; a second prediction device for predicting the state of charge of the vehicle battery based on the state data; A display device is used to display the predicted state of charge of the vehicle battery.

10. An electronic device, characterized in that: The electronic device includes: a processor, a transceiver, and a memory; the processor is communicatively connected to the transceiver and the memory respectively; The memory stores computer-executable instructions; The transceiver communicates and interacts with an external device; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 6 or 8.

11. A vehicle, characterized in that: The vehicle is provided with the vehicle battery state of charge prediction system according to claim 9.

12. A computer-readable storage medium, characterized in that A computer program is stored thereon, and the computer program is executed by a processor to implement the method according to any one of claims 1 to 6 or 8.

13. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to claim 1-6 or 8 when the computer program is executed by a controller.

Images