Method, device, equipment, storage medium and product for determining range of vehicle

Abstract

The application discloses a kind of vehicle's endurance mileage determination method, device, equipment, storage medium and product, belong to artificial intelligence technical field.The method includes: determine the first charge-discharge frequency of current battery included in vehicle;Based on the first charge-discharge frequency, determine the first charge-discharge frequency interval to which the first charge-discharge frequency belongs;Determine the first mileage prediction model corresponding to the first charge-discharge frequency interval, and the first mileage prediction model is used to predict the endurance mileage of battery in the first charge-discharge frequency interval;Get the first voltage, the first current, the first temperature, the first state of charge SOC, the first battery state SOH of current battery and the first driving mode of current vehicle;Based on the first voltage, the first current, the first temperature, the first SOC, the first SOH of current battery and the first driving mode of current vehicle, determine the endurance mileage of vehicle by the first mileage prediction model.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and in particular to a method and device for determining the range of a vehicle, a storage medium, and a product. BACKGROUND

[0002] For an electric vehicle, the range of the vehicle is a data that drivers care about very much. An accurate range can help drivers accurately determine when to charge, thereby greatly alleviating the anxiety of drivers about the range. Moreover, an accurate range not only improves the trust of drivers in the vehicle, but also improves the service life of the battery of the vehicle. Therefore, how to accurately calculate the range of the vehicle is an urgent problem to be solved. SUMMARY

[0003] Embodiments of the present application provide a method and device for determining the range of a vehicle, a storage medium, and a product. The technical solutions are as follows:

[0004] In one aspect, a method for determining the range of a vehicle is provided, and the method comprises:

[0005] determining the current first number of charge and discharge of a battery included in the vehicle;

[0006] based on the first number of charge and discharge, determining a first number of charge and discharge interval to which the first number of charge and discharge belongs;

[0007] determining a first mileage prediction model corresponding to the first number of charge and discharge interval, the first mileage prediction model being used to predict the range of the battery with the number of charge and discharge in the first number of charge and discharge interval;

[0008] obtaining the current first voltage, first current, first temperature, first state of charge (SOC), first state of health (SOH) of the battery, and the current first driving mode of the vehicle;

[0009] based on the current first voltage, first current, first temperature, first SOC, first SOH of the battery, and the current first driving mode of the vehicle, determining the range of the vehicle through the first mileage prediction model.

[0010] In one possible implementation, the method further comprises:

[0011] determine a first sample data set based on the first charge-discharge frequency interval, the first sample data set including first sample data of a first sample vehicle and label information of the first sample data, the first sample vehicle having a charge-discharge frequency in the first charge-discharge frequency interval, and the first sample data of the first sample vehicle including voltage, current, temperature, SOC, SOH of a battery included in the first sample vehicle, and driving mode of the first sample vehicle, the label information of the first sample data being real range of the first sample vehicle;

[0012] determine a predicted range of the first sample vehicle based on the first sample data set and an initial first range prediction model, the first range prediction model including an input layer, a plurality of hidden layers, and an output layer connected in sequence;

[0013] determine a loss function value of the first range prediction model based on the real range and the predicted range of the first sample vehicle, the loss function value representing a difference between the real range and the predicted range of the first sample vehicle;

[0014] in a case where the loss function value is less than a loss function threshold, the training is ended to obtain the first range prediction model;

[0015] in a case where the loss function value is not less than the loss function threshold, update feature weights and bias quantities of the plurality of hidden layers based on the loss function value, and then determine the predicted range of the first sample vehicle based on the first sample data set and the first range prediction model until the loss function value of the first range prediction model is less than the loss function threshold, at which time the training is ended to obtain the first range prediction model.

[0016] In another possible implementation,

[0017] The determining of the loss function value of the first range prediction model based on the real range and the predicted range of the first sample vehicle includes:

[0018] determine a first sample number of the first sample data set;

[0019] determine the loss function value of the first range prediction model based on the first sample number, the real range and the predicted range of the first sample vehicle, and the following formula one:

[0020] Formula one:

[0021] wherein L represents the loss function value, N represents the first sample number, i represents a serial number of the first sample vehicle, denotes a predicted range of the i th first sample vehicle, y i denotes a real range of the i th first sample vehicle.

[0022] In another possible implementation, the updating, based on the loss function value, of the feature weight and the bias quantity of the plurality of hidden layers comprises:

[0023] For the j th hidden layer, determining a partial derivative of the loss function with respect to the feature weight of the j th hidden layer to obtain a first partial derivative;

[0024] determining a partial derivative of the loss function with respect to the bias quantity of the j th hidden layer to obtain a second partial derivative;

[0025] updating, based on the first partial derivative and the second partial derivative, the feature weight and the bias quantity of the j th hidden layer by the following Formula Two:

[0026] Formula Two:

[0027] wherein j represents a serial number of a hidden layer, denotes an updated feature weight of the j th hidden layer, denotes a feature weight of the j th hidden layer before being updated, and a denotes a learning rate, denotes the first partial derivative, denotes an updated bias value of the j th hidden layer, denotes a bias value of the j th hidden layer before being updated, denotes the second partial derivative.

[0028] In another possible implementation, the method further comprises:

[0029] when the current second charge-discharge frequency of the battery is greater than the maximum value of the first charge-discharge frequency interval, determining a second charge-discharge frequency interval to which the second charge-discharge frequency belongs;

[0030] based on the second charge-discharge frequency interval, determining a second sample data set, the second sample data set comprising second sample data of a second sample vehicle and label information of the second sample data, the charge-discharge frequency of the second sample vehicle being in the second charge-discharge frequency interval, and the second sample data of the second sample vehicle comprising voltage, current, temperature, SOC, SOH of a battery included in the second sample vehicle and a driving mode of the second sample vehicle, the label information of the second sample data being a real range of the second sample vehicle;

[0031] based on the second sample data set, training a second range prediction model, the second range prediction model being used to predict a range of a battery with a charge-discharge frequency in the second charge-discharge frequency interval.

[0032] obtain a second current voltage, a second current, a second temperature, a second SOC, a second SOH of the battery and a second current driving mode of the vehicle;

[0033] determine the cruising range of the vehicle by the second range prediction model based on the second current voltage, the second current, the second temperature, the second SOC, the second SOH of the battery and the second current driving mode of the vehicle.

[0034] In another possible implementation, the determining the cruising range of the vehicle by the first range prediction model based on the first current voltage, the first current, the first temperature, the first SOC, the first SOH of the battery and the first current driving mode of the vehicle comprises:

[0035] inputting the first current voltage, the first current, the first temperature, the first SOC, the first SOH of the battery and the first current driving mode of the vehicle into the first range prediction model to output a first predicted SOC of the vehicle;

[0036] determining the cruising range of the vehicle based on the first predicted SOC and a theoretical cruising range of the vehicle.

[0037] In another aspect, a cruising range determination apparatus of a vehicle is provided, and the apparatus comprises:

[0038] a first determination module configured to determine a first number of times of charging and discharging of a battery currently included in the vehicle;

[0039] a second determination module configured to determine a first charging and discharging interval to which the first number of times of charging and discharging belongs based on the first number of times of charging and discharging;

[0040] a third determination module configured to determine a first range prediction model corresponding to the first charging and discharging interval, the first range prediction model being used to predict a cruising range of the battery with the number of times of charging and discharging in the first charging and discharging interval;

[0041] a first obtaining module configured to obtain a first current voltage, a first current, a first temperature, a first state of charge (SOC) and a first state of health (SOH) of the battery and a first current driving mode of the vehicle;

[0042] a fourth determination module configured to determine the cruising range of the vehicle by the first range prediction model based on the first current voltage, the first current, the first temperature, the first SOC, the first SOH of the battery and the first current driving mode of the vehicle.

[0043] In a possible implementation, the apparatus further comprises:

[0044] The fifth determining module is configured to determine a first sample data set based on the first charge-discharge frequency interval, the first sample data set including first sample data of a first sample vehicle and label information of the first sample data, the first sample vehicle having a charge-discharge frequency in the first charge-discharge frequency interval, and the first sample data of the first sample vehicle including voltage, current, temperature, SOC, SOH of a battery included in the first sample vehicle, and a driving mode of the first sample vehicle, the label information of the first sample data being a real range of the first sample vehicle;

[0045] The sixth determining module is configured to determine a predicted range of the first sample vehicle by an initial first range prediction model based on the first sample data set, the first range prediction model including an input layer, a plurality of hidden layers, and an output layer connected in sequence.

[0046] The seventh determining module is configured to determine a loss function value of the first range prediction model based on the real range and the predicted range of the first sample vehicle, the loss function value being used to represent a difference between the real range and the predicted range of the first sample vehicle.

[0047] The first training module is configured to train until the first range prediction model is obtained in a case where the loss function value is less than a loss function threshold.

[0048] The updating module is configured to, in a case where the loss function value is not less than the loss function threshold, update feature weights and bias amounts of the plurality of hidden layers based on the loss function value, and then determine the predicted range of the first sample vehicle by the first range prediction model based on the first sample data set until the loss function value of the first range prediction model is less than the loss function threshold, at which time the training is ended to obtain the first range prediction model.

[0049] In another possible implementation, the seventh determining module is configured to determine a first sample number of the first sample data set, and determine the loss function value of the first range prediction model by Formula One based on the first sample number, the real range and the predicted range of the first sample vehicle.

[0050] Formula One:

[0051] wherein L represents the loss function value, N represents the first sample number, i represents a serial number of the first sample vehicle, yi represents the predicted range of the i-th first sample vehicle, yi represents the real range of the i-th first sample vehicle. i ​​

[0052] In another possible implementation, the updating module is configured to, for the jth hidden layer, determine a partial derivative of the loss function with respect to a feature weight of the jth hidden layer to obtain a first partial derivative; determine a partial derivative of the loss function with respect to a bias of the jth hidden layer to obtain a second partial derivative; and update the feature weight and the bias of the jth hidden layer based on the first partial derivative and the second partial derivative according to the following Formula Two.

[0053] Formula Two:

[0054] wherein j represents a serial number of a hidden layer, represents an updated feature weight of the jth hidden layer, represents an updated feature weight of the jth hidden layer, and a represents a learning rate, represents the first partial derivative, represents an updated bias of the jth hidden layer, represents an updated bias of the jth hidden layer, represents the second partial derivative.

[0055] In another possible implementation, the apparatus further includes:

[0056] An eighth determining module is configured to determine a second charge-discharge frequency interval to which a current second charge-discharge frequency of the battery belongs, when the current second charge-discharge frequency of the battery is greater than a maximum value of the first charge-discharge frequency interval.

[0057] A ninth determining module is configured to determine a second sample data set based on the second charge-discharge frequency interval, the second sample data set including second sample data of a second sample vehicle and label information of the second sample data, the charge-discharge frequency of the second sample vehicle being in the second charge-discharge frequency interval, and the second sample data of the second sample vehicle including voltage, current, temperature, SOC, SOH of a battery included in the second sample vehicle and a driving mode of the second sample vehicle, the label information of the second sample data being a real range of the second sample vehicle.

[0058] A second training module is configured to train a second range prediction model based on the second sample data set, the second range prediction model being configured to predict a range of a battery with a charge-discharge frequency in the second charge-discharge frequency interval.

[0059] A second obtaining module is configured to obtain a current second voltage, a current second current, a current second temperature, a current second SOC, a current second SOH of the battery, and a current second driving mode of the vehicle.

[0060] The tenth determining module is configured to determine the cruising range of the vehicle by the second mileage prediction model based on the current second voltage, second current, second temperature, second SOC, second SOH of the battery, and the current second driving mode of the vehicle.

[0061] In another possible implementation, the fourth determining module is configured to input the voltage, current, temperature, SOC, SOH of the battery, and the current driving mode of the vehicle into the first mileage prediction model to output the predicted SOC of the vehicle; and determine the cruising range of the vehicle based on the predicted SOC and the theoretical cruising range of the vehicle.

[0062] In another aspect, a computer device is provided, which includes a processor and a memory, and the memory stores at least one program code, which is loaded and executed by the processor to implement the above-mentioned method for determining the cruising range of a vehicle.

[0063] In another aspect, a computer readable storage medium is provided, which stores at least one program code, which is loaded and executed by a processor to implement the above-mentioned method for determining the cruising range of a vehicle.

[0064] In another aspect, a computer program product is provided, which stores at least one program code, which is used to be executed by a processor to implement the above-mentioned method for determining the cruising range of a vehicle.

[0065] In the embodiments of the present application, on the one hand, the number of charging and discharging of the battery will affect the service life of the battery, and with the increase of the number of charging and discharging, the health degree of the battery will gradually decrease; therefore, when determining the cruising range of the vehicle, the SOH value of the battery is increased as one of the input features, so as to improve the accuracy of the determined cruising range of the vehicle. On the other hand, different mileage prediction models are set for different charging and discharging intervals, so as to improve the accuracy of the determined cruising range of the vehicle. In summary, the embodiments of the present application can improve the accuracy of the determined cruising range of the vehicle.

[0066] It should be understood that the above general description and the following detailed description are only exemplary and cannot limit the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0067] Figure 1 is a schematic diagram of an implementation environment of a method for determining the cruising range of a vehicle according to an exemplary embodiment of the present application;

[0068] Figure 2 is a flowchart of a method for determining the cruising range of a vehicle according to an exemplary embodiment of the present application;

[0069] Figure 3 is a flowchart of a method for determining a range of a vehicle according to an example embodiment of the present application;

[0070] Figure 4 is a schematic diagram of a first mileage prediction model of a vehicle according to an example embodiment of the present application;

[0071] Figure 5 is a flowchart of a method for determining a range of a vehicle according to an example embodiment of the present application;

[0072] Figure 6 is a flowchart of a method for determining a range of a vehicle according to an example embodiment of the present application;

[0073] Figure 7 is a block diagram of a range determination apparatus of a vehicle according to an example embodiment of the present application;

[0074] Figure 8 is a block diagram of a computer device according to an example embodiment of the present application;

[0075] Figure 9 is a block diagram of a vehicle controller according to an example embodiment of the present application. DETAILED DESCRIPTION

[0076] In order to make the technical solutions and advantages of the present application clearer, the embodiments of the present application are described in further detail below.

[0077] The terms "first", "second", "third", and "fourth" and the like in the description and claims of the present application and the accompanying drawings are used to distinguish different objects, and are not used to describe a particular order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a list of steps or units is not limited to the listed steps or units, but can optionally include other steps or units not listed or can optionally include other steps or units inherent to such processes, methods, products, or devices.

[0078] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data for analysis, stored data, displayed data, etc.) and signals involved in the present application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions. For example, the battery charge and discharge times (including the first charge and discharge times and the second charge and discharge times), the battery voltage (including the first voltage and the second voltage), the battery current (including the first current and the second current), the battery temperature (including the first temperature and the second temperature), the battery SOC (including the first SOC and the second SOC), the battery SOH (including the first SOH and the second SOH) and the current driving mode of the vehicle (including the first driving mode and the second driving mode) involved in the present application are all obtained under sufficient authorization.

[0079] Please refer to Figure 1 which shows a schematic diagram of an implementation environment of a method for determining the range of a vehicle according to an example embodiment of the present application. The implementation environment includes a computer device 101 and a vehicle 102. The computer device 101 is configured to train a range prediction model and predict the range (also referred to as the remaining range) of the vehicle 102 by using the range prediction model.

[0080] The vehicle 102 is a new energy vehicle, such as a pure electric vehicle, a plug-in hybrid electric vehicle or a range-extended electric vehicle. The vehicle 102 is configured with a vehicle controller, a battery, a vehicle-mounted charger for charging the battery and a battery management system for managing the battery.

[0081] The battery management system is configured to obtain the voltage, current, temperature, SOC and SOH of the battery, and the vehicle controller is configured to determine the current driving mode of the vehicle 102. In the embodiments of the present application, the range of the vehicle 102 is determined based on the voltage, current, temperature, SOC and SOH of the battery and the current driving mode of the vehicle 102.

[0082] In a possible implementation, after the battery management system obtains the voltage, current, temperature, SOC and SOH of the battery, the battery management system sends the voltage, current, temperature, SOC and SOH of the battery to the vehicle controller, the vehicle controller receives the voltage, current, temperature, SOC and SOH of the battery sent by the battery management system, and obtains the current driving mode of the vehicle 102, and then sends the voltage, current, temperature, SOC and SOH of the battery and the current driving mode of the vehicle 102 to the computer device 101. The computer device 101 determines the cruising range of the vehicle 102 based on the voltage, current, temperature, SOC and SOH of the battery and the current driving mode of the vehicle 102 by using the mileage prediction model, and then sends the cruising range of the vehicle 102 to the vehicle controller. Alternatively, after the battery management system obtains the voltage, current, temperature, SOC and SOH of the battery, the battery management system directly sends the voltage, current, temperature, SOC and SOH of the battery to the computer device 101, the vehicle controller obtains the current driving mode of the vehicle 102, and then sends the current driving mode of the vehicle 102 to the computer device 101. The computer device 101 determines the cruising range of the vehicle 102 based on the voltage, current, temperature, SOC and SOH of the battery and the current driving mode of the vehicle 102 by using the mileage prediction model, and then sends the cruising range of the vehicle 102 to the vehicle controller.

[0083] In another possible implementation, the computer device 101 deploys the trained mileage prediction model to the vehicle controller, and the vehicle controller receives the voltage, current, temperature, SOC and SOH of the battery sent by the battery management system and obtains the current driving mode of the vehicle 102, and then determines the cruising range of the vehicle 102 by using the locally deployed mileage prediction model.

[0084] In another possible implementation, the mileage prediction model is trained by the vehicle controller, and the vehicle controller receives the voltage, current, temperature, SOC and SOH of the battery sent by the battery management system and obtains the current driving mode of the vehicle 102, and then determines the cruising range of the vehicle 102 by using the trained mileage prediction model.

[0085] Please refer to Figure 2 which shows a flowchart of a method for determining the cruising range of a vehicle according to an example embodiment of the present application. Please refer to Figure 2 The method comprises the following steps.

[0086] Step 201: The computer device determines the current first charge-discharge times of the battery included in the vehicle.

[0087] The first charge-discharge times of the battery currently refers to the number of times of completing a complete charging and discharging process of the battery currently. The vehicle is configured with a battery, a battery management system for managing the battery, and a vehicle controller; the vehicle controller is electrically connected with the battery management system through a CAN bus. The battery management system obtains the first charge-discharge times of the battery currently, and then sends the first charge-discharge times to the vehicle controller, the vehicle controller receives the first charge-discharge times, and sends the first charge-discharge times to the computer device, and the computer receives the first charge-discharge times. Alternatively, the battery management system obtains the first charge-discharge times and directly sends the first charge-discharge times to the computer device.

[0088] Step 202: The computer device determines the first charge-discharge times interval to which the first charge-discharge times belongs based on the first charge-discharge times.

[0089] In the embodiments of the present application, different charge-discharge times intervals are set with different mileage prediction models; therefore, after the computer device obtains the first charge-discharge times, the first charge-discharge times interval to which the first charge-discharge times belongs is determined, and then step 203 is executed.

[0090] Step 203: The computer device determines the first mileage prediction model corresponding to the first charge-discharge times interval, and the first mileage prediction model is used to predict the endurance mileage of the battery with the charge-discharge times in the first charge-discharge times interval.

[0091] In the embodiments of the present application, different charge-discharge times intervals are set with different mileage prediction models, so as to improve the accuracy of the endurance mileage predicted based on the mileage prediction model. Before this step, the computer device has trained the first mileage prediction model corresponding to the first charge-discharge times interval in advance, and stored the first mileage prediction model; in this step, the computer device directly obtains the stored first mileage prediction model.

[0092] Step 204: The computer device obtains the first voltage, the first current, the first temperature, the first state of charge (SOC), the first state of health (SOH) of the battery currently, and the first driving mode of the vehicle currently.

[0093] The first driving mode of the vehicle currently can be an economic mode, a normal mode, a sports mode, and a long endurance mode, etc. The first SOC refers to the charging state of the battery, i.e., the remaining power condition, and the first SOC represents the proportion relationship between the remaining available power and the power in the full power state after the battery is used or stored for a period of time. The proportion is usually expressed in percentage form, and the value range is between 0% and 100%. When the first SOC is 0%, it indicates that the battery has been completely discharged; and when the first SOC is 100%, it indicates that the battery has been fully charged.

[0094] The first SOH refers to the state of health of the battery, which represents the actual capacity percentage of the battery relative to a new battery. The first SOH is used to describe the degree of health between the current state of the battery and its original state. When the battery ages or is damaged, the first SOH decreases, indicating that the capacity and performance of the battery have decreased.

[0095] In the embodiments of the present application, the first SOH is an important indicator for evaluating the current state of the battery. As the number of charge and discharge increases, the active material and lithium ions inside the battery are constantly consumed, which causes the capacity, power, and life of the battery to decrease continuously. Therefore, by estimating the remaining driving range of the vehicle based on the first SOH state of the battery, the change in the driving range can be more accurately reflected.

[0096] Step 205: The computer device determines the driving range of the vehicle based on the current first voltage, first current, first temperature, first SOC, first SOH of the battery, and the current first driving mode of the vehicle through the first mileage prediction model.

[0097] The first mileage prediction model is used to predict the first predicted SOC of the vehicle based on the current first voltage, first current, first temperature, first SOC, and first SOH of the battery, and the current first driving mode of the vehicle. Accordingly, this step can be: the computer device inputs the current first voltage, first current, first temperature, first SOC, and first SOH of the battery, and the current first driving mode of the vehicle into the first mileage prediction model to output the first predicted SOC of the vehicle; and determines the driving range of the vehicle based on the first predicted SOC and the theoretical driving range of the vehicle.

[0098] In one possible implementation, the step of determining the driving range of the vehicle based on the first predicted SOC and the theoretical driving range of the vehicle can be: the computer device determines the product of the first predicted SOC and the theoretical driving range of the vehicle to obtain the driving range of the vehicle. The theoretical driving range of the vehicle can be the total mileage of the vehicle.

[0099] In the embodiments of the present application, as the computing power of the neural network algorithm continuously improves, its fast operation speed and high accuracy are well known. Compared with ordinary algorithms, the neural network has the advantages of selecting simple input features, reducing data collection difficulty, and easily building algorithm models, which only need to spend some time in the early stage for model training to meet the actual needs in the later stage.

[0100] It should be noted that the embodiments of the present application can also be executed by the vehicle controller of the vehicle; correspondingly, the method comprises: the vehicle controller determines the current first charge-discharge times of the battery included in the vehicle, determines the first charge-discharge times interval to which the first charge-discharge times belong based on the first charge-discharge times, acquires the first mileage prediction model corresponding to the first charge-discharge times from the computer device based on the first charge-discharge times interval, and then stores the first mileage prediction model. When the vehicle controller determines the cruising range of the vehicle, the vehicle controller takes the current first voltage, first current, first temperature, first state of charge (SOC), first state of health (SOH) of the battery, and the current first driving mode of the vehicle, determines the cruising range of the vehicle through the first mileage prediction model based on the current first voltage, first current, first temperature, first SOC, first SOH of the battery, and the current first driving mode of the vehicle.

[0101] In the embodiments of the present application, on the one hand, the charge-discharge times of the battery will affect the service life of the battery, and as the charge-discharge times increase, the health degree of the battery will gradually decrease; therefore, when the cruising range of the vehicle is determined, the SOH value of the battery is increased as one of the input features, thereby improving the accuracy of the determined cruising range of the vehicle. On the other hand, different charge-discharge times intervals are provided with different mileage prediction models, thereby improving the accuracy of the determined cruising range of the vehicle. In summary, the embodiments of the present application can improve the accuracy of the determined cruising range of the vehicle.

[0102] For reference Figure 3 which shows the flowchart of the method for determining the cruising range of the vehicle according to an example embodiment of the present application. In the embodiments of the present application, the training of the mileage prediction model is taken as an example for illustration. For reference Figure 3 The method comprises:

[0103] Step 301: The computer device determines a first sample data set based on the first charge-discharge times interval, the first sample data set comprising first sample data of a first sample vehicle and label information of the first sample data, the charge-discharge times of the first sample vehicle being in the first charge-discharge times interval, and the first sample data of the first sample vehicle comprising the voltage, current, temperature, SOC, SOH of the battery included in the first sample vehicle, and the driving mode of the first sample vehicle, and the label information of the first sample data being the real cruising range of the first sample vehicle.

[0104] It should be noted that before the computer device executes step 302, the computer device needs to build an initial first mileage prediction model; for example, for reference Figure 4The first mileage prediction model comprises an input layer, a plurality of hidden layers and an output layer. The input layer comprises 6 nodes, i.e., the input layer comprises a first node, a second node, a third node, a fourth node, a fifth node and a sixth node. The first node is used for inputting voltage, the second node is used for inputting current, the third node is used for inputting temperature, the fourth node is used for inputting SOH, the fifth node is used for inputting driving mode, and the sixth node is used for inputting SOC. The output layer comprises one node, and the node of the output layer is used for outputting the predicted SOC of the vehicle.

[0105] In a possible implementation, the number of hidden layers of the first mileage prediction model can be set and changed as needed. For example, the number of hidden layers can be 3 or 4, etc. In the embodiment of the present application, the number of hidden layers is 3, i.e., the first mileage prediction model comprises a first hidden layer, a second hidden layer and a third hidden layer. The input end of the first hidden layer is connected with the output end of the input layer, the output end of the first hidden layer is connected with the input end of the second hidden layer, the output end of the second hidden layer is connected with the input end of the third hidden layer, and the output end of the third hidden layer is connected with the output layer.

[0106] After determining the number of hidden layers, the computer device also needs to determine the feature number of each hidden layer, i.e., the computer device also needs to determine the feature number of the first hidden layer, the feature number of the second hidden layer and the feature number of the third hidden layer. The computer device subtracts a preset value from the feature number of the first hidden layer to obtain the feature number of the second hidden layer, subtracts the preset value from the feature number of the second hidden layer to obtain the feature number of the third hidden layer, and the preset value can be set and changed as needed. In the embodiment of the present application, the preset value is not limited specifically. For example, the preset value can be 2. Therefore, the core of this step is to determine the feature number of the first hidden layer.

[0107] The computer device determines the feature number of the first hidden layer by determining the number of input features, the number of output features and the neuron constant of the hidden layer, and determining the feature number of the first hidden layer based on the number of input features, the number of output features and the neuron constant of the hidden layer.

[0108] The computer device determines the neuron constant of the hidden layer by determining the value range of the neuron constant of the hidden layer, determining the precision requirement information and the accuracy requirement information, the precision requirement information indicating the precision requirement of the first mileage prediction model, and the accuracy requirement information indicating the accuracy requirement of the first mileage prediction model, determining the neuron constant included in the hidden layer based on the precision requirement information and the accuracy requirement information, and determining the neuron constant based on the value range of the neuron constant and the neuron constant included in the hidden layer.

[0109] For example, the neuron constant of the hidden layer takes a value range of 1-10; when the neuron constant of the hidden layer is small, the prediction accuracy of the first mileage prediction model is low and does not meet the requirement; as the number of neurons of the hidden layer increases, the training accuracy of the first mileage prediction model is higher and higher, and the training times are less and less; however, when the neuron constant increases to more than 15, the training accuracy of the first mileage prediction model almost does not increase, but the training time of the first mileage prediction model becomes longer; therefore, the computer device determines that the neuron constant of the hidden layer is 5 based on the above content.

[0110] In the formula three, i represents the first value, x represents the number of input features, y represents the number of output features, and z represents the neuron constant of the hidden layer; in the embodiment of the present application, the value of x is 6, the value of y is 1, and the value of z is 5; the computer device takes the first value i to be an integer to obtain the feature number of the first hidden layer as 8, then subtracts a preset value (2) from the feature number of the first hidden layer to obtain the feature number (6) of the second hidden layer, and subtracts the preset value (2) from the feature number of the second hidden layer to obtain the feature number (4) of the third hidden layer.

[0111] Formula three:

[0112] In the formula three, i represents the first value, x represents the number of input features, y represents the number of output features, and z represents the neuron constant of the hidden layer; in the embodiment of the present application, the value of x is 6, the value of y is 1, and the value of z is 5; the computer device takes the first value i to be an integer to obtain the feature number of the first hidden layer as 8, then subtracts a preset value (2) from the feature number of the first hidden layer to obtain the feature number (6) of the second hidden layer, and subtracts the preset value (2) from the feature number of the second hidden layer to obtain the feature number (4) of the third hidden layer.

[0113] Step 302: The computer device determines the predicted cruising range of the first sample vehicle based on the first sample data set by using the initial first mileage prediction model, and the first mileage prediction model comprises an input layer, a plurality of hidden layers and an output layer connected in sequence.

[0114] The first sample data set comprises first sample data of a plurality of first sample vehicles, and for the first sample data of any first sample vehicle, the computer device inputs the first sample data of the first sample vehicle into the initial first mileage prediction model, outputs the predicted SOC of the first sample vehicle, and determines the predicted cruising range of the first sample vehicle based on the predicted SOC of the first sample vehicle and the theoretical cruising range of the first sample vehicle.

[0115] Step 303: The computer device determines the loss function value of the first mileage prediction model based on the real cruising range and the predicted cruising range of the first sample vehicle, and the loss function value is used to represent the difference between the real cruising range and the predicted cruising range of the first sample vehicle.

[0116] The step can be implemented through the following steps 3031 and 3032, comprising:

[0117] Step 3031: The computer device determines the first sample number of the first sample data set.

[0118] Step 3032: The computer device determines the loss function value of the first mileage prediction model based on the first sample number, the actual mileage and the predicted mileage of the first sample vehicle through the following formula one:

[0119] Formula one:

[0120] Wherein, L represents the loss function value, N represents the first sample number, i represents the serial number of the first sample vehicle, represents the predicted mileage of the i-th first sample vehicle, y i represents the actual mileage of the i-th first sample vehicle.

[0121] Step 304: In the case where the loss function value is less than the loss function threshold, the computer device ends the training to obtain the first mileage prediction model.

[0122] The loss function threshold can be set and changed as needed, and in the embodiments of the present application, the loss function threshold is not specifically limited; for example, the loss function threshold can be 0.01. In the embodiments of the present application, after the computer device trains the first mileage prediction model for multiple rounds, the loss function values of the feature weights of the multiple hidden layers included in the first mileage prediction model will gradually decrease, and over-training will cause over-fitting phenomenon, so it is necessary to set the loss function threshold, and when the loss function value is reduced to the loss function threshold (set to 0.01 in this paper), the training is ended, which is regarded as that the first mileage prediction model completes the training in the current stage.

[0123] Step 305: In the case where the loss function value is not less than the loss function threshold, the computer device updates the feature weights and the bias of the multiple hidden layers based on the loss function value, and then determines the predicted mileage of the first sample vehicle through the first mileage prediction model based on the first sample data set until the loss function value of the first mileage prediction model is less than the loss function threshold, at which time the training is ended to obtain the first mileage prediction model.

[0124] The step of updating the feature weights and the bias of the multiple hidden layers based on the loss function value can be:

[0125] For the j-th hidden layer, the partial derivative of the loss function with respect to the feature weight of the j-th hidden layer is determined to obtain the first partial derivative;

[0126] The partial derivative of the loss function with respect to the bias of the j-th hidden layer is determined to obtain the second partial derivative;

[0127] Based on the first partial derivative and the second partial derivative, the feature weight and the bias of the jth hidden layer are updated by Equation Two as follows:

[0128] Equation Two:

[0129] wherein j represents the serial number of the hidden layer, represents the updated feature weight of the jth hidden layer, represents the feature weight of the jth hidden layer before being updated, and a represents a learning rate, represents the first partial derivative, represents the updated bias value of the jth hidden layer, represents the bias value of the jth hidden layer before being updated, represents the second partial derivative.

[0130] The learning rate can be set and changed as needed, and in the embodiments of the present application, the learning rate is not specifically limited; for example, the learning rate can be 0.01.

[0131] After the computer device updates the feature weights of the plurality of hidden layers, the computer device re-determines the predicted range of the first sample vehicle based on the first sample data set and the updated first range prediction model, and then re-determines the loss function value of the first range prediction model based on the actual range of the first sample vehicle and the re-determined predicted range, and then determines whether the re-determined loss function value is less than the loss function threshold value, and in the case where the re-determined loss function value is less than the loss function threshold value, the training is ended to obtain the first range prediction model; in the case where the re-determined loss function value is not less than the loss function threshold value, the feature weights and the bias of the plurality of hidden layers are updated again, and so on.

[0132] It should be noted that the first range prediction model can also be trained by the vehicle controller; when the first range prediction model is trained by the vehicle controller, the execution subject of steps 301-305 is replaced by the vehicle controller.

[0133] Please refer to Figure 5 which shows a flowchart of a method for determining the range of a vehicle according to an example embodiment of the present application. In the embodiments of the present application, the computer device updates the range prediction model, and the computer device determines the range of the vehicle is taken as an example for illustration. Please refer to Figure 5 The method comprises the following steps:

[0134] Step 501: When the current second charge-discharge frequency of the battery is greater than the maximum value of the first charge-discharge frequency interval, the computer device determines the second charge-discharge frequency interval to which the second charge-discharge frequency belongs.

[0135] For the convenience of distinguishing, the charging and discharging times determined at different times are called different charging and discharging times; for example, the charging and discharging times determined when the last time the vehicle's cruising range is determined are called the first charging and discharging times (step 201), and the charging and discharging times determined when the current time the vehicle's cruising range is determined are called the second charging and discharging times. The SOH of the battery is highly related to the charging and discharging times of the battery; when the second charging and discharging times are greater than the maximum value of the first charging and discharging times interval, it means that the vehicle's cruising range predicted by the first range prediction model at this time is already inaccurate, and the latest data of the battery needs to be introduced to retrain the range prediction model for the prediction of the vehicle's cruising range, thereby improving the accuracy of the determined vehicle's cruising range.

[0136] Step 502: The computer device determines a second sample data set based on the second charging and discharging times interval, the second sample data set including second sample data of a second sample vehicle and label information of the second sample data, the charging and discharging times of the second sample vehicle being in the second charging and discharging times interval, and the second sample data of the second sample vehicle including voltage, current, temperature, SOC, SOH of the battery included in the second sample vehicle and driving mode of the second sample vehicle, and the label information of the second sample data being the real cruising range of the second sample vehicle.

[0137] In some embodiments, this step is similar to step 301, and will not be repeated here.

[0138] Step 503: The computer device trains a second range prediction model based on the second sample data set, the second range prediction model being used for predicting the cruising range of the battery with charging and discharging times in the second charging and discharging times interval.

[0139] The computer device determines the predicted cruising range of the second sample vehicle based on the second sample data set through the initial second range prediction model, the second range prediction model including an input layer, a plurality of hidden layers and an output layer connected in sequence; determines the loss function value of the second range prediction model based on the real cruising range and the predicted cruising range of the second sample vehicle; in the case that the loss function value is less than the loss function threshold, the training is ended to obtain the second range prediction model, and in the case that the loss function value is not less than the loss function threshold, the computer device updates the bias of the feature weight of the plurality of hidden layers based on the loss function value, and then determines the predicted cruising range of the second sample vehicle based on the second sample data set through the second range prediction model until the loss function values of the determined second range prediction models are all less than the loss function threshold, at which time the training is ended to obtain the second range prediction model.

[0140] Step 504: The computer device obtains the current second voltage, second current, second temperature, second SOC, second SOH of the battery and the current second driving mode of the vehicle.

[0141] For the convenience of distinguishing, the voltage, current, temperature, SOC and SOH of the battery and the driving mode of the vehicle determined at different times are referred to as different voltage, current, temperature, SOC and SOH of the battery and different driving mode of the vehicle; for example, the voltage, current, temperature, SOC and SOH of the battery and the driving mode of the vehicle determined when the last time the vehicle's range determination is performed are referred to as the first voltage, the first current, the first temperature, the first SOC and the first SOH and the first driving mode of the vehicle (step 204), and the voltage, current, temperature, SOC and SOH of the battery and the driving mode of the vehicle determined when the current time the vehicle's range determination is performed are referred to as the second voltage, the second current, the second temperature, the second SOC and the second SOH and the second driving mode of the vehicle.

[0142] Step 505: The computer device determines the vehicle's range based on the current second voltage, second current, second temperature, second SOC, second SOH of the battery and the current second driving mode of the vehicle through the second mileage prediction model.

[0143] The computer device inputs the current second voltage, second current, second temperature, second SOC, second SOH of the battery and the current second driving mode of the vehicle into the second mileage prediction model to output the second predicted SOC of the vehicle; and determines the vehicle's range based on the second predicted SOC and the theoretical range of the vehicle.

[0144] In the embodiment of the present application, the battery SOH value is highly related to the number of times of charging and discharging of the battery. When the number of times of charging and discharging of the vehicle reaches a certain limit value, the latest data of the battery is introduced to retrain the weight values of the mileage prediction model (for the convenience of distinguishing, the retrained mileage prediction model is referred to as the second mileage prediction model) to determine the vehicle's range through the second mileage prediction model, thereby improving the accuracy of the determined vehicle's range.

[0145] Please refer to Figure 6 which shows a flowchart of a vehicle's range determination method according to an example embodiment of the present application. In the embodiment of the present application, the computer device updates the mileage prediction model, and the vehicle's range is determined by the vehicle control unit. Please refer to Figure 6 The method comprises:

[0146] Step 601: When the current second number of times of charging and discharging of the battery is greater than the maximum value of the first number of times of charging and discharging, the vehicle control unit sends a request to the computer device, and the request carries the second number of times of charging and discharging.

[0147] In the embodiment of the present application, the mileage prediction model is updated by the computer device; therefore, when the current second charge-discharge frequency of the battery is greater than the maximum value of the first charge-discharge frequency interval, the vehicle controller sends a request to the computer device to request the computer device to update the mileage prediction model, and the updated mileage prediction model is referred to as a second mileage prediction model.

[0148] Step 602: The computer device receives the request sent by the vehicle controller, and determines the second charge-discharge frequency interval to which the second charge-discharge frequency belongs.

[0149] Step 603: The computer device determines a second sample data set based on the second charge-discharge frequency interval, the second sample data set including second sample data of a second sample vehicle and label information of the second sample data, the charge-discharge frequency of the second sample vehicle being in the second charge-discharge frequency interval, and the second sample data of the second sample vehicle including voltage, current, temperature, SOC, SOH of the battery included in the second sample vehicle and driving mode of the second sample vehicle, the label information of the second sample data being the real endurance mileage of the second sample vehicle.

[0150] In some embodiments, this step is similar to step 301, which will not be described here.

[0151] Step 604: The computer device trains the second mileage prediction model based on the second sample data set, the second mileage prediction model being used to predict the endurance mileage of the battery with the charge-discharge frequency in the second charge-discharge frequency interval.

[0152] In some embodiments, this step is the same as step 503, which will not be described here.

[0153] Step 605: The computer device sends the second mileage prediction model to the vehicle controller.

[0154] Step 606: The vehicle controller receives the second mileage prediction model and stores the second mileage prediction model.

[0155] The vehicle controller stores the second mileage prediction model, so as to facilitate subsequent prediction of the endurance mileage of the vehicle by the second mileage prediction model.

[0156] Step 607: When the vehicle controller determines the endurance mileage of the vehicle, the vehicle controller obtains the current second voltage, second current, second temperature, second SOC, second SOH of the battery and the current second driving mode of the vehicle.

[0157] In some embodiments, the step of obtaining, by the vehicle controller, the current second voltage, the current second current, the current second temperature, the current second SOC, the current second SOH of the battery and the current second driving mode of the vehicle can be: obtaining, by a battery management system of the vehicle, the current second voltage, the current second current, the current second temperature, the current second SOC, the current second SOH of the battery, sending the current second voltage, the current second current, the current second temperature, the current second SOC, the current second SOH to the vehicle controller, receiving, by the vehicle controller, the current second voltage, the current second current, the current second temperature, the current second SOC, the current second SOH, and obtaining the current second driving mode of the vehicle.

[0158] Step 608: determining, by the vehicle controller, the cruising range of the vehicle based on the current second voltage, the current second current, the current second temperature, the current second SOC, the current second SOH of the battery and the current second driving mode of the vehicle through the second mileage prediction model.

[0159] The vehicle controller inputs the current second voltage, the current second current, the current second temperature, the current second SOC, the current second SOH of the battery and the current second driving mode of the vehicle into the second mileage prediction model to output the second predicted SOC of the vehicle; and determines the cruising range of the vehicle based on the second predicted SOC and the theoretical cruising range of the vehicle.

[0160] In the embodiments of the present application, the second mileage prediction model is deployed into the vehicle controller, so that the vehicle controller can predict the cruising range of the vehicle through the second mileage prediction model even without connecting to a wireless network, thereby improving the application range.

[0161] Please refer to Figure 7 which shows a block diagram of a device for determining the cruising range of a vehicle according to an example embodiment of the present application. The device comprises:

[0162] A first determination module 701 is configured to determine the current first number of charging and discharging of a battery included in a vehicle.

[0163] A second determination module 702 is configured to determine a first number of charging and discharging interval to which the first number of charging and discharging belongs based on the first number of charging and discharging.

[0164] A third determination module 703 is configured to determine a first mileage prediction model corresponding to the first number of charging and discharging interval, the first mileage prediction model being used to predict the cruising range of the battery with the number of charging and discharging in the first number of charging and discharging interval.

[0165] A first acquisition module 704 is configured to acquire the current first voltage, the current first current, the current first temperature, the current first state of charge (SOC), the current first state of health (SOH) of the battery and the current first driving mode of the vehicle.

[0166] The fourth determining module 705 is configured to determine the cruising range of the vehicle by the first range prediction model based on the current first voltage, the current first current, the current first temperature, the current first SOC, the current first SOH of the battery, and the current first driving mode of the vehicle.

[0167] In a possible implementation, the apparatus further includes:

[0168] The fifth determining module is configured to determine a first sample data set based on the first charge-discharge frequency interval, the first sample data set including first sample data of a first sample vehicle and label information of the first sample data, the charge-discharge frequency of the first sample vehicle being in the first charge-discharge frequency interval, the first sample data of the first sample vehicle including voltage, current, temperature, SOC, SOH of a battery included in the first sample vehicle, and a driving mode of the first sample vehicle, and the label information of the first sample data being a real cruising range of the first sample vehicle.

[0169] The sixth determining module is configured to determine a predicted cruising range of the first sample vehicle by an initial first range prediction model based on the first sample data set, the first range prediction model including an input layer, a plurality of hidden layers, and an output layer connected in sequence.

[0170] The seventh determining module is configured to determine a loss function value of the first range prediction model based on the real cruising range and the predicted cruising range of the first sample vehicle, the loss function value being used to represent a difference between the real cruising range and the predicted cruising range of the first sample vehicle.

[0171] The first training module is configured to end the training to obtain the first range prediction model when the loss function value is less than a loss function threshold.

[0172] The updating module is configured to, when the loss function value is not less than the loss function threshold, update feature weights and bias amounts of the plurality of hidden layers based on the loss function value, and then determine the predicted cruising range of the first sample vehicle by the first range prediction model based on the first sample data set until the loss function value of the first range prediction model is less than the loss function threshold, at which time the training is ended to obtain the first range prediction model.

[0173] In another possible implementation, the seventh determining module is configured to determine a first sample number of the first sample data set, and determine the loss function value of the first range prediction model based on the first sample number, the real cruising range and the predicted cruising range of the first sample vehicle by the following formula one.

[0174] Formula one:

[0175] wherein, L represents the loss function value, N represents the first sample number, i represents the serial number of the first sample vehicle, represents the predicted range of the i-th first sample vehicle, y i represents the real range of the i-th first sample vehicle.

[0176] In another possible implementation, the updating module is configured to, for the j-th hidden layer, determine a first partial derivative of the loss function with respect to a feature weight of the j-th hidden layer to obtain a first partial derivative; determine a second partial derivative of the loss function with respect to a bias of the j-th hidden layer to obtain a second partial derivative; and update the feature weight and the bias of the j-th hidden layer based on the first partial derivative and the second partial derivative according to the following Formula Two.

[0177] Formula Two:

[0178] wherein, j represents the serial number of the hidden layer, represents the updated feature weight of the j-th hidden layer, represents the feature weight of the j-th hidden layer before being updated, and a represents a learning rate, represents the first partial derivative, represents the updated bias of the j-th hidden layer, represents the bias of the j-th hidden layer before being updated, represents the second partial derivative.

[0179] In another possible implementation, the apparatus further includes:

[0180] An eighth determining module is configured to determine a second charge-discharge frequency interval to which the current second charge-discharge frequency of the battery belongs when the current second charge-discharge frequency of the battery is greater than the maximum value of the first charge-discharge frequency interval.

[0181] A ninth determining module is configured to determine a second sample data set based on the second charge-discharge frequency interval, the second sample data set including second sample data of a second sample vehicle and label information of the second sample data, the charge-discharge frequency of the second sample vehicle being in the second charge-discharge frequency interval, and the second sample data of the second sample vehicle including voltage, current, temperature, SOC, SOH of a battery included in the second sample vehicle and a driving mode of the second sample vehicle, the label information of the second sample data being a real range of the second sample vehicle.

[0182] a second training module, configured to train a second mileage prediction model based on the second sample data set, the second mileage prediction model being used to predict the endurance mileage of the battery with the number of charging and discharging times in the second number of charging and discharging times interval;

[0183] a second obtaining module, configured to obtain a second voltage, a second current, a second temperature, a second SOC, a second SOH of the battery currently, and a second driving mode of the vehicle currently;

[0184] a tenth determining module, configured to determine the endurance mileage of the vehicle by the second mileage prediction model based on the second voltage, the second current, the second temperature, the second SOC, the second SOH of the battery currently, and the second driving mode of the vehicle currently.

[0185] In another possible implementation, the fourth determining module 705 is configured to input the voltage, the current, the temperature, the SOC, the SOH of the battery, and the current driving mode of the vehicle into the first mileage prediction model to output a predicted SOC of the vehicle; and determine the endurance mileage of the vehicle based on the predicted SOC and a theoretical endurance mileage of the vehicle.

[0186] In the embodiments of the present application, on the one hand, the number of charging and discharging times of the battery affects the service life of the battery, and as the number of charging and discharging times increases, the health degree of the battery gradually decreases; therefore, when determining the endurance mileage of the vehicle, the SOH value of the battery is added as one of the input features, so as to improve the accuracy of the determined endurance mileage of the vehicle. On the other hand, different mileage prediction models are set for different number of charging and discharging times intervals, so as to improve the accuracy of the determined endurance mileage of the vehicle. In summary, the embodiments of the present application can improve the accuracy of the determined endurance mileage of the vehicle.

[0187] It should be noted that the vehicle endurance mileage determination apparatus provided in the above embodiments is only used as an example for the division of the above functional modules when determining the endurance mileage of the vehicle, and in actual applications, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the above described functions. In addition, the vehicle endurance mileage determination apparatus and the vehicle endurance mileage determination method provided in the above embodiments belong to the same concept, and the specific implementation process is described in detail in the method embodiments, which will not be repeated here.

[0188] For reference Figure 8 , Figure 8A structural block diagram of the computer device 800 provided by an example embodiment of the present application is shown. The computer device 800 includes a central processing unit (CPU) 801 and a memory 802, wherein the memory 802 stores at least one program code, and the at least one program code is loaded and executed by the CPU 801 to implement the vehicle range determination method provided by each method embodiment described above. Of course, the computer device 800 can also have a wired or wireless network interface, a keyboard, an input and output interface, and other components for implementing device functions, which are not described here in detail.

[0189] Those skilled in the art can understand that the structure shown in the above Figure 8 The structure shown in the above is not a limitation on the computer device 800, and the computer device 800 can include more or fewer components than those shown in the figure, or combine certain components, or use different component arrangements.

[0190] Figure 9 FIG. 9 is a structural schematic diagram of a vehicle controller according to an embodiment of the present application.

[0191] Generally, the vehicle controller 900 includes a main control module 901, a CAN interface 902, a hard-wire input interface 903, and a hard-wire output interface 904. The main control module 901 is connected to the CAN interface 902, the hard-wire input interface 903, and the hard-wire output interface 904, respectively.

[0192] The master module 901 generally includes a processor and a memory. The processor can include one or more processing cores, such as a 4-core processor, a 9-core processor, etc. The processor can be implemented in at least one of a hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), a PLA (Programmable Logic Array). The processor can also include a main processor and a coprocessor. The main processor is a processor for processing data in the wake-up state, also known as a CPU (Central Processing Unit). The coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor can be integrated with a GPU (Graphics Processing Unit) for rendering and drawing the content to be displayed on the vehicle display screen. In some embodiments, the processor can also include an AI (Artificial Intelligence) processor for processing machine learning-related computing operations. The memory can include one or more computer-readable storage media, which can be non-transitory. The memory can also include a high-speed random access memory and a non-volatile memory such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory is used to store at least one computer program for being executed by the processor to implement the vehicle range determination method provided by the method embodiment of the present application.

[0193] The CAN interface 902 can include a power CAN interface, a motor CAN interface, and a diagnostic CAN interface. The power CAN interface is used to communicate with the power system module of the vehicle, the motor CAN interface is used to communicate with the motor controller of the vehicle, and the diagnostic CAN interface is used to communicate with the diagnostic device.

[0194] The hard-wired input interface 903 is used to receive a hard-wired control signal. The hard-wired output interface 904 is used to send a control instruction to an electric control element of the vehicle to make the electric control element of the vehicle perform a corresponding action. The electric control element of the vehicle includes a power management system, a motor controller, an on-board charger, a body control system, etc.

[0195] The master module 901 can communicate with the power system module, motor controller and diagnostic equipment of the vehicle through the CAN interface 902, and generate control instructions according to the hard-wire control signals received by the hard-wire input interface 903, to send the control instructions to the electric control elements of the vehicle through the hard-wire output interface 904.

[0196] Those skilled in the art can understand that, Figure 9 The structure shown in the figure does not constitute a limitation on the whole vehicle controller 900, and can include more or fewer components than shown, or combine certain components, or adopt different component arrangements.

[0197] The embodiments of the present application also provide a computer readable storage medium, which stores at least one program code, and the at least one program code is loaded and executed by a processor to implement the vehicle range determination method in any of the above implementation manners. Optionally, the storage medium can be a non-transitory computer readable storage medium, for example, the non-transitory computer readable storage medium can be a ROM (Read-Only Memory), a RAM (Random Access Memory), a CD-ROM (Compact Disc Read-Only Memory), a magnetic tape, a floppy disk and an optical data storage device, etc.

[0198] The embodiments of the present application also provide a computer program product, which stores at least one program code, and the at least one program code is loaded and executed by a processor to implement the vehicle range determination method in any of the above embodiments.

[0199] In some embodiments, the computer program product related to the embodiments of the present application can be deployed on one computer device for execution, or on multiple computer devices located in one place for execution, or on multiple computer devices distributed in multiple places and interconnected through a communication network for execution, and the multiple computer devices distributed in multiple places and interconnected through a communication network can constitute a blockchain system.

[0200] Those skilled in the art can understand that all or part of the steps of the above-mentioned embodiments can be completed by hardware, or by a program instructing related hardware, and the program can be stored in a computer readable storage medium, and the above-mentioned storage medium can be a read-only memory, a magnetic disk or an optical disk, etc.

[0201] The above is only for the convenience of those skilled in the art to understand the technical solutions of the present application, and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for determining the driving range of a vehicle, characterized in that, The method includes: Determine the current first charge / discharge count of the vehicle's batteries; Based on the first number of charge-discharge cycles, determine the first charge-discharge cycle interval to which the first number of charge-discharge cycles belongs; A first mileage prediction model is determined for the first charge-discharge cycle interval. The first mileage prediction model is used to predict the driving range of the battery with the number of charge-discharge cycles in the first charge-discharge cycle interval. The first voltage, first current, first temperature, first state of charge (SOC), first state of battery (SOH), and the first driving mode of the vehicle are obtained. Based on the battery's current first voltage, first current, first temperature, first SOC, first SOH and the vehicle's current first driving mode, the vehicle's driving range is determined through the first mileage prediction model.

2. The method according to claim 1, characterized in that, The method further includes: Based on the first charge-discharge cycle interval, a first sample dataset is determined. The first sample dataset includes first sample data of the first sample vehicle and the tag information of the first sample data. The charge-discharge cycle of the first sample vehicle is within the first charge-discharge cycle interval. The first sample data of the first sample vehicle includes the voltage, current, temperature, SOC, SOH of the battery included in the first sample vehicle and the driving mode of the first sample vehicle. The tag information of the first sample data is the actual driving range of the first sample vehicle. Based on the first sample dataset, the predicted driving range of the first sample vehicle is determined by an initial first mileage prediction model, which includes an input layer, multiple hidden layers and an output layer connected in sequence. Based on the actual driving range and predicted driving range of the first sample vehicle, the loss function value of the first driving range prediction model is determined, and the loss function value is used to represent the difference between the actual driving range and the predicted driving range of the first sample vehicle. If the loss function value is less than the loss function threshold, the training ends and the first mileage prediction model is obtained. If the loss function value is not less than the loss function threshold, the feature weights and biases of the multiple hidden layers are updated based on the loss function value. Then, based on the first sample dataset, the predicted driving range of the first sample vehicle is determined by the first mileage prediction model. This process continues until the loss function value of the first mileage prediction model is less than the loss function threshold. At this point, training ends and the first mileage prediction model is obtained.

3. The method according to claim 2, characterized in that, The step of determining the loss function value of the first mileage prediction model based on the actual driving range and predicted driving range of the first sample vehicle includes: Determine the first number of samples in the first sample dataset; Based on the first sample size, the actual driving range of the first sample vehicles, and the predicted driving range, the loss function value of the first mileage prediction model is determined using the following formula: Formula 1: Where L represents the loss function value, N represents the number of the first samples, and i represents the sequence number of the first sample vehicle. Let y represent the predicted driving range of the i-th vehicle in the first sample. i This represents the actual driving range of the i-th first sample vehicle.

4. The method according to claim 2 or 3, characterized in that, The step of updating the feature weights and biases of the multiple hidden layers based on the loss function value includes: For the j-th hidden layer, the first partial derivative is obtained by determining the partial derivative of the loss function with respect to the feature weights of the j-th hidden layer; The second partial derivative is obtained by determining the partial derivative of the loss function with respect to the bias of the j-th hidden layer; Based on the first partial derivative and the second partial derivative, the feature weights and biases of the j-th hidden layer are updated using the following formula 2; Formula 2: Where j represents the index of the hidden layer. This represents the updated feature weights of the j-th hidden layer. Let α represent the feature weights before the update of the j-th hidden layer, and let α represent the learning rate. Denotes the first partial derivative. This represents the updated bias value of the j-th hidden layer. This represents the bias value before the j-th hidden layer is updated. This represents the second partial derivative.

5. The method according to claim 1, characterized in that, The method further includes: When the current second charge-discharge count of the battery is greater than the maximum value of the first charge-discharge count interval, the second charge-discharge count interval to which the second charge-discharge count belongs is determined; Based on the second charge-discharge cycle range, a second sample dataset is determined. The second sample dataset includes the second sample data of the second sample vehicle and the label information of the second sample data. The charge-discharge cycle of the second sample vehicle is within the second charge-discharge cycle range. The second sample data of the second sample vehicle includes the voltage, current, temperature, SOC, SOH of the battery included in the second sample vehicle and the driving mode of the second sample vehicle. The label information of the second sample data is the actual driving range of the second sample vehicle. Based on the second sample dataset, a second mileage prediction model is trained. The second mileage prediction model is used to predict the driving range of a battery with a number of charge-discharge cycles within the second charge-discharge cycle range. The current second voltage, second current, second temperature, second SOC, second SOH of the battery and the current second driving mode of the vehicle are obtained. Based on the battery's current second voltage, second current, second temperature, second SOC, second SOH, and the vehicle's current second driving mode, the vehicle's driving range is determined through the second mileage prediction model.

6. The method according to claim 1, characterized in that, The step of determining the vehicle's driving range based on the battery's current first voltage, first current, first temperature, first SOC, first SOH, and the vehicle's current first driving mode, using the first range prediction model, includes: The first voltage, first current, first temperature, first SOC, first SOH of the battery and the first driving mode of the vehicle are input into the first mileage prediction model to output the first predicted SOC of the vehicle; The driving range of the vehicle is determined based on the first predicted SOC and the theoretical driving range of the vehicle.

7. A device for determining the driving range of a vehicle, characterized in that, The device includes: The first determining module is used to determine the current first charge-discharge cycle of the battery included in the vehicle; The second determining module is used to determine the first charge-discharge interval to which the first charge-discharge interval belongs based on the first charge-discharge interval; The third determining module is used to determine the first mileage prediction model corresponding to the first charge-discharge cycle interval. The first mileage prediction model is used to predict the driving range of the battery with the number of charge-discharge cycles in the first charge-discharge cycle interval. The first acquisition module is used to acquire the current first voltage, first current, first temperature, first state of charge (SOC), first state of battery (SOH), and the current first driving mode of the vehicle. The fourth determining module is used to determine the vehicle's driving range based on the battery's current first voltage, first current, first temperature, first SOC, first SOH and the vehicle's current first driving mode, through the first mileage prediction model.

8. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing at least one piece of program code, the at least one piece of program code being loaded and executed by the processor to implement the method for determining the driving range of a vehicle as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The storage medium stores at least one piece of program code, which is loaded and executed by a processor to implement the vehicle range determination method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The product stores at least one piece of program code, which is executed by a processor to implement the method for determining the driving range of a vehicle as described in any one of claims 1 to 6.

Images