CN117863886A - Range-extending vehicle endurance prediction method and device, electronic equipment and medium - Google Patents

Abstract

The application provides a endurance prediction method, a device, electronic equipment and a medium of a range-extending vehicle, wherein the method comprises the following steps: acquiring current power data of a plurality of components in the extended-range vehicle; based on current power data of a plurality of components in the range-extending vehicle, energy consumption weight distribution is carried out on each component through an energy consumption weight distribution rule, so that energy consumption weights of each component are obtained; determining the energy consumption data corresponding to each component per kilometer according to the current power data of a plurality of components in the range-extending vehicle and the energy consumption weight corresponding to each component; and predicting the endurance mileage of the extended-range vehicle according to the energy consumption data corresponding to each kilometer of each component. According to the technical scheme, the accuracy of predicting the range of the range-extended vehicle can be improved.

Description

Range-extending vehicle endurance prediction method and device, electronic equipment and medium

Technical Field

The present disclosure relates to the field of endurance prediction of extended-range vehicles, and in particular, to a method, an apparatus, an electronic device, and a medium for endurance prediction of extended-range vehicles.

Background

The problem that the battery is insufficient and can not be charged in time can be encountered in the running process of the new energy automobile, which is an important challenge for popularization of the new energy automobile. To solve this problem, extended range vehicles have been developed. The range-extending vehicle is an electric vehicle with an internal combustion engine, and when the battery is low, the internal combustion engine can charge the battery, so that the running of the vehicle is ensured. However, extended range vehicles are relatively inefficient in charging with an internal combustion engine. Therefore, in order to effectively plan the driving route of the extended range vehicle and find a suitable charging station, it is necessary to accurately predict the range of the extended range vehicle. The conventional prediction method generally predicts based on parameters such as the weight, air resistance coefficient, rolling resistance and the like of the extended-range vehicle. However, these factors are affected by many external factors, such as weather conditions, road conditions, etc., so that the accuracy of this prediction method is low, and cannot meet the actual use requirements.

Disclosure of Invention

In view of this, the embodiments of the present application provide a method, an apparatus, an electronic device, and a medium for predicting the endurance of a range-extended vehicle, so as to solve the technical problem of low accuracy of endurance prediction of a range-extended vehicle in the prior art.

In a first aspect of an embodiment of the present application, a method for predicting a endurance of a range-extending vehicle is provided, where the method includes obtaining current power data of a plurality of components in the range-extending vehicle; based on current power data of a plurality of components in the range-extending vehicle, energy consumption weight distribution is carried out on each component through an energy consumption weight distribution rule, so that energy consumption weights of each component are obtained; determining the energy consumption data corresponding to each component per kilometer according to the current power data of a plurality of components in the range-extending vehicle and the energy consumption weight corresponding to each component; and predicting the endurance mileage of the extended-range vehicle according to the energy consumption data corresponding to each kilometer of each component.

In a second aspect of the embodiments of the present application, there is provided a endurance prediction apparatus for a range-extended vehicle, the apparatus including: the acquisition module is used for acquiring current power data of a plurality of components in the range-extending vehicle; the weight distribution module is used for distributing the energy consumption weights of all the components through the energy consumption weight distribution rule based on the current power data of a plurality of components in the range-extending vehicle to obtain the energy consumption weights of all the components; the determining module is used for determining the energy consumption data corresponding to each component per kilometer according to the current power data of the components in the range-extended vehicle and the energy consumption weights corresponding to each component; and the prediction module is used for predicting the endurance mileage of the extended-range vehicle according to the energy consumption data corresponding to each kilometer of each component.

In a third aspect of embodiments of the present application, there is provided an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method as provided in the first aspect above when the computer program is executed.

In a fourth aspect of embodiments of the present application, there is provided a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the method as provided in the first aspect described above.

Compared with the prior art, the beneficial effects of the embodiment of the application at least comprise: according to the method and the device for predicting the range of the extended range vehicle, the current power data of each part of the extended range vehicle is obtained, and the energy consumption weight distribution rule is applied, so that the energy consumption data corresponding to each kilometer of each part is determined, the range of the extended range vehicle is predicted more accurately, the extended range vehicle can conduct driving route planning and charging station searching according to the predicted range, and driving efficiency and user experience are improved greatly. More accurate driving mileage prediction and planning, unnecessary charging behavior is avoided, energy is saved, and environmental pollution caused by battery production and treatment is reduced.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following description will briefly introduce the drawings that are needed in the embodiments or the description of the prior art, it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 shows a schematic diagram of an exemplary system architecture to which the technical solution of an embodiment of the invention may be applied;

fig. 2 is a flowchart of a endurance prediction method of a range-extending vehicle according to an embodiment of the present application;

FIG. 3 is a flowchart of another endurance prediction method of the extended range vehicle according to an embodiment of the present application;

FIG. 4 is a flowchart of a method of endurance prediction of a further range-extending vehicle according to an embodiment of the present application;

FIG. 5 is a flowchart of a method of endurance prediction of a further range-extending vehicle according to an embodiment of the present application;

fig. 6 is a block diagram of a endurance predicting apparatus of an extended range vehicle according to an embodiment of the present application;

fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

Fig. 1 shows a schematic diagram of an exemplary system architecture to which the technical solution of an embodiment of the present invention may be applied.

As shown in fig. 1, the system architecture 100 may include a first vehicle end 101, a second vehicle end 102, a third vehicle end 103, a network 104, and a server 105. The network 104 is a medium used to provide a communication link between the first vehicle end 101, the second vehicle end 102, the third vehicle end 103, and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

It should be understood that the number of clients, networks, and servers in fig. 1 is merely illustrative. There may be any number of vehicle ends, networks, and servers, as desired for implementation. For example, the server 105 may be a server cluster formed by a plurality of servers.

The user may interact with the server 105 through the network 104 using the first vehicle end 101, the second vehicle end 102, the third vehicle end 103, to receive or transmit data, etc. The first vehicle end 101, the second vehicle end 102, and the third vehicle end 103 may be various electronic devices mounted on the vehicle for receiving or transmitting data.

The server 105 may be a cloud of internet of vehicles providing various services. For example, the server 105 may determine the energy consumption data corresponding to each kilometer of each component by acquiring the current power data of each component of the extended-range vehicle and applying the energy consumption weight distribution rule from the first vehicle end 101, the second vehicle end 102 or the third vehicle end 103, so as to more accurately predict the range of the extended-range vehicle, so that the extended-range vehicle can perform driving route planning and charging station searching according to the predicted range, and driving efficiency and user experience are greatly improved. More accurate driving mileage prediction and planning, unnecessary charging behavior is avoided, energy is saved, and environmental pollution caused by battery production and treatment is reduced.

The following describes in detail a method and an apparatus for predicting cruising of a range-extending vehicle according to an embodiment of the present application with reference to the accompanying drawings.

Fig. 2 is a flowchart of a method for predicting the endurance of a range-extended vehicle according to an embodiment of the present application, where the method provided in the embodiment of the present application may be executed by any electronic device having a computer processing capability, for example, the server or the vehicle end.

As shown in fig. 2, the endurance prediction method of the extended range vehicle includes steps S210 to S240.

In step S210, current power data of a plurality of components in the extended range vehicle is acquired.

In step S220, energy consumption weight distribution is performed on each component through an energy consumption weight distribution rule based on current power data of a plurality of components in the extended range vehicle, so as to obtain energy consumption weights of each component.

In step S230, energy consumption data corresponding to each component per kilometer is determined according to current power data of a plurality of components in the extended range vehicle and energy consumption weights corresponding to each component.

In step S240, the endurance mileage of the extended-range vehicle is predicted according to the energy consumption data corresponding to each kilometer of each component.

According to the method, the current power data of each part of the range-extending vehicle can be obtained, and the energy consumption weight distribution rule can be applied, so that the energy consumption data corresponding to each kilometer of each part can be determined, the range of the range-extending vehicle can be predicted more accurately, the range-extending vehicle can conduct driving route planning and charging station searching according to the predicted range, and driving efficiency and user experience are improved greatly. More accurate driving mileage prediction and planning, unnecessary charging behavior is avoided, energy is saved, and environmental pollution caused by battery production and treatment is reduced.

In some embodiments, the plurality of components of the extended range vehicle include, in particular, an internal combustion engine, an electric motor, and a battery pack. They each take on a different role in the system, the internal combustion engine being responsible for supplying charging energy to the battery pack, the electric motor driving the vehicle using the electric energy of the battery pack. The current power data of each component is the current power data of the internal combustion engine, the power data of the motor, and the power data of the battery pack, respectively. These data are acquired by sensors for the respective power data mounted at corresponding locations of the components. Specifically, the power sensor of the internal combustion engine detects the power generated by the internal combustion engine when burning fuel; the power sensor of the motor detects the power required by the motor to convert the electric energy into power; the power sensor of the battery pack detects the power of the battery pack when the battery pack is supplied with electric power. After the power data are obtained, energy consumption weights can be distributed to each component according to the energy consumption weight distribution rule, and then the energy consumption data corresponding to each component per kilometer can be determined. Finally, predicting the endurance mileage of the extended-range vehicle based on the energy consumption data. The method can not only acquire the energy consumption condition of the vehicle in real time, but also enable the energy management to be more intelligent by distributing the energy consumption weights of the components, and effectively improve the accuracy of the range prediction of the range-extending vehicle.

In some embodiments, the energy consumption model for predicting range of the extended range vehicle uses processing logic corresponding to the energy consumption weight allocation rule described above when processing the power data. The processing logic may be configured to assign energy consumption weights to the internal combustion engine, the electric motor, and the battery pack in the extended range vehicle based on current power data of those components. The distribution of the energy consumption weights reflects the proportional relation of the components in the whole vehicle energy consumption, which is particularly important for judging which components are main contributors of the vehicle energy consumption, and is also beneficial to optimizing the energy use, so that the running of the vehicle is more efficient. In this example, the energy consumption model may be obtained by training the multi-layer perceptron based on historical power data of a corresponding vehicle type of the range-extended vehicle. A multi-layer perceptron is an artificial neural network that can use historical data to learn and gradually optimize predictions of future conditions. In the training process, the network weight is adjusted according to the historical data so as to reduce the prediction error as much as possible.

The following describes the training process of the energy consumption model specifically by using the embodiment described in fig. 3, and fig. 3 is a flowchart of another endurance prediction method of the extended-range vehicle according to the embodiment of the present application.

As shown in fig. 3, the method further includes steps S310 to S330 before acquiring current power data of a plurality of components in the extended range vehicle.

In step S310, the vehicle type of the extended-range vehicle is determined.

In step S320, corresponding historical power data including engine power data, motor power data, and battery pack power data is acquired according to the vehicle model.

In step S330, the multi-layer perceptron is trained based on the historical power data including the internal combustion engine power data, the motor power data and the battery pack power data, and an energy consumption model corresponding to the vehicle model is obtained.

The method can determine the vehicle type of the extended range vehicle, and acquire corresponding historical power data according to the vehicle type, wherein the historical power data comprises power data of an internal combustion engine, power data of a motor and power data of a battery pack. And training the multi-layer perceptron based on historical power data including power data of the internal combustion engine, power data of the motor and power data of the battery pack to obtain an energy consumption model corresponding to the vehicle type, wherein the energy consumption model can predict the endurance mileage of the extended-range vehicle under the running condition according to the real-time power data, thereby helping a driver to carry out better running planning and improving the energy utilization efficiency.

In some embodiments, determining the vehicle type of the extended range vehicle may determine the vehicle type of the extended range vehicle via factory information of the vehicle. For example, the factory information of a vehicle generally includes detailed information such as the manufacturer, model number, date of manufacture, frame number, engine model number, and configuration of the vehicle. Among these pieces of information, information such as manufacturer and model number may directly indicate the model of the vehicle. Therefore, the vehicle type of the extended range vehicle can be accurately judged as long as the factory information of the extended range vehicle is obtained through corresponding equipment or interfaces. After the model of the vehicle is determined, historical power data corresponding to the model can be queried according to the model, and basic data can be provided for subsequent prediction of the endurance mileage of the vehicle. The mode of determining the vehicle type by adopting the factory information of the vehicle is convenient and reliable, the vehicle type is not required to be judged manually, the prediction error caused by manual misjudgment is avoided, and the accuracy of the range-extending vehicle endurance mileage prediction is improved.

In some embodiments, after determining a vehicle type of the extended range vehicle, historical power data corresponding to the vehicle type needs to be acquired. These historical power data typically include power data of the internal combustion engine, power data of the electric motor, and power data of the battery pack. Engine power data may refer to power data generated by the engine during vehicle operation, including power output of the engine under different conditions (e.g., different speeds, loads, etc.). These data can reflect the energy consumption of the internal combustion engine during driving. The power data of the motor may refer to power data generated by the motor during driving of the vehicle. These data may reflect the power consumption of the motor in various driving states. Including the power output of the motor in different states such as start, travel, brake, etc. The power data of the battery pack may refer to power supply data of the battery pack during running of the vehicle. These data may reflect the energy consumption of the battery pack, including power variations during power supply and charging. The historical power data is usually detected by a system of the vehicle in the actual running process, accurately reflects the actual working conditions of the internal combustion engine, the motor and the battery pack in the running process of the vehicle, and provides basic data for building the vehicle energy consumption model.

In some embodiments, the historical power data may include power data of an internal combustion engine, power data of an electric motor, and power data of a battery pack, which are basic data for training the multi-layer perceptron. The multi-layer perceptron is a deep learning model and is also an artificial neural network, and can learn a complex mode in data through training and predict. During the training process, the multi-layer perceptron can learn based on historical power data, automatically adjust internal parameters, and hopefully minimize prediction errors. In particular operation, historical power data is input to a multi-layer perceptron, which may learn and train based on the data. The multi-layer perceptron may self-adjust during training to more accurately predict energy consumption of the vehicle in the face of new power data. After training is completed, a model for predicting the energy consumption of the range-extending vehicle according to the current power data is formed. The energy consumption model can be used for more accurately predicting the energy consumption according to the power data of each part of the vehicle collected in real time. According to the method, through a machine learning technology, the model can automatically learn and adapt to the energy consumption characteristics of different vehicle types, so that the prediction accuracy is improved, and the use efficiency and the user experience of the range-extended vehicle are improved.

In some embodiments, training the multi-layer perceptron based on historical power data including engine power data, motor power data, and battery pack power data, the deriving the energy consumption model includes: converting the power data of the internal combustion engine, the power data of the motor and the power data of the battery pack into a feature matrix corresponding to the power data of the internal combustion engine, a feature matrix corresponding to the power data of the motor and a feature matrix corresponding to the power data of the battery pack respectively; respectively carrying out dot product operation with initial energy consumption weights corresponding to hidden layers of the multi-layer perceptron based on a feature matrix corresponding to power data of the internal combustion engine, a feature matrix corresponding to power data of the motor and a feature matrix corresponding to power data of the battery pack, and carrying out nonlinear transformation processing on the results of each dot product operation to obtain energy consumption data of the internal combustion engine, energy consumption data of the motor and energy consumption data of the battery pack; and calculating loss based on the energy consumption data of the internal combustion engine, the energy consumption data of the motor and the energy consumption data of the battery pack, and reversely updating the initial energy consumption weight corresponding to the hidden layer based on the loss to obtain an energy consumption model.

Based on the foregoing embodiments, the internal combustion engine power data, the motor power data, and the battery pack power data are processed by being converted into the feature matrix. These feature matrices contain key information for the power data of each component to facilitate subsequent computation and analysis. First, power data of the internal combustion engine, power data of the electric motor, and power data of the battery pack are converted into corresponding feature matrices. Feature matrices are a common data representation, each row representing a sample (i.e., power data representing a period of time in this application), and each column representing a feature (e.g., power value). And then, carrying out dot product operation on the feature matrixes and the corresponding initial energy consumption weights in the hidden layers of the multi-layer perceptron. Dot product operation is to multiply and sum corresponding elements, and is a common matrix operation mode. After the dot product operation is completed, nonlinear transformation processing is further carried out on the result, so that the nonlinear expression capacity of the model can be increased. After this series of operations, the energy consumption data of the internal combustion engine, the energy consumption data of the motor, and the energy consumption data of the battery pack can be obtained. Further, the loss is calculated based on the above calculated energy consumption data. The loss is the difference between the model predicted energy consumption data and the actual energy consumption data. The smaller the calculation result of the loss function, the higher the accuracy of the representative model prediction. Finally, the initial energy consumption weights corresponding to the hidden layers are updated back based on the calculated losses, which is achieved by a back propagation algorithm. The back propagation algorithm is a learning algorithm commonly used in the neural network, and the weight of the hidden layer is continuously adjusted through the algorithm, so that the prediction result of the model is more similar to actual energy consumption data. Through the series of processing and calculation, an energy consumption model is obtained and is used for predicting the endurance mileage of the extended-range vehicle.

In some embodiments, performing energy consumption weight distribution on each component through an energy consumption weight distribution rule based on current power data of a plurality of components in the extended range vehicle, and obtaining the energy consumption weight of each component includes: inputting current power data of an internal combustion engine, current power data of a motor and current power data of a battery pack in the range-extending vehicle into the energy consumption model; acquiring a mapping relation between power data and energy consumption weight from a hidden layer in an energy consumption model; and determining the energy consumption weight corresponding to the current power data of the internal combustion engine, the energy consumption weight corresponding to the current power data of the motor and the energy consumption weight corresponding to the current power data of the battery pack according to the mapping relation between the power data and the energy consumption weight. For example, it is first necessary to input current power data of the internal combustion engine, current power data of the electric motor, and current power data of the battery pack in the extended-range vehicle to the energy consumption model obtained by the training method described above. In the energy consumption model, the ability to fit and learn these input data is provided, so the range of the vehicle can be predicted from the current power data. After the current power data of the energy consumption model are converted into the corresponding feature matrix, the mapping relation between the power data and the energy consumption weight can be obtained from the hidden layer of the energy consumption model. The mapping relation is used for describing the distribution situation of energy consumption weights of all the components corresponding to the specific power condition of the vehicle. After the mapping relation is obtained, the energy consumption weight corresponding to the current power data of the internal combustion engine, the energy consumption weight corresponding to the current power data of the motor and the energy consumption weight corresponding to the current power data of the battery pack can be determined. These energy consumption weight data illustrate the contribution of the individual components to the overall energy consumption in the current driving state. Through the steps, the running condition of the vehicle can be analyzed in real time, and the endurance mileage can be accurately predicted, so that a driver is helped to make an optimal running decision.

In some embodiments, determining energy consumption data for each component per kilometer based on current power data for a plurality of components in the extended range vehicle and energy consumption weights for each component comprises: converting the current power data of the internal combustion engine, the current power data of the motor and the current power data of the battery pack into a characteristic matrix of the current power data of the internal combustion engine, a characteristic matrix corresponding to the current power data of the motor and a characteristic matrix corresponding to the current power data of the battery pack; according to the energy consumption weight vector corresponding to the current power data of the internal combustion engine and the current power data feature matrix of the internal combustion engine, calculating the energy consumption data corresponding to each kilometer of the internal combustion engine; according to the energy consumption weight vector corresponding to the current power data of the motor and the current power data feature matrix of the motor, calculating the energy consumption data corresponding to each kilometer of the motor; and calculating the energy consumption data corresponding to each kilometer of the battery pack according to the energy consumption weight vector corresponding to the current power data of the battery pack and the current power data feature matrix of the battery pack. For example, it is first necessary to convert current power data of an internal combustion engine, an electric motor, and a battery pack of the extended range vehicle into corresponding feature matrices. The feature matrix is used for representing a geometric property and a distribution rule of the data, and the data can be visualized to view the interrelationship between the data, and meanwhile, the feature matrix is also provided for the machine learning model to analyze and calculate. Then, the energy consumption weight vector corresponding to the current power data of the internal combustion engine, the motor and the battery pack can be obtained through the mapping relation obtained from the energy consumption model. These energy consumption weight vectors represent the proportion of the individual components in the overall energy consumption, i.e. the importance of the individual components. And carrying out product calculation on the current power data characteristic matrix of the internal combustion engine and the corresponding energy consumption weight vector to obtain the corresponding energy consumption data of the internal combustion engine per kilometer. Likewise, the energy consumption data per kilometer of the motor and the battery pack can be calculated in the same manner. The corresponding energy consumption data of each kilometer, namely the energy consumption of the extended-range vehicle in a real-time driving state. The energy consumption data of each kilometer of all key components are obtained through the steps, and the data are key bases for accurately predicting the driving mileage of the extended range vehicle.

Fig. 4 is a flowchart of a method for predicting the endurance of a range-extending vehicle according to another embodiment of the present application, and as shown in the drawing, the method may further include step S410 and step S420.

In step S410, factory configuration information of the extended range vehicle is obtained according to the frame identifier of the extended range vehicle.

In step S420, the range of the extended-range vehicle is updated according to the factory configuration information of the extended-range vehicle and the historical driving behavior data of the extended-range vehicle, so as to obtain the target range of the extended-range vehicle.

According to the method, the factory configuration information of the extended range vehicle can be obtained according to the frame identification of the extended range vehicle, and the range of the extended range vehicle is optimized and updated according to the factory configuration information of the extended range vehicle and the historical driving behavior data of the extended range vehicle to obtain the target range of the extended range vehicle, so that the accuracy of the range of the extended range vehicle can be further improved.

In some embodiments, the factory configuration information includes a factory time of the vehicle, and the service life of the extended range vehicle may be determined according to the factory time. And then, the service life of the extended-range vehicle is combined with the historical driving behavior data of the extended-range vehicle, and the endurance mileage of the extended-range vehicle is optimized and updated. The historical driving behavior data includes various state data of the vehicle during past traveling, such as acceleration frequency, deceleration frequency, braking frequency, and the like. In this embodiment, an optimization rule of the vehicle range can be configured in advance according to the service life of the extended-range vehicle and the historical driving behavior data, so that the accuracy of the extended-range vehicle range can be further improved.

Fig. 5 is a flowchart of another method for predicting the endurance of the extended range vehicle according to an embodiment of the present application, and as shown in the drawing, the method may further include step S510 and step S530.

In step S510, navigation information of the extended-range vehicle is acquired.

In step S520, weather information of the current position of the extended-range vehicle and travel path information of the extended-range vehicle are determined according to the navigation information of the extended-range vehicle

In step S530, the range of the extended-range vehicle is updated according to the weather information of the current location of the extended-range vehicle and the mapping relationship between the travel path information of the extended-range vehicle and the preset variable mileage, so as to obtain the target range of the extended-range vehicle, wherein the preset variable mileage includes the increased mileage or the decreased mileage.

According to the method, the weather information of the current position of the extended-range vehicle and the driving path information of the extended-range vehicle can be determined according to the navigation information of the extended-range vehicle, then the range of the extended-range vehicle is updated according to the weather information of the current position of the extended-range vehicle and the driving path information of the extended-range vehicle, and the target range of the extended-range vehicle is obtained.

In some embodiments, the current position of the vehicle and the predicted driving path are determined by acquiring navigation information of the extended-range vehicle. The acquisition of such information may generally be achieved by means of a navigation device or a positioning system on board the vehicle. The predicted driving path can comprise information such as the distance between the current position and the destination, road conditions, traffic conditions and the like, and the factors can influence the range of the extended-range vehicle. And then updating according to weather information of the current position of the range-extending vehicle. Weather changes have a great influence on the range vehicle and the endurance mileage. For example, in cold weather, the vehicle may need to expend more energy to maintain heating, potentially reducing the range of travel. Under the condition of high wind speed, wind resistance may increase, causing additional burden to a vehicle power system and affecting endurance mileage. The weather information of the current position of the extended-range vehicle and the driving path information of the extended-range vehicle are combined, so that the actual running state of the vehicle and the running condition to be encountered can be predicted more accurately, further optimization and updating are carried out on the range output by the energy consumption model according to the information, and the target range is more accurate. Therefore, for a driver, the target endurance mileage can provide an important decision basis for the driver, can predict whether to charge in advance or not, or modify an estimated driving path and the like, and is beneficial to improving the driving efficiency and the user experience.

Based on the foregoing embodiments, the endurance mileage of the vehicle may be updated according to the pre-configured weather information and travel path information and the pre-configured mapping relationship of the variable mileage (which may be an increased mileage or a decreased mileage). The mapping relationship may be preset. For example, if traveling on a downhill road section or in good weather conditions, the range of the vehicle is increased; conversely, if traveling on an uphill road section or under severe weather conditions, the range of the vehicle is reduced. In this embodiment, the mileage increase or mileage decrease may be set according to the actual application scenario, which is not limited herein.

Fig. 6 is a block diagram of a endurance prediction apparatus of an extended range vehicle according to an embodiment of the present application, and as shown in fig. 6, the endurance prediction apparatus 600 of an extended range vehicle includes an obtaining module 610, a weight allocation module 620, a determining module 630, and a prediction module 640.

Specifically, the acquiring module 610 is configured to acquire current power data of a plurality of components in the extended-range vehicle.

The weight distribution module 620 is configured to perform energy consumption weight distribution on each component according to an energy consumption weight distribution rule based on current power data of a plurality of components in the extended range vehicle, so as to obtain energy consumption weights of each component.

And the determining module 630 is configured to determine energy consumption data corresponding to each component per kilometer according to current power data of a plurality of components in the extended range vehicle and energy consumption weights corresponding to each component.

And the prediction module 640 is used for predicting the endurance mileage of the extended-range vehicle according to the energy consumption data corresponding to each kilometer of each component.

The endurance prediction apparatus 600 of the extended-range vehicle can acquire current power data of each component of the extended-range vehicle and apply an energy consumption weight distribution rule to determine energy consumption data corresponding to each kilometer of each component, so as to more accurately predict the endurance mileage of the extended-range vehicle, so that the extended-range vehicle can carry out driving route planning and charging station searching according to the predicted endurance mileage, and driving efficiency and user experience are greatly improved. More accurate driving mileage prediction and planning, unnecessary charging behavior is avoided, energy is saved, and environmental pollution caused by battery production and treatment is reduced.

In some embodiments, prior to obtaining current power data for a plurality of components in the extended range vehicle, the endurance prediction apparatus 600 of the extended range vehicle is further configured to: determining the vehicle type of the extended range vehicle; acquiring corresponding historical power data according to a vehicle type, wherein the historical power data comprises power data of an internal combustion engine, power data of a motor and power data of a battery pack; and training the multi-layer perceptron based on the historical power data including the power data of the internal combustion engine, the power data of the motor and the power data of the battery pack to obtain an energy consumption model corresponding to the vehicle type.

In some embodiments, training the multi-layer perceptron based on historical power data including internal combustion engine power data, motor power data, and battery pack power data, the deriving the energy consumption model includes: converting the power data of the internal combustion engine, the power data of the motor and the power data of the battery pack into a feature matrix corresponding to the power data of the internal combustion engine, a feature matrix corresponding to the power data of the motor and a feature matrix corresponding to the power data of the battery pack respectively; respectively carrying out dot product operation with initial energy consumption weights corresponding to hidden layers of the multi-layer perceptron based on a feature matrix corresponding to power data of the internal combustion engine, a feature matrix corresponding to power data of the motor and a feature matrix corresponding to power data of the battery pack, and carrying out nonlinear transformation processing on the results of each dot product operation to obtain energy consumption data of the internal combustion engine, energy consumption data of the motor and energy consumption data of the battery pack; and calculating loss based on the energy consumption data of the internal combustion engine, the energy consumption data of the motor and the energy consumption data of the battery pack, and reversely updating the initial energy consumption weight corresponding to the hidden layer based on the loss to obtain an energy consumption model.

In some embodiments, the weight distribution module 620 is configured to: inputting current power data of an internal combustion engine, current power data of a motor and current power data of a battery pack in the range-extending vehicle into the energy consumption model; acquiring a mapping relation between power data and energy consumption weight from a hidden layer in an energy consumption model; and determining the energy consumption weight corresponding to the current power data of the internal combustion engine, the energy consumption weight corresponding to the current power data of the motor and the energy consumption weight corresponding to the current power data of the battery pack according to the mapping relation between the power data and the energy consumption weight.

In some embodiments, the determining module 630: converting the current power data of the internal combustion engine, the current power data of the motor and the current power data of the battery pack into a characteristic matrix of the current power data of the internal combustion engine, a characteristic matrix corresponding to the current power data of the motor and a characteristic matrix corresponding to the current power data of the battery pack; according to the energy consumption weight vector corresponding to the current power data of the internal combustion engine and the current power data feature matrix of the internal combustion engine, calculating the energy consumption data corresponding to each kilometer of the internal combustion engine; according to the energy consumption weight vector corresponding to the current power data of the motor and the current power data feature matrix of the motor, calculating the energy consumption data corresponding to each kilometer of the motor; and calculating the energy consumption data corresponding to each kilometer of the battery pack according to the energy consumption weight vector corresponding to the current power data of the battery pack and the current power data feature matrix of the battery pack.

In some embodiments, prior to obtaining current power data for a plurality of components in the extended range vehicle, the endurance prediction apparatus 600 of the extended range vehicle is further configured to: acquiring factory configuration information of the extended range vehicle according to the frame identification of the extended range vehicle; and updating the range of the extended-range vehicle according to the factory configuration information of the extended-range vehicle and the historical driving behavior data of the extended-range vehicle to obtain the target range of the extended-range vehicle.

In some embodiments, prior to obtaining current power data for a plurality of components in the extended range vehicle, the endurance prediction apparatus 600 of the extended range vehicle is further configured to: acquiring navigation information of the extended range vehicle; according to the navigation information of the extended-range vehicle, weather information of the current position of the extended-range vehicle and travel path information of the extended-range vehicle are determined; and updating the range of the range-increasing vehicle according to the weather information of the current position of the range-increasing vehicle and the mapping relation between the travel path information of the range-increasing vehicle and the preset variable range, so as to obtain the target range of the range-increasing vehicle, wherein the preset variable range comprises the increased range or the decreased range.

Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application, and as shown in fig. 7, an electronic device 700 of the embodiment includes: a processor 710, a memory 720, and a computer program 730 stored in the memory 720 and executable on the processor 710. The steps of the various method embodiments described above are implemented by processor 710 when executing computer program 730. Alternatively, the processor 710, when executing the computer program 730, performs the functions of the modules in the apparatus embodiments described above.

The electronic device 700 may be a desktop computer, a notebook computer, a palm computer, a cloud server, or the like. The electronic device 700 may include, but is not limited to, a processor 710 and a memory 720. It will be appreciated by those skilled in the art that fig. 7 is merely an example of an electronic device 700 and is not limiting of the electronic device 700 and may include more or fewer components than shown, or different components.

The processor 710 may be a central processing unit (Central Processing Unit, CPU) or other general purpose processor, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like.

The memory 720 may be an internal storage unit of the electronic device 700, for example, a hard disk or a memory of the electronic device 700. The memory 720 may also be an external storage device of the electronic device 700, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the electronic device 700. Memory 720 may also include both internal and external storage units of electronic device 700. The memory 720 is used to store computer programs and other programs and data required by the electronic device.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit.

The integrated module, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a readable storage medium (e.g., a computer readable storage medium). Based on such understanding, the present application implements all or part of the flow in the methods of the above embodiments, or may be implemented by a computer program to instruct related hardware, and the computer program may be stored in a computer readable storage medium, where the computer program may implement the steps of the respective method embodiments described above when executed by a processor. The computer program may comprise computer program code, which may be in source code form, object code form, executable file or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth.

The above embodiments are only for illustrating the technical solution of the present application, and are not limiting thereof; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.

Claims (10)

1. The endurance prediction method of the extended-range vehicle is characterized by comprising the following steps of:

acquiring current power data of a plurality of components in the range-extending vehicle;

based on current power data of a plurality of components in the range-extending vehicle, energy consumption weight distribution is carried out on each component through an energy consumption weight distribution rule, so that energy consumption weights of each component are obtained;

determining energy consumption data corresponding to each component per kilometer according to current power data of a plurality of components in the range-extending vehicle and energy consumption weights corresponding to each component;

and predicting the endurance mileage of the range-extended vehicle according to the energy consumption data corresponding to each kilometer of each component.

2. The method of claim 1, wherein prior to acquiring current power data for a plurality of components in the extended range vehicle, the method further comprises:

determining the vehicle type of the range-extending vehicle;

acquiring corresponding historical power data according to the vehicle type, wherein the historical power data comprises power data of an internal combustion engine, power data of a motor and power data of a battery pack;

and training the multi-layer perceptron based on the historical power data including the power data of the internal combustion engine, the power data of the motor and the power data of the battery pack to obtain an energy consumption model corresponding to the vehicle type.

3. The method of claim 2, wherein training a multi-layer perceptron based on the historical power data including engine power data, motor power data, and battery pack power data, the deriving an energy consumption model comprises:

converting the internal combustion engine power data, the motor power data and the battery pack power data into a feature matrix corresponding to the internal combustion engine power data, a feature matrix corresponding to the motor power data and a feature matrix corresponding to the battery pack power data respectively;

performing dot product operation on the basis of the feature matrix corresponding to the power data of the internal combustion engine, the feature matrix corresponding to the power data of the motor and the feature matrix corresponding to the power data of the battery pack respectively with the initial energy consumption weight corresponding to the hidden layer of the multi-layer perceptron, and performing nonlinear transformation processing on the result of each dot product operation to obtain the energy consumption data of the internal combustion engine, the energy consumption data of the motor and the energy consumption data of the battery pack;

and calculating loss based on the energy consumption data of the internal combustion engine, the energy consumption data of the motor and the energy consumption data of the battery pack, and reversely updating the initial energy consumption weight corresponding to the hidden layer based on the loss to obtain the energy consumption model.

4. The method of claim 3, wherein assigning energy consumption weights to each of the components via an energy consumption weight assignment rule based on current power data of a plurality of components in the extended range vehicle, the obtaining the energy consumption weights for each of the components comprising:

inputting current power data of an internal combustion engine, current power data of a motor and current power data of a battery pack in the range-extending vehicle into the energy consumption model;

acquiring a mapping relation between power data and energy consumption weight from a hidden layer in the energy consumption model;

and determining the energy consumption weight corresponding to the current power data of the internal combustion engine, the energy consumption weight corresponding to the current power data of the motor and the energy consumption weight corresponding to the current power data of the battery pack according to the mapping relation between the power data and the energy consumption weight.

5. The method of claim 4, wherein determining energy consumption data for each of the components per kilometer based on current power data for a plurality of components in the extended range vehicle and energy consumption weights for each of the components comprises:

converting the current power data of the internal combustion engine, the current power data of the motor and the current power data of the battery pack into a characteristic matrix of the current power data of the internal combustion engine, a characteristic matrix corresponding to the current power data of the motor and a characteristic matrix corresponding to the current power data of the battery pack;

According to the energy consumption weight vector corresponding to the current power data of the internal combustion engine and the current power data feature matrix of the internal combustion engine, calculating the energy consumption data corresponding to each kilometer of the internal combustion engine;

according to the energy consumption weight vector corresponding to the current power data of the motor and the current power data feature matrix of the motor, calculating the energy consumption data corresponding to each kilometer of the motor;

and calculating the energy consumption data corresponding to each kilometer of the battery pack according to the energy consumption weight vector corresponding to the current power data of the battery pack and the current power data feature matrix of the battery pack.

6. The method according to claim 1, wherein the method further comprises:

acquiring factory configuration information of the extended range vehicle according to the frame identification of the extended range vehicle;

and updating the range of the extended-range vehicle according to the factory configuration information of the extended-range vehicle and the historical driving behavior data of the extended-range vehicle to obtain the target range of the extended-range vehicle.

7. The method according to claim 1, wherein the method further comprises:

acquiring navigation information of the extended range vehicle;

determining weather information of the current position of the extended-range vehicle and travel path information of the extended-range vehicle according to the navigation information of the extended-range vehicle;

And updating the range of the range-increasing vehicle according to the weather information of the current position of the range-increasing vehicle and the mapping relation between the travel path information of the range-increasing vehicle and the preset variable range to obtain the target range of the range-increasing vehicle, wherein the preset variable range comprises an increased range or a decreased range.

8. A range prediction apparatus for a range-extending vehicle, the apparatus comprising:

the acquisition module is used for acquiring current power data of a plurality of components in the range-extending vehicle;

the weight distribution module is used for distributing energy consumption weights of the components according to an energy consumption weight distribution rule based on current power data of the components in the range-extending vehicle to obtain energy consumption weights of the components;

the determining module is used for determining the energy consumption data corresponding to each component per kilometer according to the current power data of a plurality of components in the range-extending vehicle and the energy consumption weights corresponding to each component;

and the prediction module is used for predicting the endurance mileage of the range-extended vehicle according to the energy consumption data corresponding to each kilometer of each component.

9. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 7 when the computer program is executed.

10. A readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any one of claims 1 to 7.