CN117184093A

CN117184093A - Fuel consumption estimation method, device, vehicle, storage medium and program product

Info

Publication number: CN117184093A
Application number: CN202311253695.XA
Authority: CN
Inventors: 季文博; 曾泽泉; 刘洪延; 马力戈
Original assignee: FAW Jiefang Automotive Co Ltd
Current assignee: FAW Jiefang Automotive Co Ltd
Priority date: 2023-09-26
Filing date: 2023-09-26
Publication date: 2023-12-08

Abstract

The application relates to a fuel consumption estimating method, a fuel consumption estimating device, a vehicle and a storage medium. The method comprises the following steps: determining the driving mileage between the current position and the target position of the vehicle to be evaluated and the virtual road condition data between the current position and the target position through the established virtual road network; processing the virtual road condition data through a whole vehicle state prediction model, and predicting driving behaviors involved in the process of driving the vehicle to be evaluated from the current position to the target position; processing driving behaviors through a whole vehicle power demand model, and predicting engine power parameters involved in the process of driving the vehicle to be evaluated from the current position to the target position; and determining the predicted fuel consumption required by the vehicle to be evaluated to reach the target position according to the driving behavior, the engine power parameters and the driving mileage. The method can be used for fusing road characteristics, driving style and engine power parameters together and accurately reflecting the predicted fuel consumption required by the vehicle to be evaluated to reach the target position.

Description

Fuel consumption estimating method, device, vehicle, storage medium and program product

Technical Field

The application relates to the technical field of vehicle fuel consumption, in particular to a fuel consumption estimating method, a fuel consumption estimating device, a vehicle, a storage medium and a computer program product.

Background

With the development of urban traffic, more and more vehicles are put into use. The vehicle oil meter can only provide the volume of the residual oil quantity of the current oil tank for a driver, and the target driving mileage oil consumption cannot be estimated, so that the driver can only roughly judge according to own experience, and the situation that the engine is flameout due to oil shortage is easily caused.

At present, the related driving mileage oil consumption estimation method only takes the driving behavior of a driver and road condition information into consideration to conduct quantitative prediction, and cannot accurately calculate the oil quantity required by the vehicle to reach a destination.

Disclosure of Invention

In view of the foregoing, it is desirable to provide a fuel consumption estimating method, a fuel consumption estimating device, a vehicle, a storage medium, and a computer program product that can improve fuel consumption estimating accuracy.

In a first aspect, the present application provides a fuel consumption estimation method. The method comprises the following steps:

acquiring the current position of a vehicle to be evaluated and a target position to be driven to;

determining the driving mileage between the current position and the target position and the virtual road condition data between the current position and the target position through the established virtual road network;

Processing the virtual road condition data through a whole vehicle state prediction model, and predicting driving behaviors involved in the process of driving the vehicle to be evaluated from the current position to the target position;

processing the driving behavior through a whole vehicle power demand model, and predicting engine power parameters involved in the process of driving the vehicle to be evaluated from the current position to the target position;

and determining the predicted fuel consumption required by the vehicle to be evaluated to reach the target position according to the driving behavior, the engine power parameter and the driving mileage.

In a second aspect, the application further provides a fuel consumption estimating device. The device comprises:

the position acquisition module is used for acquiring the current position of the vehicle to be evaluated and the target position to be driven;

the virtual road condition determining module is used for determining the driving mileage between the current position and the target position and the virtual road condition data between the current position and the target position through the established virtual road network;

the driving behavior prediction module is used for processing the virtual road condition data through a whole vehicle state prediction model and predicting driving behaviors involved in the process of driving the vehicle to be evaluated from the current position to the target position;

The power parameter prediction module is used for processing the driving behavior through a whole vehicle power demand model and predicting engine power parameters involved in the process of driving the vehicle to be evaluated from the current position to the target position;

and the fuel consumption prediction module is used for determining the predicted fuel consumption required by the vehicle to be evaluated to reach the target position according to the driving behavior, the engine power parameter and the driving mileage.

In one embodiment, the virtual road network comprises a plurality of virtual paths, and each virtual path is composed of a plurality of virtual path points; the virtual road condition determining module is further configured to determine a target virtual path in the built virtual road network according to the current position and the target position; determining mileage between any two adjacent virtual path points in the target virtual path; and determining the driving mileage between the current position and the target position according to the mileage between any two adjacent virtual path points in the target virtual path.

In one embodiment, each virtual path point corresponds to virtual road condition data; the driving behavior prediction module is further configured to process virtual road condition data of each virtual path point in the target virtual path through a whole vehicle state prediction model, and predict and obtain driving behaviors corresponding to each virtual path point in the target virtual path.

In one embodiment, the engine power parameters include an engine speed, an engine torque and a specific fuel consumption of the engine, and the power parameter prediction module is further configured to process driving behaviors corresponding to each virtual path point through a whole vehicle power demand model, and predict to obtain the engine speed and the engine torque corresponding to each virtual path point; and determining the specific fuel consumption of the vehicle to be evaluated at each virtual path point according to the engine speed and the engine torque corresponding to each virtual path point.

In one embodiment, the driving behavior includes a predicted vehicle speed, and the fuel consumption prediction module is further configured to determine a virtual sub-path based on each adjacent two virtual path points in the target virtual path; determining a predicted running duration corresponding to each virtual sub-path according to the predicted vehicle speed of the virtual path point included in each virtual sub-path and the mileage of each virtual sub-path; determining predicted fuel consumption corresponding to each virtual sub-path according to the predicted driving time length corresponding to each virtual sub-path and the engine power parameters of the virtual path points included in each virtual sub-path; and determining the predicted fuel consumption required by the vehicle to be evaluated to reach the target position according to the predicted fuel consumption corresponding to each virtual sub-path.

In one embodiment, the virtual road condition determining module is further configured to collect real road condition data when the vehicle travels at different sampling points of the real road section; clustering the positions of the sampling points to obtain a plurality of clustering sets; respectively taking the clustering centers of each clustering set as virtual path points corresponding to the clustering centers; for any cluster set, determining virtual road condition data corresponding to virtual path points of the cluster set according to the real road condition data of all sampling points in the cluster set; and generating a virtual road section according to the virtual road condition data corresponding to each virtual path point, and constructing a virtual road network according to the generated virtual road section.

In one embodiment, the fuel consumption prediction module is further configured to generate fuel consumption prompt information according to the predicted fuel consumption; the fuel consumption prompt information is used for indicating the magnitude relation between the residual fuel quantity of the vehicle to be evaluated and the predicted fuel consumption; and carrying out audible and visual alarm under the condition that the fuel consumption prompt information is used for indicating that the residual fuel quantity of the vehicle to be evaluated is smaller than the predicted fuel consumption.

In a third aspect, the present application also provides a computer device. The computer equipment comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the oil consumption estimation method when executing the computer program.

In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the fuel consumption estimation method described above.

In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of the fuel consumption estimation method described above.

According to the fuel consumption estimating method, the fuel consumption estimating device, the vehicle, the storage medium and the computer program product, the driving mileage between the current position and the target position and the virtual road condition data between the current position and the target position are determined through the built virtual road network, the virtual road condition data are processed through the whole vehicle state estimating model, and the driving behavior involved in the process of the vehicle to be estimated from the current position to the target position is estimated. In the process, all the virtual road condition data between the current position and the target position are directly obtained through the virtual road network, so that the road characteristics which affect the oil consumption comprehensively and accurately can be obtained, the virtual road condition data are processed through the whole vehicle state prediction model, more accurate driving behaviors can be obtained, and the combination of the road characteristics and the driving behaviors is realized. And then, the driving behavior is processed through the whole vehicle power demand model, and engine power parameters involved in the process that the vehicle to be evaluated runs from the current position to the target position are predicted. In the process, the driving behavior is processed through the whole vehicle power demand model, so that the relation between the driving behavior and the engine power parameters can be obtained, and the combination of road characteristics, the driving behavior and the engine power parameters of the vehicle to be evaluated is realized. And finally, determining the predicted fuel consumption required by the vehicle to be evaluated to reach the target position according to the driving behavior, the engine power parameter and the driving mileage. The finally obtained predicted fuel consumption is estimated based on the multidimensional data, so that the determined predicted fuel consumption is more accurate. In general, the method fuses road characteristics, driving style and engine power parameters together through real-time interaction of the virtual road network, the whole vehicle state prediction model and the whole vehicle power demand model, and accurately reflects the predicted fuel consumption required by the vehicle to be evaluated to reach the target position.

Drawings

FIG. 1 is a diagram of an application environment of a method for estimating oil consumption in one embodiment;

FIG. 2 is a flow chart of a method for estimating oil consumption according to an embodiment;

FIG. 3 is a schematic diagram of a target virtual path in one embodiment;

FIG. 4 is a flowchart of an algorithm corresponding to the oil consumption estimation method in one embodiment;

FIG. 5 is a block diagram illustrating an apparatus for estimating fuel consumption according to an embodiment;

fig. 6 is an internal structural view of the vehicle in one embodiment.

Detailed Description

The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.

The fuel consumption estimation method provided by the embodiment of the application can be applied to an application environment shown in figure 1. Wherein the vehicle 102 communicates with the internet of vehicles platform 104 via a network. The data storage system may store data that needs to be processed by the internet of vehicles platform 104. The data storage system may be integrated on the internet of vehicles platform 104 or may be located on a cloud or other server. The vehicle 102 acquires a current position of a vehicle to be evaluated and a target position to be traveled to; the vehicle 102 determines the driving mileage between the current position and the target position and the virtual road condition data between the current position and the target position through the built virtual road network; the vehicle 102 processes the virtual road condition data through a whole vehicle state prediction model and predicts the driving behavior involved in the process of driving the vehicle to be evaluated from the current position to the target position; the vehicle 102 processes driving behaviors through a whole vehicle power demand model, and predicts engine power parameters involved in the process of driving the vehicle to be evaluated from the current position to the target position; the vehicle 102 determines a predicted fuel consumption required for the vehicle under evaluation to reach the target location based on the driving behavior, the engine power parameters, and the mileage. The internet of vehicles platform 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.

In one embodiment, as shown in fig. 2, a fuel consumption estimating method is provided, and the method is applied to the vehicle in fig. 1 for illustration, and includes the following steps:

step 202, obtaining the current position of the vehicle to be evaluated and the target position to be driven.

The current position of the vehicle to be evaluated is acquired through a positioning device carried by the vehicle to be evaluated, and the target position is input by a driver driving the vehicle to be evaluated.

Specifically, a positioning device carried by the vehicle to be evaluated acquires the current position of the vehicle to be evaluated, and acquires the target position input by the driver.

And 204, determining the driving mileage between the current position and the target position and the virtual road condition data between the current position and the target position through the built virtual road network.

The virtual road network comprises a plurality of virtual paths, each virtual path is composed of a plurality of virtual path points, and each virtual path corresponds to a real path matched with each virtual path. The virtual paths in the virtual road network are communicated with each other, and a plurality of virtual paths reaching the same target position are provided.

Virtual path points refer to location marker points on the virtual path. The virtual path points may be custom or computationally determined. For example, the vehicle under evaluation determines a plurality of evenly distributed virtual path points at custom intervals. For example, the vehicle to be evaluated sets virtual path points with the number matched with the complexity according to the complexity of the real road condition; for example, the real road condition is a straight road, and correspondingly, fewer virtual path points can be set; the real road condition is a winding road surface (or a road with a curvature larger than a preset curvature), and correspondingly, more virtual path points can be set. For example, the vehicle performs cluster analysis on a large number of sampling points, and uses a cluster center as a plurality of virtual path points.

The virtual road condition data refers to the road condition data of the virtual path point on the virtual path. The road condition data includes gradient, road curvature, road type and sampling time. The road type comprises a road, an urban road, a rural road, a factory and mine road, a forestry road, an examination road, a competition road, an automobile test road, a workshop channel, a school road and the like. The virtual road condition data is determined based on sampling data of the real road condition point corresponding to the virtual road condition point. Each virtual path point corresponds to virtual road condition data.

The driving distance between the current position and the target position refers to the driving distance between a first virtual path point corresponding to the current position and a second virtual path point corresponding to the target position in the virtual road network. Because a large number of virtual road condition points are needed for building a virtual road network, if virtual road condition data corresponding to any point on a real path are recorded into the virtual road network, the needed data storage resources are very large, the calculated amount is also very large, and the building of the virtual road network is not facilitated. Fig. 3 is a schematic diagram of a target virtual path in an embodiment, in fig. 3, points 1-2 represent projection points of the current position, and a virtual road condition point closest to the point is a virtual road condition point i+3.

Specifically, a vehicle to be evaluated acquires a built virtual road network from a vehicle networking platform, projects the current position and the target position of the vehicle to be evaluated into the virtual road network to obtain a current position projection point and a target position projection point, takes a virtual road condition point closest to the current position projection point as a first virtual path point corresponding to the current position in the virtual road network, takes the virtual road condition point closest to the target position projection point as a second virtual path point corresponding to the target position in the virtual road network, calculates a driving distance between the first virtual path point and the second virtual path point through the virtual road network, takes the driving distance as a driving mileage between the current position and the target position, takes virtual road condition data corresponding to the first virtual path point as virtual road condition data corresponding to the current position, and takes virtual road condition data corresponding to the second virtual path point as virtual road condition data corresponding to the target position.

And 206, processing the virtual road condition data through a whole vehicle state prediction model, and predicting the driving behavior involved in the process of driving the vehicle to be evaluated from the current position to the target position.

The whole vehicle state prediction model is a neural network model which is obtained by taking a large amount of historical road condition data as input and taking driving behaviors involved in the process of outputting a vehicle to be evaluated to reach a target position as targets for training. For example, the whole vehicle state prediction model is a model trained based on an LSTM neural network.

Driving behavior refers to various driving indexes of the vehicle to be evaluated when the vehicle to be evaluated is driven on the remaining road section. The driving index refers to driving parameters required by the running of the vehicle to be evaluated. For example, the driving index includes a predicted vehicle speed, a brake pedal opening, a clutch pedal opening, an accelerator pedal opening, a gear, and the like of the vehicle to be evaluated.

Specifically, the vehicle to be evaluated acquires a pre-trained whole vehicle state prediction model, takes virtual road condition data between the current position and the target position as input of the whole vehicle state prediction model, processes the virtual road condition data through the whole vehicle state prediction model, and predicts driving behaviors involved in the process of driving the vehicle to be evaluated from the current position to the target position.

In some embodiments, the training process of the whole vehicle state prediction model specifically includes the following steps:

generating a training sample based on a large amount of historical road condition data; generating a label of a training sample based on driving behaviors adapting to historical road condition data; training a whole vehicle state prediction model through a large number of training samples, and outputting predicted driving behaviors by the whole vehicle state prediction model; and updating parameters of the whole vehicle state prediction model according to the difference between the predicted driving behavior and the label of the training sample until the difference between the predicted driving behavior and the label of the training sample is smaller than a preset value, so as to obtain the trained whole vehicle state prediction model.

And step 208, processing driving behaviors through the whole vehicle power demand model, and predicting engine power parameters involved in the process of driving the vehicle to be evaluated from the current position to the target position.

The vehicle power demand model is a neural network model which is obtained by taking a large amount of driving behavior data as input and taking engine power parameters involved in the process of outputting a vehicle to be evaluated to reach a target position as a target for training. For example, the vehicle power demand model is a model based on DNN neural network training.

The engine power parameter refers to various power indexes of an engine of the vehicle to be evaluated when the vehicle to be evaluated runs on the rest road section. The power index refers to a power parameter corresponding to an engine on which the vehicle to be evaluated runs. For example, the power indicator may include parameters such as engine speed, engine torque, engine power, specific fuel consumption, etc.

Specifically, the vehicle to be evaluated acquires a pre-trained whole vehicle power demand model, takes driving behaviors involved in the process of driving to the target position predicted by the whole vehicle state prediction model as input of the whole vehicle power demand model, processes the driving behaviors through the whole vehicle power demand model, and predicts engine power parameters involved in the process of driving the vehicle to be evaluated from the current position to the target position.

In some embodiments, the training process of the whole vehicle power demand model specifically includes the following steps:

generating training samples based on a plurality of driving behaviors; generating a label of a training sample based on engine power parameters adapting driving behavior; training a whole vehicle power demand model through a large number of training samples, and outputting predicted engine power parameters by the whole vehicle power demand model; and updating parameters of the whole vehicle power demand model according to the difference between the predicted engine power parameters and the labels of the training samples until the difference between the predicted engine power parameters and the labels of the training samples is smaller than a preset value, so as to obtain the trained whole vehicle power demand model.

Step 210, determining the predicted fuel consumption required by the vehicle to be evaluated to reach the target position according to the driving behavior, the engine power parameter and the driving mileage.

The driving behavior, the engine power parameter and the driving mileage are mapped, and different mapping relations can be obtained by analyzing the relation among the driving behavior, the engine power parameter and the driving mileage at different angles. For example, the larger the driving index corresponding to the driving behavior, the larger the engine power parameter, and the larger the consumed fuel consumption under the same driving mileage. For example, the greater the mileage, the greater the engine power parameter, and the greater the fuel consumption, under the same driving behavior.

Specifically, the vehicle to be evaluated acquires driving behavior predicted by the whole vehicle state prediction model, engine power parameters predicted by the whole vehicle power demand model and driving mileage output by the virtual road network, and determines predicted fuel consumption required by the vehicle to be evaluated to reach a target position according to a mapping relation among the driving behavior, the engine power parameters and the driving mileage. And displaying the predicted fuel consumption by a large screen of the vehicle-mounted terminal of the vehicle to be evaluated, and realizing the fuel consumption mileage estimation function.

In the fuel consumption estimating method, the driving mileage between the current position and the target position and the virtual road condition data between the current position and the target position are determined through the built virtual road network, the virtual road condition data are processed through the whole vehicle state predicting model, and the driving behavior involved in the process of driving the vehicle to be estimated from the current position to the target position is predicted. In the process, all the virtual road condition data between the current position and the target position are directly obtained through the virtual road network, so that the road characteristics which affect the oil consumption comprehensively and accurately can be obtained, the virtual road condition data are processed through the whole vehicle state prediction model, more accurate driving behaviors can be obtained, and the combination of the road characteristics and the driving behaviors is realized. And then, the driving behavior is processed through the whole vehicle power demand model, and engine power parameters involved in the process that the vehicle to be evaluated runs from the current position to the target position are predicted. In the process, the driving behavior is processed through the whole vehicle power demand model, so that the relation between the driving behavior and the engine power parameters can be obtained, and the combination of road characteristics, the driving behavior and the engine power parameters of the vehicle to be evaluated is realized. And finally, determining the predicted fuel consumption required by the vehicle to be evaluated to reach the target position according to the driving behavior, the engine power parameter and the driving mileage. The finally obtained predicted fuel consumption is estimated based on the multidimensional data, so that the determined predicted fuel consumption is more accurate. In general, on the premise of adding a sensor, the method fuses road characteristics, driving style and engine power parameters together through real-time interaction of a virtual road network, a whole vehicle state prediction model and a whole vehicle power demand model, accurately reflects the predicted fuel consumption required by the vehicle to be evaluated to reach a target position, and further provides fueling guidance for a driver.

In one embodiment, determining the driving distance between the current location and the target location through the established virtual road network comprises the following steps:

1. and determining a target virtual path in the established virtual road network according to the current position and the target position.

The virtual path of the target is a virtual path selected by a driver, wherein the virtual path comprises a current position projection point, a target position projection point and the virtual path. For example, the virtual paths I1, I2, and I3 each include a current position projection point and a target position projection point, and the virtual path selected by the driver is the virtual path I1, and thus the virtual path I1 is the target virtual path.

Specifically, the vehicle to be evaluated projects the current position and the target position into a virtual road network respectively to obtain a current position projection point and a target position projection point, and a virtual path which comprises the current position projection point and the target position projection point and is selected by a driver is determined to be used as a target virtual path in the built virtual road network.

2. And determining the mileage between any two adjacent virtual path points in the target virtual path.

When the virtual road network is built, the virtual road condition data are obtained by collecting real road condition data of vehicles in running through different sampling points on a real road section, so that mileage between any two adjacent virtual path points can be determined according to sampling time and sampling speed corresponding to the two adjacent virtual path points. The sampling vehicle speed corresponding to the virtual path point can be determined according to the average vehicle speed value of different vehicles at the virtual path point, or can be determined according to the vehicle speed of the same vehicle at the virtual path point.

Specifically, the vehicle to be evaluated determines a plurality of virtual sub-paths in the target virtual path according to any two adjacent virtual path points in the target virtual path, and calculates mileage between the two adjacent virtual path points in each virtual sub-path section according to a corresponding algorithm.

In some embodiments, the vehicle to be evaluated determines the acceleration of the vehicle to be evaluated between any two adjacent virtual waypoints according to the vehicle speed corresponding to the two adjacent virtual waypoints; and determining the mileage between the two adjacent virtual path points according to the acceleration. The corresponding algorithm is as follows:

s is the mileage between two adjacent virtual path points; v (V) _i 、V _i+1 The vehicle speeds of two adjacent virtual route points are respectively.

3. And determining the driving mileage between the current position and the target position according to the mileage between any two adjacent virtual path points in the target virtual path.

In order to improve the estimation accuracy of mileage, the embodiment determines the mileage of the virtual sub-path between the current position and the target position in a sectional estimation mode, and accumulates the mileage of the virtual sub-path in the target virtual path to obtain the driving mileage between the current position and the target position.

Specifically, the vehicle to be evaluated accumulates mileage between any two adjacent virtual path points in the target virtual path to obtain the driving mileage between the current position and the target position.

In this embodiment, according to the current position and the target position, a target virtual path is determined in the built virtual road network, the mileage between any two adjacent virtual path points in the target virtual path is determined, and the mileage between any two adjacent virtual path points in the target virtual path is accumulated to obtain the driving mileage between the current position and the target position. According to the method, the mileage between any two adjacent virtual path points in the target virtual path is calculated in a segmented mode, so that the calculation accuracy of the mileage can be improved, the finally obtained driving mileage between the current position and the target position is more accurate, and more accurate basic data are provided for the follow-up calculation of the predicted fuel consumption required by the vehicle to be evaluated to reach the target position.

In one embodiment, each virtual waypoint corresponds to the existence of virtual road condition data. Processing the virtual road condition data through the whole vehicle state prediction model, predicting driving behaviors involved in the process of driving the vehicle to be evaluated from the current position to the target position, and comprising the following steps:

and processing the virtual road condition data of each virtual path point in the virtual path through the whole vehicle state prediction model, and predicting to obtain the driving behavior corresponding to each virtual path point in the virtual path.

Specifically, the vehicle to be evaluated inputs virtual road condition data of each virtual path point in the target virtual path into the whole vehicle state prediction model, and the whole vehicle state prediction model outputs driving behaviors corresponding to each virtual path point.

For example, fig. 3 is a schematic diagram of a target virtual path in an embodiment, a virtual road condition point corresponding to a current position is marked as i+3, a virtual path point corresponding to a target position is marked as I, and a plurality of virtual road condition points exist between the virtual road condition point i+3 and the virtual road condition point I. And inputting the virtual road condition data of the virtual road condition point i+3 into a whole vehicle state prediction model, and outputting driving behaviors corresponding to the virtual road condition point i+3 by the whole vehicle state prediction model. And sequentially inputting the virtual road condition data of each virtual road condition point into the whole vehicle state prediction model to obtain the driving behavior corresponding to each virtual road condition point.

In some embodiments, when factors such as the load of the vehicle to be evaluated, the driver, the vehicle configuration and the like are changed, the driver can clear the historical driving behaviors at regular intervals, and online learning and prediction are performed again according to the new driving behaviors, so that self-adaptive adjustment is realized, the prediction accuracy is improved, and the driver is scientifically guided to refuel in time.

In this embodiment, a plurality of virtual road condition points are set on a virtual path, and virtual road condition data of each virtual road condition point is processed through a whole vehicle state prediction model, so as to obtain driving behaviors corresponding to each virtual path point in the virtual path. In the above process, when the vehicle to be evaluated is at the current virtual road condition point, the driving behavior corresponding to the next virtual road condition point is predicted, on one hand, the neural network principle is combined, the driving behavior is predicted based on the virtual road condition data, so that the accuracy of predicting the driving behavior can be improved, and on the other hand, when the driving route of the vehicle to be evaluated is replaced, the updated virtual path can be adaptively predicted, and the driving behavior of the vehicle to be evaluated on the updated virtual path can be predicted.

In one embodiment, the engine power parameters include engine speed, engine torque, and specific fuel consumption of the engine. The driving behavior is processed through the whole vehicle power demand model, and engine power parameters involved in the process of driving the vehicle to be evaluated from the current position to the target position are predicted, and the method comprises the following steps:

the driving behavior corresponding to each virtual path point is processed through the whole vehicle power demand model, and the engine speed and the engine torque corresponding to each virtual path point are obtained through prediction; and determining the specific fuel consumption of the vehicle to be evaluated at each virtual path point according to the engine speed and the engine torque corresponding to each virtual path point.

The data corresponding relation at each virtual path point in the target virtual path is as follows: each virtual path point corresponds to virtual path data, predicted driving behavior, and predicted engine parameters.

The specific fuel consumption is an evaluation index of the engine efficiency, and represents the fuel consumption rate, specifically refers to the mass of fuel consumed in 1h per 1kw of effective power emitted by the engine, and is expressed in g/(kw.h). The specific fuel consumption can be calculated by a specific fuel consumption calculation formula, or the specific fuel consumption matched with the engine speed and the engine torque is searched in an engine power characteristic curve, wherein the left ordinate of the engine power characteristic curve is the engine output torque, the abscissa is the engine speed, and the right ordinate is the average effective pressure of an engine acting cylinder.

Specifically, the vehicle to be evaluated inputs driving behaviors corresponding to virtual path points in a target virtual path into a whole vehicle power demand model respectively, and engine speeds and engine torques corresponding to the virtual path points are predicted through the whole vehicle power demand model respectively; and substituting the engine speed and the engine torque corresponding to each virtual path point into an engine power characteristic curve respectively by the vehicle to be evaluated, and determining the specific fuel consumption of each virtual path point and the engine speed and the engine torque.

In this embodiment, the driving behaviors corresponding to the virtual path points are respectively processed through the vehicle power demand model, so that the engine power parameters corresponding to the virtual path points are predicted, and compared with the engine power parameters corresponding to the whole section of the traditional prediction target virtual path, the method combines the neural network principle, predicts the engine power parameters based on the driving behaviors, and can improve the accuracy of predicting the engine power parameters.

In one embodiment, determining the predicted fuel consumption required by the vehicle to be evaluated to reach the target position according to driving behavior, engine power parameters and driving mileage comprises the following steps:

1. a virtual sub-path is determined based on each adjacent two virtual path points in the target virtual path.

The target virtual path comprises a plurality of virtual path points, and each two adjacent virtual path points divide the target virtual path into a virtual sub-path. For example, in fig. 3, virtual path point i and virtual path point i+1 divide the target virtual path into one virtual sub-path.

Specifically, the vehicle to be evaluated takes every two adjacent virtual path points in the target virtual path as two end points of the virtual sub-path, so that a plurality of virtual sub-paths are obtained.

2. And determining the predicted running duration corresponding to each virtual sub-path according to the predicted vehicle speed of the virtual path point included in each virtual sub-path and the mileage of each virtual sub-path.

The virtual path points included in the virtual sub-path refer to virtual path points corresponding to two endpoints of the virtual sub-path. Mileage of a virtual sub-path refers to the distance travelled between two endpoints of the virtual sub-path.

The predicted vehicle speed is a speed parameter in the driving behavior predicted by the whole vehicle state prediction model.

The predicted running duration refers to the required running duration when the vehicle to be evaluated runs on each virtual sub-path according to the predicted vehicle speed. According to the relation among the speed, the mileage and the duration, the predicted running duration of the vehicle to be evaluated corresponding to each virtual sub-path can be determined.

Specifically, fig. 4 is a flowchart of an algorithm corresponding to an oil consumption estimation method in an embodiment, as shown in fig. 4, a vehicle to be estimated determines mileage of a virtual sub-path through a virtual road network, determines a predicted vehicle speed of a virtual path point included in the virtual sub-path through a whole vehicle state prediction model, and determines a predicted running duration of the vehicle to be estimated corresponding to each virtual sub-path according to a formula of speed, mileage and duration.

In some embodiments, the formulas for speed, mileage, and duration are as follows:

wherein the virtual path points included in the virtual sub-path are virtual path point i and virtual path point i+1, x _i,i+1 Mileage being a virtual sub-path; v (V) _i And V _i+1 The predicted vehicle speeds are respectively a virtual path point i and a virtual path point i+1; t is t _i And the predicted driving time length of the vehicle to be evaluated corresponding to the virtual sub-path is set.

3. And determining the predicted fuel consumption corresponding to each virtual sub-path according to the predicted driving time length corresponding to each virtual sub-path and the engine power parameters of the virtual path points included in each virtual sub-path.

The mapping relationship exists among the predicted driving duration corresponding to the virtual sub-path, the engine power parameters of the virtual path points included in the virtual sub-path and the predicted fuel consumption corresponding to the virtual sub-path, and the mapping relationship can be obtained through classifying and summarizing a large amount of experimental data, and can also be obtained through deduction according to the data quantity.

Specifically, the vehicle to be evaluated determines the predicted fuel consumption corresponding to each virtual sub-path according to the mapping relation among the predicted driving time, the engine power parameters of the virtual path points included in the virtual sub-path and the predicted fuel consumption corresponding to the virtual sub-path.

In some embodiments, the mapping relationship among the predicted driving duration, the engine power parameter of the virtual path point included in the virtual sub-path, and the predicted fuel consumption corresponding to the virtual sub-path is as follows:

wherein the virtual path points included in the virtual sub-path are virtual path point i and virtual path point i+1, T _i Corresponding engine torque of the vehicle to be evaluated at the virtual path point i; n is n _e,i For the vehicle to be evaluated at virtual path point iThe corresponding engine speed; b is the specific fuel consumption of the vehicle to be evaluated at the virtual path point i; ρ is the density of the oil.

4. And determining the predicted fuel consumption required by the vehicle to be evaluated to reach the target position according to the predicted fuel consumption corresponding to each virtual sub-path.

Specifically, the vehicle to be evaluated accumulates the predicted fuel consumption corresponding to each virtual sub-path, and the accumulated result is the predicted fuel consumption required by the vehicle to be evaluated to reach the target position.

In some embodiments, the mathematical expression of the predicted fuel consumption required for the vehicle under evaluation to reach the target location is as follows:

the TFC is the predicted fuel consumption required by the vehicle to be evaluated to reach the target position.

In this embodiment, based on the predicted travel duration corresponding to each virtual sub-path and the engine power parameters of the virtual path points included in each virtual sub-path, the predicted fuel consumption corresponding to each virtual sub-path is determined, and the predicted fuel consumption corresponding to each virtual sub-path is accumulated to obtain the predicted fuel consumption required for the vehicle to be evaluated to reach the target position. In the above process, based on the predicted driving duration corresponding to the virtual sub-path and the engine power parameters of the virtual path points included in the virtual sub-path, the predicted fuel consumption corresponding to the virtual sub-path is determined, the road characteristics, the driving style and the engine power parameters are fused together, the predicted fuel consumption corresponding to the virtual sub-path is accurately reflected, and the predicted fuel consumption corresponding to each virtual sub-path is calculated in a sectional manner, so that the total predicted fuel consumption required by the vehicle to be evaluated to reach the target position is obtained, and the prediction accuracy of the total predicted fuel consumption can be improved.

In one embodiment, the method for building a virtual road network includes the following steps:

1. and collecting real road condition data of the vehicle during running at different sampling points of the real road section.

The sampling points on the real road section are used for marking the positions of the vehicles when the vehicles are sampled on the real road section. The sampling points correspond to sampling positions and sampled real road condition data. In order to ensure the accuracy of the real road condition data, the real road condition data is determined by the real road condition data of a plurality of running vehicles.

The real road condition data are obtained through the Internet of vehicles platform, and specifically comprise longitude and latitude, altitude, GPS speed, steering wheel rotation angle and other information corresponding to the sampling points.

Specifically, the vehicle to be evaluated runs on the same real road section through a plurality of different vehicles, samples, marks the sampling position of the vehicle on the real road section according to the sampling time, and acquires real road condition data sampled by the vehicle.

2. And clustering the positions of the sampling points to obtain a plurality of clustering sets, and taking the clustering center of each clustering set as each corresponding virtual path point.

Because the corresponding running speeds of different vehicles are different during sampling, the number and the positions of the corresponding sampling points of different vehicles on the same real road section are different. Therefore, in order to obtain accurate real road condition data, in this embodiment, the positions of the sampling points are clustered with the real road condition data collected by the vehicle with the largest number of sampling points as the center, so as to obtain clustering sets, the clustering center of each clustering set is respectively used as a virtual path point corresponding to each clustering set, and the virtual road condition data of the virtual path points is determined based on the real road condition data of each sampling point in the clustering sets.

Specifically, the vehicle to be evaluated uses the vehicle with the largest number of sampling points as a reference vehicle, the real road condition data collected by the rest vehicles are clustered by using the real road condition data sampled by the reference vehicle as a center, a plurality of cluster sets are obtained, and the cluster center of each cluster set is respectively used as a virtual path point corresponding to each cluster set.

In some embodiments, if the sampling points of the remaining vehicles do not coincide with the clustering center, determining the clustering center closest to the sampling points of the remaining vehicles, and dividing the real road condition data of the remaining vehicles into a clustering set corresponding to the clustering center.

In some embodiments, the cluster center closest to the sampling points of the remaining vehicles is determined according to the following formula:

wherein h is the distance between the sampling point and the clustering center of the rest vehicles, longit _f 、lat _f Longitude and latitude of the cluster center respectively; longit _p And lat _p The longitude and latitude of the sampling points of the remaining vehicles, respectively.

3. For any cluster set, determining virtual road condition data corresponding to virtual path points of the cluster set according to the real road condition data of all sampling points in the cluster set.

The virtual road condition data is a real road condition data clustering result of all sampling points in the clustering set. Specifically, for any clustering set, the vehicle to be evaluated clusters real road condition data of all sampling points in the clustering set to obtain a clustering result, and the clustering result is used as virtual road condition data corresponding to virtual path points of the clustering set to be evaluated.

For example, the real road condition data includes longitude and latitude, altitude, GPS speed, steering wheel angle, road type and sampling time corresponding to the sampling point, and correspondingly, the virtual road condition data corresponding to the virtual road condition point includes position, gradient, driving mileage, road curvature, road type and sampling time. And determining corresponding slopes of all the corresponding altitudes of the sampling points of the same cluster set, carrying out average value obtaining treatment on the slopes, and taking an average value result as the slope of the virtual road condition point. And summing the distances between the clustering center corresponding to the current position of the vehicle to be evaluated and any two adjacent clustering centers between the clustering centers to be evaluated to obtain the driving mileage of the clustering center (virtual road condition point) to be evaluated. And carrying out probability statistics on the road types corresponding to all the sampling points of the same cluster set, and taking the road type with the highest probability as the road type of the virtual road condition point. And carrying out probability statistics on sampling moments corresponding to all sampling points of the same cluster set, and taking the sampling moment with the highest probability as the road type of the virtual road condition point.

If the steering wheel steering change rate of more than 95% of sampling points in the same clustering set is greater than a preset value, determining that the curvature of the current real road section is not 0, otherwise, determining that the curvature of the current real road section is infinite (the real road section is represented as a straight road). Calculating the road curvature of the virtual road condition point according to the following formula:

Wherein k is the curvature of two adjacent polymerization centers; a is the wheel tread of the front wheel of the commercial vehicle, n ₁ And n ₂ The rotation speeds of front wheels at two sides of the vehicle can be obtained through a data platform; r is the wheel radius. As shown in FIG. 3, 1-1 represents a cluster center, and 1-2 represents a GPS point of the current vehicle; 1-3 represents a curvature; 1-4 represents an inboard wheel turning displacement; 1-5 represents an inner wheel position point; 1-6 represent outer wheel location points; 1-7 represent outboard wheel turning displacements.

4. And generating a virtual road section according to the virtual road condition data corresponding to each virtual path point, and constructing a virtual road network according to the generated virtual road section.

The virtual road section comprises a plurality of virtual path points, and the virtual path points are connected to obtain the virtual road section.

Specifically, the vehicle to be evaluated connects the virtual path points, and configures virtual road condition data to the respective virtual path points respectively to obtain a virtual road section; and connecting the generated multiple virtual road sections by the vehicle to be evaluated according to the road connectivity to obtain a virtual road network.

In the embodiment, based on the dimension and the characteristics of the data of the internet of vehicles platform, a plurality of clustering sets are obtained by clustering the positions of different sampling points of a real road section, the clustering center of each clustering set is respectively used as a virtual path point corresponding to each clustering set, and the virtual road condition data corresponding to the virtual path points of the clustering set is obtained by clustering the real road condition data of all the sampling points in the same clustering set; in the process, the similar sampling points are classified into the same clustering set in a position clustering mode, and the clustering analysis is carried out on all the sampling points in the same clustering set, so that the obtained virtual road condition data combines the real road condition data of all the sampling points in the same clustering set, and the authenticity of the virtual road condition data is improved. And then, generating a virtual road section according to the virtual road condition data corresponding to each virtual path point, and constructing a virtual road network according to the generated virtual road section. The virtual road network comprises different virtual road sections, and even if a driver changes a route, the virtual road condition data of the changed virtual road section can be obtained through the virtual road network, so that the predicted oil consumption is calculated again based on the virtual road condition data in a self-adaptive mode, and the universality is improved.

In one embodiment, the fuel consumption estimation method further includes the steps of:

generating fuel consumption prompt information according to the predicted fuel consumption; the fuel consumption prompt information is used for indicating the magnitude relation between the residual fuel quantity of the vehicle to be evaluated and the predicted fuel consumption; and carrying out audible and visual alarm under the condition that the fuel consumption prompt information is used for indicating that the residual fuel quantity of the vehicle to be evaluated is smaller than the predicted fuel consumption.

Specifically, the vehicle to be evaluated compares the predicted fuel consumption with the residual fuel quantity of the vehicle to be evaluated, and generates fuel consumption prompt information according to the comparison result; and displaying the oil consumption prompt information on an oil meter of the vehicle to be evaluated and carrying out acousto-optic prompt under the condition that the oil consumption prompt information is used for indicating that the residual oil quantity of the vehicle to be evaluated is smaller than the predicted oil consumption quantity.

In this embodiment, the driver may be prompted to refuel according to the relationship between the remaining oil amount of the vehicle to be evaluated and the predicted oil consumption amount, so as to avoid the situation that the engine is flameout due to oil shortage caused by too little oil amount.

In a detailed embodiment, a fuel consumption estimation method specifically includes the following steps:

2. And clustering the positions of the sampling points to obtain a plurality of clustering sets.

3. And taking the clustering center of each clustering set as the virtual path point corresponding to each clustering center.

4. For any cluster set, determining virtual road condition data corresponding to virtual path points of the cluster set according to the real road condition data of all sampling points in the cluster set.

5. Generating a virtual road section according to the virtual road condition data corresponding to each virtual path point, and constructing a virtual road network according to the generated virtual road section; the virtual road network comprises a plurality of virtual paths, each virtual path is composed of a plurality of virtual path points, and each virtual path point corresponds to virtual road condition data.

6. The current position of the vehicle to be evaluated and the target position to be driven to are obtained.

7. And determining a target virtual path and virtual road condition data between the current position and the target position in the established virtual road network according to the current position and the target position.

8. And determining the mileage between any two adjacent virtual path points in the target virtual path.

9. And determining the driving mileage between the current position and the target position according to the mileage between any two adjacent virtual path points in the target virtual path.

10. Processing the virtual road condition data of each virtual path point in the virtual path through the whole vehicle state prediction model, and predicting to obtain driving behaviors corresponding to each virtual path point in the virtual path; the driving behavior includes a predicted vehicle speed.

11. And respectively processing driving behaviors corresponding to the virtual path points through the whole vehicle power demand model, and predicting to obtain the engine speed and the engine torque corresponding to the virtual path points.

12. And determining the specific fuel consumption of the vehicle to be evaluated at each virtual path point according to the engine speed and the engine torque corresponding to each virtual path point.

13. A virtual sub-path is determined based on each adjacent two virtual path points in the target virtual path.

14. And determining the predicted running duration corresponding to each virtual sub-path according to the predicted vehicle speed of the virtual path point included in each virtual sub-path and the mileage of each virtual sub-path.

15. And determining the predicted fuel consumption corresponding to each virtual sub-path according to the predicted running time corresponding to each virtual sub-path, the engine speed, the engine torque and the specific fuel consumption of the virtual path point included in each virtual sub-path.

16. And determining the predicted fuel consumption required by the vehicle to be evaluated to reach the target position according to the predicted fuel consumption corresponding to each virtual sub-path.

17. Generating fuel consumption prompt information according to the predicted fuel consumption; the fuel consumption prompt information is used for indicating the magnitude relation between the residual fuel quantity and the predicted fuel consumption of the vehicle to be evaluated.

18. And carrying out audible and visual alarm under the condition that the fuel consumption prompt information is used for indicating that the residual fuel quantity of the vehicle to be evaluated is smaller than the predicted fuel consumption.

In the embodiment, a plurality of clustering sets are obtained by clustering positions of different sampling points of a real road section, clustering centers of each clustering set are respectively used as virtual path points corresponding to the clustering centers, and virtual road condition data corresponding to the virtual path points of the clustering set are obtained by clustering real road condition data of all the sampling points in the same clustering set; in the process, the similar sampling points are classified into the same clustering set in a position clustering mode, and the clustering analysis is carried out on all the sampling points in the same clustering set, so that the obtained virtual road condition data combines the real road condition data of all the sampling points in the same clustering set, and the authenticity of the virtual road condition data is improved. And then, generating a virtual road section according to the virtual road condition data corresponding to each virtual path point, and constructing a virtual road network according to the generated virtual road section. The virtual road network comprises different virtual road sections, and even if a driver changes a route, virtual road condition data of the changed virtual road sections can be obtained through the virtual road network, so that the predicted oil consumption is recalculated based on the virtual road condition data.

In this embodiment, the driving mileage between the current position and the target position and the virtual road condition data between the current position and the target position are determined through the established virtual road network, and the virtual road condition data are processed through the whole vehicle state prediction model to predict the driving behavior involved in the process of the vehicle to be evaluated from the current position to the target position. In the process, all the virtual road condition data between the current position and the target position are directly obtained through the virtual road network, so that the road characteristics which affect the oil consumption comprehensively and accurately can be obtained, the virtual road condition data are processed through the whole vehicle state prediction model, more accurate driving behaviors can be obtained, and the combination of the road characteristics and the driving behaviors is realized. And then, the driving behavior is processed through the whole vehicle power demand model, and engine power parameters involved in the process that the vehicle to be evaluated runs from the current position to the target position are predicted. In the process, the driving behavior is processed through the whole vehicle power demand model, so that the relation between the driving behavior and the engine power parameters can be obtained, and the combination of road characteristics, the driving behavior and the engine power parameters of the vehicle to be evaluated is realized. And finally, determining the predicted fuel consumption required by the vehicle to be evaluated to reach the target position according to the driving behavior, the engine power parameter and the driving mileage. The finally obtained predicted fuel consumption is estimated based on the multidimensional data, so that the determined predicted fuel consumption is more accurate. In general, the method fuses road characteristics, driving style and engine power parameters together through real-time interaction of the virtual road network, the whole vehicle state prediction model and the whole vehicle power demand model, and accurately reflects the predicted fuel consumption required by the vehicle to be evaluated to reach the target position.

It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides a fuel consumption estimating device for realizing the fuel consumption estimating method. The implementation scheme of the solution to the problem provided by the device is similar to that described in the above method, so the specific limitation of one or more embodiments of the fuel consumption estimating device provided below may refer to the limitation of the fuel consumption estimating method, and will not be repeated here.

In one embodiment, as shown in fig. 5, there is provided a fuel consumption estimating apparatus, including: a position obtaining module 501, configured to obtain a current position of a vehicle to be evaluated and a target position to be driven to;

the virtual road condition determining module 502 is configured to determine, through the built virtual road network, a driving distance between the current position and the target position, and virtual road condition data between the current position and the target position;

the driving behavior prediction module 503 is configured to process the virtual road condition data through a vehicle state prediction model, and predict a driving behavior involved in a process that the vehicle to be evaluated travels from the current position to the target position;

the power parameter prediction module 504 is configured to process the driving behavior through the whole vehicle power demand model, and predict engine power parameters involved in the process that the vehicle to be evaluated travels from the current position to the target position;

the fuel consumption prediction module 505 is configured to determine a predicted fuel consumption required by the vehicle to be evaluated to reach the target position according to the driving behavior, the engine power parameter and the driving mileage.

In one embodiment, the virtual road network comprises a plurality of virtual paths, and each virtual path is composed of a plurality of virtual path points; the virtual road condition determining module 502 is further configured to determine a target virtual path in the established virtual road network according to the current position and the target position; determining mileage between any two adjacent virtual path points in the target virtual path; and determining the driving mileage between the current position and the target position according to the mileage between any two adjacent virtual path points in the target virtual path.

In one embodiment, each virtual path point corresponds to virtual road condition data; the driving behavior prediction module 503 is further configured to process, by using the vehicle state prediction model, virtual road condition data of each virtual path point in the target virtual path, and predict and obtain driving behaviors corresponding to each virtual path point in the target virtual path.

In one embodiment, the engine power parameters include an engine speed, an engine torque and a specific fuel consumption of the engine, and the power parameter prediction module 504 is further configured to process driving behaviors corresponding to each virtual path point through the whole vehicle power demand model, and predict to obtain the engine speed and the engine torque corresponding to each virtual path point; and determining the specific fuel consumption of the vehicle to be evaluated at each virtual path point according to the engine speed and the engine torque corresponding to each virtual path point.

In one embodiment, the driving behavior includes a predicted vehicle speed, and the fuel consumption prediction module 505 is further configured to determine a virtual sub-path based on each adjacent two virtual path points in the target virtual path; determining a predicted running duration corresponding to each virtual sub-path according to the predicted vehicle speed of the virtual path point included in each virtual sub-path and the mileage of each virtual sub-path; determining predicted fuel consumption corresponding to each virtual sub-path according to the predicted driving time length corresponding to each virtual sub-path and the engine power parameters of the virtual path points included in each virtual sub-path; and determining the predicted fuel consumption required by the vehicle to be evaluated to reach the target position according to the predicted fuel consumption corresponding to each virtual sub-path.

In one embodiment, the virtual road condition determining module 502 is further configured to collect real road condition data when the vehicle is running at different sampling points of the real road section; clustering the positions of the sampling points to obtain a plurality of clustering sets; respectively taking the clustering centers of each clustering set as virtual path points corresponding to the clustering centers; for any cluster set, determining virtual road condition data corresponding to virtual path points of the cluster set according to the real road condition data of all sampling points in the cluster set; and generating a virtual road section according to the virtual road condition data corresponding to each virtual path point, and constructing a virtual road network according to the generated virtual road section.

In one embodiment, the fuel consumption prediction module 505 is further configured to generate fuel consumption prompt information according to the predicted fuel consumption; the fuel consumption prompt information is used for indicating the magnitude relation between the residual fuel quantity of the vehicle to be evaluated and the predicted fuel consumption; and carrying out audible and visual alarm under the condition that the fuel consumption prompt information is used for indicating that the residual fuel quantity of the vehicle to be evaluated is smaller than the predicted fuel consumption.

All or part of the modules in the fuel consumption estimating device can be realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one embodiment, a vehicle is provided, the internal structure of which may be as shown in FIG. 6. The vehicle includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input device. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program, when executed by a processor, implements a fuel consumption estimation method. The display unit of the computer equipment is used for forming a visual picture, and can be a display screen, a projection device or a virtual reality imaging device, wherein the display screen can be a liquid crystal display screen or an electronic ink display screen, the input device of the computer equipment can be a touch layer covered on the display screen, can also be a key, a track ball or a touch pad arranged on a shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.

It will be appreciated by those skilled in the art that the structure shown in FIG. 6 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.

In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, implements the steps of the method embodiments described above.

In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.

It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.

Claims

1. The fuel consumption estimation method is characterized by comprising the following steps of:

2. The method of claim 1, wherein the virtual road network comprises a plurality of virtual paths, each virtual path being formed by a plurality of virtual path points; the determining the driving mileage between the current position and the target position through the built virtual road network comprises the following steps:

determining a target virtual path in the established virtual road network according to the current position and the target position;

determining mileage between any two adjacent virtual path points in the target virtual path;

and determining the driving mileage between the current position and the target position according to the mileage between any two adjacent virtual path points in the target virtual path.

3. The method according to claim 2, wherein each virtual path point corresponds to virtual road condition data, the virtual road condition data is processed by a whole vehicle state prediction model, and driving behaviors involved in the process of driving the vehicle to be evaluated from the current position to the target position are predicted, including:

And processing the virtual road condition data of each virtual path point in the target virtual path through a whole vehicle state prediction model, and predicting to obtain the driving behavior corresponding to each virtual path point in the target virtual path.

4. A method according to claim 3, wherein the engine power parameters include engine speed, engine torque and specific fuel consumption of the engine, and the processing of the driving behavior by the vehicle power demand model predicts engine power parameters involved in the process of driving the vehicle to be evaluated from the current position to the target position, and comprises:

the driving behavior corresponding to each virtual path point is processed through the whole vehicle power demand model, and the engine speed and the engine torque corresponding to each virtual path point are obtained through prediction;

and determining the specific fuel consumption of the vehicle to be evaluated at each virtual path point according to the engine speed and the engine torque corresponding to each virtual path point.

5. The method of claim 4, wherein the driving behavior comprises a predicted vehicle speed, and wherein the determining a predicted fuel consumption required by the vehicle under evaluation to reach the target location based on the driving behavior, the engine power parameter, and the mileage comprises:

Determining a virtual sub-path based on each adjacent two virtual path points in the target virtual path;

determining a predicted running duration corresponding to each virtual sub-path according to the predicted vehicle speed of the virtual path point included in each virtual sub-path and the mileage of each virtual sub-path;

determining predicted fuel consumption corresponding to each virtual sub-path according to the predicted driving time length corresponding to each virtual sub-path and the engine power parameters of the virtual path points included in each virtual sub-path;

and determining the predicted fuel consumption required by the vehicle to be evaluated to reach the target position according to the predicted fuel consumption corresponding to each virtual sub-path.

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

collecting real road condition data of a vehicle during running at different sampling points of a real road section;

clustering the positions of the sampling points to obtain a plurality of clustering sets;

respectively taking the clustering centers of each clustering set as virtual path points corresponding to the clustering centers;

for any cluster set, determining virtual road condition data corresponding to virtual path points of the cluster set according to the real road condition data of all sampling points in the cluster set;

And generating a virtual road section according to the virtual road condition data corresponding to each virtual path point, and constructing a virtual road network according to the generated virtual road section.

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

generating fuel consumption prompt information according to the predicted fuel consumption; the fuel consumption prompt information is used for indicating the magnitude relation between the residual fuel quantity of the vehicle to be evaluated and the predicted fuel consumption;

and carrying out audible and visual alarm under the condition that the fuel consumption prompt information is used for indicating that the residual fuel quantity of the vehicle to be evaluated is smaller than the predicted fuel consumption.

8. A fuel consumption estimation device, characterized in that the device comprises:

9. A vehicle comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 7 when the computer program is executed.

10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.

11. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.