Method and device for on-line prediction of remaining driving mileage of electric vehicle

• US 10,124,675 B2
• Filed: 10/26/2017
• Issued: 11/13/2018
• Est. Priority Date: 10/27/2016
• Status: Active Grant

• Current Assignee: Hefei University of Technology
• Original Assignee: Hefei University of Technology
• Inventors: Lu, Xiaonong, Zhang, Qiang, Wang, Wanying, Wang, Anning, Yang, Shanlin, Ren, Minglun, Peng, Zhanglin
• Primary Examiner(s): Do, Truc M
• Application Number:
  US15/794,989
• Publication Number:
  US 20180118033A1
• Time in Patent Office: 383 Days
• CPC Class Codes: B60L 2240/12 Speed
• CPC Class Codes: B60L 2240/421 Speed
• CPC Class Codes: B60L 2240/547 Voltage
• CPC Class Codes: B60L 2240/549 Current
• CPC Class Codes: B60L 2240/62 Vehicle position
• CPC Class Codes: B60L 2240/64 Road conditions
• CPC Class Codes: B60L 2240/662 Temperature
• CPC Class Codes: B60L 2260/52 drive range estimation, e.g. of estimation of available travel distance
• CPC Class Codes: B60L 2260/54 Energy consumption estimation
• CPC Class Codes: B60L 3/12 Recording operating variables ; Monitoring of operating variables
• CPC Class Codes: B60L 58/12 responding to state of charge [SoC]
• CPC Class Codes: Y02T 10/64 Electric machine technologies in electromobility
• CPC Class Codes: Y02T 10/70 Energy storage systems for electromobility, e.g. batteries
• CPC Class Codes: Y02T 10/72 Electric energy management in electromobility
• CPC Class Codes: Y02T 90/16 Information or communication technologies improving the operation of electric vehicles

Abstract

The present invention relates to a method and device for on-line prediction of remaining driving mileage of an electric vehicle. The method comprises: acquiring in-transit data and driving environment data of the electric vehicle which is driving; calculating the power consumption per mileage of the electric vehicle in the current case by using the in-transit data and the driving environment data in combination with a power consumption rate data model; predicting the remaining driving mileage of the electric vehicle based on the power consumption per mileage. The device provided by the present invention is implemented on the basis of the method above. The prediction result of the present invention is more accurate, to avoid the problem that the power is exhausted due to exceeding the mileage expected by a user so that the electric vehicle cannot continue to drive, thereby improving the driving experience of the user.

Claims

1. A method for on-line prediction of remaining driving mileage of an electric vehicle, characterized in that, the method comprises using a device for on-line prediction of remaining driving mileage of an electric vehicle to execute the steps of:

acquiring in-transit data of the electric vehicle which is driving through a CAN (Controller Area Network) bus, the in-transit data including battery status information, motor status information and vehicle speed information, wherein the battery status information includes the value of voltage of a battery pack, the value of current of the battery pack and the value of remaining charge of the battery pack, the motor status information includes a motor speed, and the vehicle speed information includes a current driving speed and driving mileage;

acquiring driving environment data of the electric vehicle through a driving environment data collecting device including a network device which can directly obtain corresponding weather information from the relevant authority and a measuring device which can obtain the road condition information, the driving environment data including weather information and road condition information, wherein the weather information includes the type of weather at the current geographical position and an ambient temperature, and the road condition information includes the type and tilt degree of road surfaces;

calculating power consumption per mileage of the electric vehicle in the current case by using the in-transit data and the driving environment data in combination with a updated power consumption rate data model; and

predicting the remaining driving mileage of the electric vehicle based on the power consumption per mileage;

wherein the updated power consumption rate data model is obtained through following steps;

acquiring the in-transit data of the electric vehicle to form a historical running data set, and acquiring the driving environment data of the electric vehicle to form a historical driving environment data set;

fusing the historical running data set and the historical driving environment data set to obtain in-transit time series data of the electric vehicle;

acquiring correlation between the power consumption per mileage of the electric vehicle and the respective parameter in the historical running data set and the historical driving environment data set by using a correlation analysis method in a preset driving environment; and

after removing parameters whose correlations are less than a preset value of correlation, fitting the power consumption per mileage and remaining parameters to obtain the power consumption rate data model of the electric vehicle.

2. The method for on-line prediction of the remaining driving mileage of the electric vehicle according to claim 1, characterized in that, the step of acquiring the in-transit data of the electric vehicle to form the historical running data set, and the driving environment data of the electric vehicle to form the historical driving environment data set comprises:

reading the in-transit data of the electric vehicle through a CAN (Controller Area Network) bus, the in-transit data including battery status information, motor status information and vehicle speed information, wherein the battery status information includes the value of voltage of a battery pack, the value of current of the battery pack and the value of remaining charge of the battery pack, the motor status information includes a motor speed, and the vehicle speed information includes a current driving speed and driving mileage;

reading the driving environment data of the electric vehicle, the driving environment data including weather information and road condition information, wherein the weather information includes the type of weather at the current geographical position and an ambient temperature, and the road condition information includes the type and tilt degree of road surfaces; and

storing the in-transit data and the driving environment data in a file in which the historical running data set is located and a file in which the historical driving environment data set is located, respectively.

3. The method for on-line prediction of the remaining driving mileage of the electric vehicle according to claim 1, characterized in that, the step of fusing the historical running data set and the historical driving environment data set to obtain the in-transit time series data of the electric vehicle comprises:

performing normalization processing on the in-transit data;

performing parameterization processing on the driving environment data; and

fusing the in-transit data and the driving environment data into a data set according to the recording time to be saved in a tile in which the in-transit time series data is located.

4. The method for on-line prediction of the remaining driving mileage of the electric vehicle according to claim 3, characterized in that, the method of the normalization processing includes:

one or more of a Min-Max normalization method, z-score normalization method, a decimal scaling normalization method, a linear function conversion method, a logarithmic function conversion method, an arccotangent function conversion method and a proportion method.

5. The method for on-line prediction of the remaining driving mileage of the electric vehicle according to claim 1, characterized in that, the step of acquiring the correlation between the power consumption per mileage of the electric vehicle and the respective parameter in the historical running data set and the historical driving environment, data set by using the correlation analysis method in the preset driving environment comprises:

selecting and determining a analysis time window according to the preset driving environment;

calculating the power consumption per mileage of the electric vehicle according the in-transit data included in each analysis time window and the formula of a preset power consumption per mileage; and

calculating the correlation between the respective parameter in the historical running data set and the historical driving environment data set and the power consumption per mileage of the electric vehicle by using a factor analysis method.

6. The method for on-line prediction of the remaining driving mileage of the electric vehicle according to claim 5, characterized in that, the formula of the preset power consumption per mileage is:

7. The method for on-line prediction of the remaining driving mileage of the electric vehicle according to claim 1, characterized in that, the step of after removing the parameters whose correlations are less than the preset value of correlation, fitting the power consumption per mileage and the remaining parameters to obtain the power consumption rate data model of the electric vehicle comprises:

presetting the power consumption rate data model of the electric vehicle, that is, C_L=a₁f(x₁)+a₂f(x₂)+ . . . +a_mf(x_m)+ . . . +a_Nf(x_N), wherein x₁, x₂, . . . , x_m, . . . , x_N represents that the parameters whose correlations are not less than the preset value of correlation;

f(x₁), f(x₂), . . . , f(x_m), . . . , f(x_N) represents the correlation function between each parameter and the model;

a₁, a₂, . . . , a_m, . . . , a_N represents the coefficient of the respective function; and

in is a nonzero natural number less than N; and

calculating the value of each coefficient am and the linear or mapping relationship between the respective correlation function f(x_m) and the respective parameter xm by the control variable method using the in-transit data in a preset number of analysis time windows, so as to obtain the power consumption rate data model.