Commercial electric vehicle energy consumption prediction method and apparatus, and computer device

Patent metadata

Field	Value
Publication number	US-2023222852-A1
Application number	US-202217929889-A
Country	US
Kind code	A1
Filing date	Sep 6, 2022
Priority date	Jan 7, 2022
Publication date	Jul 13, 2023
Grant date	—

Abstract

The present application relates to an electric vehicle energy consumption prediction method and apparatus, a computer device, a computer-readable storage medium, and a computer program product. The method includes: acquiring discharge duration data of an electric vehicle; acquiring driving position characteristic data of the electric vehicle; and inputting the discharge duration data and the driving position characteristic data into an energy consumption prediction model to obtain energy consumption prediction data of the electric vehicle. The energy consumption prediction model is obtained based on a machine learning algorithm.

First claim

What is claimed is:

1 . An electric vehicle energy consumption prediction method, comprising:
obtaining discharge duration data of an electric vehicle; obtaining driving position characteristic data of the electric vehicle; and inputting the discharge duration data and the driving position characteristic data into an energy consumption prediction model to obtain energy consumption prediction data of the electric vehicle; wherein the energy consumption prediction model is obtained based on a machine learning algorithm.

2 . The method according to claim 1 , wherein, prior to inputting the discharge duration data and the driving position characteristic data into the energy consumption prediction model to obtain energy consumption prediction data of the commercial electric vehicle, the method further comprises:
performing, according to historical driving data and rated battery capacity of the electric vehicle and a preset model loss function, model training based on the machine learning algorithm, to obtain the energy consumption prediction model.

3 . The method according to claim 2 , wherein performing, according to historical driving data and rated battery capacity of the electric vehicle and a preset model loss function, model training based on the machine learning algorithm to obtain the energy consumption prediction model comprises:
obtaining the historical driving data and the rated battery capacity of the electric vehicle, wherein the historical driving data comprises historical charge and discharge data and historical driving position characteristic data; calculating historical energy consumption data per unit time of the electric vehicle based on the historical charge and discharge data and the rated battery capacity; obtaining historical energy consumption data according to the historical energy consumption data per unit time and the historical driving position characteristic data; and performing, according to the historical energy consumption data and the preset model loss function, model training based on the machine learning algorithm to obtain the energy consumption prediction model.

4 . The method according to claim 3 , wherein obtaining the historical driving data of the electric vehicle comprises:
obtaining historical raw driving data of the electric vehicle; and pre-processing the historical raw driving data to obtain the historical driving data of the electric vehicle.

5 . The method according to claim 3 , wherein calculating historical energy consumption data per unit time of the electric vehicle based on the historical charge and discharge data and the rated battery capacity comprises:
obtaining historical charge data and historical discharge data of the electric vehicle based on the historical charge and discharge data by taking a set time as a cycle; obtaining a battery state of health of the electric vehicle within the set time based on the historical charge data and the rated battery capacity; and obtaining the historical energy consumption data per unit time of the electric vehicle according to the battery state of health, the rated battery capacity, and historical discharge data corresponding to the historical charge data.

6 . The method according to claim 5 , wherein one charge section corresponds to a plurality of sub-discharge sections within the set time; and obtaining the historical energy consumption data per unit time of the electric vehicle according to the battery state of health, the rated battery capacity, and historical discharge data corresponding to the historical charge data comprises:
obtaining the historical energy consumption data per unit time of the electric vehicle according to the battery state of health, the rated battery capacity, and historical discharge data of the sub-discharge sections.

7 . The method according to claim 5 , wherein a plurality of charge sections exist within the set time; and obtaining the historical energy consumption data per unit time of the electric vehicle according to the battery state of health, the rated battery capacity, and historical discharge data corresponding to the historical charge data comprises:
obtaining the historical energy consumption data per unit time of the electric vehicle according to the battery state of health, the rated battery capacity, historical charge data of the charge sections, and historical discharge data of discharge sections corresponding to the charge sections.

8 . The method according to claim 7 , wherein obtaining the historical energy consumption data per unit time of the electric vehicle according to the battery state of health, the rated battery capacity, historical charge data of the charge sections, and historical discharge data of discharge sections corresponding to the charge sections comprises:
obtaining energy consumption of the discharge sections corresponding to the charge sections according to the battery state of health, the rated battery capacity, the historical charge data of the charge sections, and the historical discharge data of the discharge sections corresponding to the charge sections; calculating, if a maximum energy consumption value in the energy consumption of the discharge sections corresponding to the charge sections is less than the rated battery capacity, historical energy consumption data per unit time within the set time according to the maximum energy consumption value; or calculating, if the maximum energy consumption value in the energy consumption of the discharge sections corresponding to the charge sections is greater than or equal to the rated battery capacity and less than a preset multiple of the rated battery capacity, the historical energy consumption data per unit time within the set time according to an average value of the energy consumption of the discharge sections corresponding to the charge sections; and discarding, if the maximum energy consumption value in the energy consumption of the discharge sections corresponding to the charge sections is greater than or equal to the preset multiple of the rated battery capacity, the historical charge and discharge data within the corresponding set time.

9 . The method according to claim 3 , wherein, after inputting the discharge duration data and the driving position characteristic data into the energy consumption prediction model to obtain energy consumption prediction data of the electric vehicle, the method further comprises:
dividing the historical energy consumption data into a training set and a test set, and obtaining energy consumption prediction data corresponding to the test set based on the training set and the energy consumption prediction model; and correcting the energy consumption prediction data according to the test set and the energy consumption prediction data corresponding to the test set, to obtain corrected energy consumption prediction data.

10 . The method according to claim 1 , wherein inputting the discharge duration data and the driving position characteristic data into the energy consumption prediction model to obtain energy consumption prediction data of the electric vehicle comprises:
interpolating the discharge duration data to obtain interpolated discharge duration data, and inputting the interpolated discharge duration data and the driving position characteristic data into the energy consumption prediction model.

11 . The method according to claim 1 , wherein inputting the discharge duration data and the driving position characteristic data into the energy consumption prediction model to obtain energy consumption prediction data of the electric vehicle comprises:
inputting the discharge duration data and the driving pos

Assignees

• Contemporary Amperex Technology Co Ltd

Inventors

• Duan Panting
• Zhao Wei

Classifications

• G06N20/20

  Ensemble learning · CPC title

• G06N5/01

  Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound · CPC title

• G06N3/08

  Learning methods · CPC title

• G01C21/3469

  Fuel consumption; Energy use; Emission aspects · CPC title

• G07C5/04 Primary

  using counting means or digital clocks · CPC title