New energy vehicle remaining driving mileage prediction method and system

Abstract

The invention provides a new energy vehicle remaining driving mileage prediction method and system, relates to the field of new energy vehicle driving mileage prediction, and aims to solve the problem of how to improve the accuracy of new energy vehicle remaining driving mileage prediction. The method comprises the following steps: collecting discharge condition data of a plurality of vehicles through a big data platform, after a training target data set required by neural network training and a training input data set with high correlation with the remaining driving mileage of the vehicle are obtained through screening according to a preset condition, performing neural network training to establish a new energy vehicle remaining driving mileage prediction model; and obtaining current discharge condition data of the vehicle having a demand for the residual driving mileage prediction value, substituting the current discharge condition data into the new energy vehicle residual driving mileage prediction model, and calculating the residual driving mileage prediction value of the required vehicle. According to the invention, accurate residual driving mileage prediction can be obtained by establishing the vehicle residual driving mileage prediction model, and a driver can formulate a reasonable route plan according to the remaining driving mileage.

Description

technical field [0001] The invention relates to the field of prediction of remaining driving mileage of vehicles, in particular to a method and system for predicting remaining driving mileage of new energy vehicles. Background technique [0002] At present, more and more people are buying new energy vehicles. New energy vehicles use power batteries as the only energy source. The power of the power battery determines the remaining driving mileage of the vehicle. Once the power battery is exhausted, the vehicle will not be able to run. Therefore, it is very important for drivers to know the remaining driving range of their own vehicles. [0003] In order to solve the above problems, Chinese patent application number (CN106908075B) discloses a big data acquisition and processing system and a method for estimating the battery life of an electric vehicle based on it. Destination, the online computing system estimates whether the destination can be reached based on the recorded v...

AI Technical Summary

Problems solved by technology

[0004] The above method is the vehicle power model calculated by the cloud server based on the real-time vehicle data in the actual driving state. The cloud server or background server needs to upload the vehicle data to build the model, but the existing vehicle upload data cannot guarantee the integrity of the transmitted data. stability and accuracy, once the data is wrong, it will not be possible to establish an accurate model

As a result, the accuracy of the remaining mileage of the vehicle is affected, the planning of the driver's journey is affected, and the driver's experience is reduced.

Images