A charging pile fault prediction method based on an expandable lifting tree

Abstract

The invention discloses a charging pile fault prediction method based on an expandable lifting tree. The method mainly comprises two stages. The first stage comprises the following steps: firstly, fault characteristic state signals of each component of the charging pile and fault information of the charging pile are collected to a data analysis platform as model training sample data; the data analysis platform adopts an Xgboost algorithm to train a large number of sample data received, and obtains a fault prediction model of charging pile which achieves a certain degree of accuracy satisfaction. In the second stage, when the data analysis platform receives the state signal of the charging pile again, the trained Xgboost model will be used to judge the fault state of the charging pile. Themethod solves the fault prediction problem of the charging pile by using the artificial intelligence technology, has extremely high accuracy, can reduce the manual maintenance and repair cost of the charging pile, and saves a large amount of human and financial resources.

Description

technical field [0001] The invention belongs to the technical field of fault prediction of electric vehicle charging piles, and in particular relates to a fault prediction method for electric vehicle charging piles based on an extensible boosting tree Xgboost. Background technique [0002] As the source of energy supply for electric vehicles, electric vehicle charging stations are an important supporting infrastructure necessary for the development of electric vehicles. However, at present, charging pile companies generally have insufficient maintenance of charging piles, and there are also many faulty piles and zombie piles in some areas. These problems seriously affect the user's charging experience and restrict the development of the electric vehicle industry. It can be said that realizing intelligent fault prediction of charging piles, timely maintenance and repair, and making charging piles work more safely and stably are of great significance to improving the efficienc...

AI Technical Summary

Problems solved by technology

[0004] In view of the lack of speed of the existing charging pile fault prediction technology, the failure characteristic components considered are not comprehensive enough, etc., combined with the characteristics of the signal data of each component of the charging pile and the type of fault prediction tasks, the present invention proposes a method based on scalable improvement Fault prediction method for electric vehicle charging pile based on tree Xgboost

Images