Fault prediction method and prediction system

Abstract

The embodiment of the invention relates to a fault prediction method and prediction system, the fault prediction method is applied to a server, and the prediction method comprises the steps: obtaining charging data when a charging pile fails; performing feature extraction on the charging data to obtain feature charging information corresponding to each charging pile fault; dividing each charging pile fault into a corresponding preset fault type through fault qualitative analysis so as to generate a training sample set of each preset fault type; and training according to the training sample sets to generate fault models corresponding to the preset fault types, wherein the fault models are used for fault prediction of the charging pile. According to the embodiment of the invention, the effective data in the charging data can be accurately obtained through the feature extraction step, and the corresponding fault models are established for different preset fault types, so that the data analysis speed can be further improved, and the fault prediction efficiency and maintenance efficiency of the charging pile are improved.

Description

technical field [0001] The embodiments of the present application relate to the technical field of charging piles, and in particular to a fault prediction method and prediction system. Background technique [0002] The development of electric vehicles is becoming the mainstream of the development of the automobile industry. At the end of 2019, the cumulative sales of electric passenger vehicles in the world have exceeded 7 million. The corresponding charging infrastructure, especially the construction of charging piles, has attracted the attention of countries all over the world. [0003] However, since the charging pile technology is still in the stage of rapid development, a unified industry standard has not been formed, which leads to difficulties in maintenance and repair, and also causes a high rate of broken piles. Traditional fault detection requires different methods according to specific charging piles, so fault detection and maintenance are complex and time-consumi...

AI Technical Summary

Problems solved by technology

[0003] However, since the charging pile technology is still in the stage of rapid development, a unified industry standard has not been formed, which leads to difficulties in maintenance and repair, and also causes a high rate of broken piles

Traditional fault detection requires different methods according to specific charging piles, so fault detection and maintenance are complex and time-consuming, resulting in low maintenance efficiency for charging piles

Images