Equipment fault detection classifier training method, computing equipment and storage medium

Abstract

The invention discloses an equipment fault detection classifier training method, which comprises the following steps: acquiring an equipment operation data set from equipment, processing each operation data record of the data set to generate an original sample, and obtaining an original sample set comprising a plurality of original samples; encoding each original sample in the original sample set to generate an individual, and obtaining an initial population comprising a plurality of individuals; constructing a fitness function according to fault types included in the original sample set; performing genetic iteration on the population according to the fitness function to obtain a target population; determining an optimal individual in the target population; determining an optimized feature set of the original sample set according to the chromosome of the optimal individual; processing each original sample in the original sample set according to the optimized feature set to generate a training sample, and obtaining a training sample set comprising a plurality of training samples; and training the classifier according to the training sample set. The invention also discloses computing equipment and a computer readable storage medium.

Description

technical field [0001] The invention relates to the field of equipment fault diagnosis, in particular to a training method for equipment fault detection classifiers, computing equipment and storage media. Background technique [0002] With the development of computer and sensor technology, more and more computers are monitoring the operation of equipment and automatically judging the operation of equipment. Usually, by deploying sensors in the equipment, the operating data of the equipment is collected, and the operating data is analyzed by a computer to obtain the analysis results. However, due to the large number of operating data collection items and the complex operating conditions of the equipment, the corresponding relationship between operating data and equipment failure types is not clear enough. Therefore, a large number of original features have to be proposed for fault identification, but due to the constraints of many factors such as the size of the classifier, ...

AI Technical Summary

Problems solved by technology

However, after the feature set is removed, some features will be missed, which will cause the obtained classifier to fail to achieve good diagnostic results.

Images