Research on Equipment Fault Diagnosis Classification Model Based on Integrated Incremental Dynamic Weight Combination

EasyChair Preprint 1343

Abstract

This study proposes a classification model of equipment fault diagnosis based on integrated incremental learning mechanism based on the characteristics of industrial equipment status data. The model first proposes a Dynamic Weight Combination Classification Model based on Long Short-Term Memory (LSTM) and Support Vector Machine (SVM). Referred to as DWCLS model, it is used to solve the problem of fault feature extraction and classification in high noise equipment state data. Secondly, based on this model, integrated incremental learning mechanism and unbalanced data processing technology are introduced to solve massive unbalanced New data feature extraction and classification and sample category imbalance problem prevalent under equipment status data. Finally, an equipment fault diagnosis classification model based on integrated incremental dynamic weight combination is formed Equipment Fault Diagnosis Classification Model Based on Integrated Incremental Dynamic Weight Combination referred to as DWCMI model, and proved by experiments that the model can effectively overcome the problems of excessive data volume, unbalanced, high noise, and inability to correlate data samples in the process of equipment fault diagnosis.

Keyphrases: Integrated increment, Support Vector Machine, Unbalanced data processing, fault diagnosis, neural network

@booklet{EasyChair:1343,
  author    = {Jing Liu and Zhengshan Jiao and Zhijie Wang and Haipeng Ji and Bing Yu},
  title     = {Research on Equipment Fault Diagnosis Classification Model Based on Integrated Incremental Dynamic Weight Combination},
  howpublished = {EasyChair Preprint 1343},
  year      = {EasyChair, 2019}}