Open AccessRolling Bearing Fault Diagnosis Based on PCA-ResNet
Author(s) -
Xinjie Peng,
Zhigang Wang,
Binbin Li,
Long Qian,
Bin Jiao
Publication year - 2022
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2218/1/012082
Subject(s) - principal component analysis , artificial intelligence , fault (geology) , computer science , residual , bearing (navigation) , pattern recognition (psychology) , artificial neural network , noise reduction , task (project management) , identification (biology) , support vector machine , fault detection and isolation , deep learning , noise (video) , machine learning , residual neural network , data mining , engineering , algorithm , botany , systems engineering , seismology , actuator , image (mathematics) , biology , geology
Aiming at the situation that there are many interference factors in the collected signals of rolling bearings working in harsh and complex environment. Propose A method of noise reduction based on principal component analysis (PCA) and fault diagnosis and classification based on residual neural network (ResNet). Experimental results show that this method can effectively complete the task of fault identification and classification, and is superior to LeNet-5, SVM, DNN and other common deep learning methods.