Intelligent fault diagnosis of rolling bearing using deep wavelet auto-encoder with extreme learning machine

2018 ◽  
Vol 140 ◽  
pp. 1-14 ◽  
Author(s):  
Shao Haidong ◽  
Jiang Hongkai ◽  
Li Xingqiu ◽  
Wu Shuaipeng
Keyword(s):  
Fault Diagnosis ◽  
Extreme Learning Machine ◽  
Rolling Bearing ◽  
Intelligent Fault Diagnosis ◽  
Learning Machine

Intelligent Fault Diagnosis of Multichannel Motor–Rotor System Based on Multimanifold Deep Extreme Learning Machine

2020 ◽  
Vol 25 (5) ◽  
pp. 2177-2187 ◽  
Author(s):  
Xiaoli Zhao ◽  
Minping Jia ◽  
Peng Ding ◽  
Chen Yang ◽  
Daoming She ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Extreme Learning Machine ◽  
Rotor System ◽  
Intelligent Fault Diagnosis ◽  
Learning Machine

A sequential feature extraction method based on discrete wavelet transform, phase space reconstruction, and singular value decomposition and an improved extreme learning machine for rolling bearing fault diagnosis

2017 ◽  
Vol 232 (6) ◽  
pp. 635-649 ◽  
Author(s):  
DZ Li ◽  
X Zheng ◽  
QW Xie ◽  
QB Jin
Keyword(s):  
Fault Diagnosis ◽  
Phase Space ◽  
Extreme Learning Machine ◽  
Rolling Bearing ◽  
Singular Value ◽  
Discrete Wavelet ◽  
Bearing Fault ◽  
Bearing Fault Diagnosis ◽  
Learning Machine ◽  
Value Decomposition

A novel fault diagnosis approach based on a combination of discrete wavelet transform, phase space reconstruction, singular value decomposition, and improved extreme learning machine is presented in rolling bearing fault identification and classification. The proposed method provides proper solutions for improving the accuracy of faults classification. To achieve this goal, initial signals are divided into sub-band wavelet coefficients using discrete wavelet transform. Then, each of sub-band is mapped into three-dimensional space using the phase space reconstruction method to completely describe characteristics in the high dimension. Thereafter, singular values are calculated by singular value decomposition method, which demonstrate crucial variances in original vibration signal. Lastly, an improved extreme learning machine is adopted as a classifier for fault classification. The proposed method is applied to the rolling bearing fault diagnosis with non-linear and non-stationary characteristics. Based on outputs of the improved extreme learning machine, the working condition and fault location could be determined accurately and quickly. Achieved results, compared with other schemes, show that the proposed scheme in this article can be regarded as an effective and reliable method for rolling bearing fault diagnosis.

Sign in / Sign up

Export Citation Format

Share Document