Feature Extraction and Recognition for Rolling Element Bearing Fault Utilizing Short-Time Fourier Transform and Non-negative Matrix Factorization

• Published in: Chinese journal of mechanical engineering Vol. 28; no. 1; pp. 96 - 105
• Main Authors: Gao, Huizhong, Liang, Lin, Chen, Xiaoguang, Xu, Guanghua
• Format: Journal Article
• Language: English
• Published: Beijing Chinese Mechanical Engineering Society 2015; Springer Nature B.V; School of Mechanical Engineering, Xi’an Jiaotong University, Xi’an 710049, China
• Edition: English ed.
• Subjects: Artificial neural networks; Bearing; Clustering; Electrical Machines and Networks; Electronics and Microelectronics; Engineering; Engineering Thermodynamics; Factorization; Fault diagnosis; Faults; Feature extraction; Feature recognition; Fourier transforms; Frequency distribution; Heat and Mass Transfer; Instrumentation; Learning theory; Machines; Manufacturing; Mapping; Mechanical Engineering; Neural networks; Power Electronics; Processes; Representations; Roller bearings; Theoretical and Applied Mechanics; Time-frequency analysis; Vibration; Vibration analysis; 人工神经网络; 振动信号; 滚动轴承故障; 特征提取; 短时傅立叶变换; 自动识别; 非负矩阵分解; 高维特征空间; rolling element bearing; feature extraction; non-negative matrix factorization; time-frequency distribution
• ISSN: 1000-9345; 2192-8258
• DOI: 10.3901/CJME.2014.1103.166

Due to the non-stationary characteristics of vibration signals acquired from rolling element bearing fault, thc time-frequency analysis is often applied to describe the local information of these unstable signals smartly. However, it is difficult to classitythe high dimensional feature matrix directly because of too large dimensions for many classifiers. This paper combines the concepts of time-frequency distribution（TFD） with non-negative matrix factorization（NMF）, and proposes a novel TFD matrix factorization method to enhance representation and identification of bearing fault. Throughout this method, the TFD of a vibration signal is firstly accomplished to describe the localized faults with short-time Fourier transform（STFT）. Then, the supervised NMF mapping is adopted to extract the fault features from TFD. Meanwhile, the fault samples can be clustered and recognized automatically by using the clustering property of NMF. The proposed method takes advantages of the NMF in the parts-based representation and the adaptive clustering. The localized fault features of interest can be extracted as well. To evaluate the performance of the proposed method, the 9 kinds of the bearing fault on a test bench is performed. The proposed method can effectively identify the fault severity and different fault types. Moreover, in comparison with the artificial neural network（ANN）, NMF yields 99.3% mean accuracy which is much superior to ANN. This research presents a simple and practical resolution for the fault diagnosis problem of rolling element bearing in high dimensional feature space.