Study On Fault Feature Extraction Of Mechanical Systems Using Independent Component Analysis Method

With the development of the fault diagnosis technology, the fault feature extraction is found to be the most important and difficult problem, which is the bottle-neck problem of the fault diagnosis technology and relates directly to both the veracity of diagnosis and the reliability of early diagnosis. To solve the fault feature extraction problem completely, theories, methods and techniques for information processing, especially modern signal processing, have been depended on, and new methods, new theories and new techniques for fault feature extraction are being researched.Based on these conditions, this paper describes the exploratory work of the fault feature extraction in mechanical systems with the novel efficient blind source separation (BSS) technology - Independent Component Analysis (ICA). The main contents of this paper include:(1) The theory of ICA and its popular algorithms are introduced. Then some properties are shown for each;(2) The data experiments are demonstrated, and sound signals are separated with the fast algorithm FastICA successfully;(3) The general failure modes and fault diagnosis methods of rolling bearing are introduced, and the experiment platform is set up to simulate the faults of rolling bearing based on vibration diagnosis method;(4) Several data about some types of bearing fault are analyzed by using ICA method, which are pre-processed and post-processed. The applicability of this method under several conditions is analyzed.The experimental results show that ICA method is effective for feature signal extraction of bearing fault, which is significant for early fault diagnosis of mechanical systems.