Vibration feature extraction techniques for fault diagnosis of rotating machinery : a literature survey

The safety, reliability, efficiency and performance of rotating machinery are major concerns in industry. The task of condition monitoring and fault diagnosis of rotating machinery faults is significant but is often cumbersome and labour intensive. Effective and efficient feature extraction techniques are critical for reliably diagnosing rotating machinery faults. Various vibration feature extraction methods have been proposed for different types of rotating machinery during the past few decades. However, limited research has been conducted on synthesizing and analysing these techniques, resulting in apprehension when technicians need to choose a technique suitable for application. This paper presents an updated review of a variety of vibration feature extraction techniques that have demonstrated success when applied to rotating machinery. The literature is categorised into the following groups: time domain, frequency domain, time frequency analysis. The paper will comment on future directions for research on vibration feature extraction for fault diagnosis of rotating machinery.