Rolling bearing fault diagnosis and health assessment using EEMD and the adjustment Mahalanobis–Taguchi system

For the timely identification of the potential faults of a rolling bearing and to observe its health condition intuitively and accurately, a novel fault diagnosis and health assessment model for a rolling bearing based on the ensemble empirical mode decomposition (EEMD) method and the adjustment Mahalanobis–Taguchi system (AMTS) method is proposed. The specific steps are as follows: First, the vibration signal of a rolling bearing is decomposed by EEMD, and the extracted features are used as the input vectors of AMTS. Then, the AMTS method, which is designed to overcome the shortcomings of the traditional Mahalanobis–Taguchi system and to extract the key features, is proposed for fault diagnosis. Finally, a type of HI concept is proposed according to the results of the fault diagnosis to accomplish the health assessment of a bearing in its life cycle. To validate the superiority of the developed method proposed approach, it is compared with other recent method and proposed methodology is successfully validated on a vibration data-set acquired from seeded defects and from an accelerated life test. The results show that this method represents the actual situation well and is able to accurately and effectively identify the fault type.