Early Classification of Bearing Faults Using.pdfVIP

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, VOL. 60, NO. 2, FEBRUARY 2013 567 Early Classification of Bearing Faults Using Morphological Operators and Fuzzy Inference A. Santhana Raj and N. Murali Abstract—Bearing faults of rotating machinery are observed as impulses in the vibration signal, but it is mostly immersed in noise. In order to effectively remove this noise and detect the impulses, a novel technique with morphological operators and fuzzy inference is proposed in this paper. The effectiveness of the morphological operators lies with the correct selection of structuring elements (SEs). This paper also proposes a new algorithm for this SE selection based on kurtosis, thereby making the analysis free of empirical methods. When analyzed with three different sets of faults, the results show that this method is effective and robust in bringing out the impulses. With fuzzy inference being coupled to this new technique, it makes the algorithm to be able to detect early faults also. Index Terms—Fault detection, fuzzy systems, morphology, mul- tiple signal classification, signal processing algorithms. I. INTRODUCTION ARLY FAULT detection in rotating machineries is useful Ein terms of system maintenance and process automation, which will help to save millions on emergency maintenance and production costs. Faulty bearings contribute to most of the failures in rotating machinery [1], [2]. Quite naturally, fault identification of rolling element bearings has been a subject of extensive research. Bentley [3] had shown that approximately 90% of rolling- Fig. 1. Flowchart of proposed method to classify faults. element-bearing failures are related to either inne