Application of empirical mode decomposition and artificial neural network for automatic bearing fault diagnosis based on vibration signals Jaouher Ben Ali a,b,⇑ , Nader Fnaiech a , Lotfi Saidi a , Brigitte Chebel-Morello b , Farhat Fnaiech a a University of Tunis, National Higher School of Engineers of Tunis, Laboratory of Signal Image and Energy Mastery (SIME), 5 Avenue Taha Hussein, P.O. Box 56, 1008 Tunis, Tunisia b Automatic Controls and Micro-Mechatronic Systems Department, FEMTO-ST Institute, 24, Rue Alain Savary, 25000 Besançon, France article info Article history: Received 9 January 2014 Received in revised form 1 August 2014 Accepted 23 August 2014 Keywords: Artificial neural network (ANN) Bearing Condition and health management (CHM) Empirical mode decomposition (EMD) abstract Condition monitoring and fault diagnosis of rolling element bearings (REBs) are at present very important to ensure the steadiness of industrial and domestic machinery. According to the non-stationary and non- linear characteristics of REB vibration signals, feature extraction method is based on empirical mode decomposition (EMD) energy entropy in this paper. A mathematical analysis to select the most significant intrinsic mode functions (IMFs) is presented. Therefore, the chosen features are used to train an artificial neural network (ANN) to classify bearings defects. Experimental results indicated that the proposed method based on run-to-failure vibration signals can reliably categorize bearing defects. Using a proposed health index (HI), REB degradations are perfectly detected with different defect types and severities. Experimental results consist in continuously evaluating the condition of the monitored bearing and thereby detect online the severity of the defect successfully. This paper shows potential application of ANN as effective tool for automatic bearing performance degradation assessment without human intervention. Ó 2014 Elsevier Ltd. All rights reserved. 1. Introduction Today, diagnosis is a very important research area in industry. Traditional concepts of preventive and corrective maintenance are gradually supplemented by diagnosis form. The main objective of this maintenance type is to ensure the dependability of indus- trial systems and increase their availability with lower cost. How- ever, fault diagnosis is not an easy task; it is essentially a problem of pattern recognition. The most effective feature extraction and more accurate classifier are needed to obtain higher diagnostic accuracy [1]. Rolling element bearings (REBs) are widely used in industrial and domestic applications. REB is one of the most common components in modern rotating machinery and their failure is one of the most fre- quent reasons for machine breakdown. Approximately 45% of the failures are due to the bearing faults [2]. Failure surveys by the elec- tric power research institute (EPRI) indicate that bearing-related faults are about 40% among the most frequent faults in induction motors [3]. Although the development of this critical component has pro- gressed in a rapid manner, the development of an expert system for the diagnosis remains an important focus of research. One of the fundamental problems currently facing a wide range of indus- tries is how to identify a bearing fault before it reaches a critical level and catastrophic failure. Analyzing vibration signals is a quite common technique for mechanical system monitoring thanks to the great information that contain [4]. However, REB vibration signals are considered as non-stationary and non-linear [5]. Besides, noises present a seri- ous trouble in the study of this type of signals [6]. Moreover, the relatively weak bearing signals are always affected by quite stronger signals (gears, bars...) [5]. All these constraints lead us to converge to a single question: What is the most effective method for bearing fault diagnosis? To answer this question, many research lines have been devel- oped and many techniques are being used. In [7], artificial neural networks (ANN) and principal components analysis (PCA) are used to diagnose the severity of bearing outer race faults. Four bearing classes were examined; the no-fault class and three different notches in the outer race (0.15, 0.50 and 1.00 mm wide). http://dx.doi.org/10.1016/j.apacoust.2014.08.016 0003-682X/Ó 2014 Elsevier Ltd. All rights reserved. ⇑ Corresponding author at: Department of Electrical Engineering, Higher School of Engineers of Tunis, Laboratory of Signal Image and Energy Mastery (SIME), 5 Avenue Taha Hussein, P.O. Box 96, 1008 Tunis, Tunisia. Tel.: +216 96 568 115, +216 52 276 629. E-mail address: benalijaouher@yahoo.fr (J. Ben Ali). Applied Acoustics 89 (2015) 16–27 Contents lists available at ScienceDirect Applied Acoustics journal homepage: www.elsevier.com/locate/apacoust