1 Intelligent Diagnosis Method for Ball Bearing faults Using Time-Domain Features and Neural Network Reza Zaeri a* , Behrooz Attaran a , Afshin Ghanbarzadeh a ,Karim Ansari Asl b a Mechanical Engineering, Shahid Chamran, Golestan, 83135161357, Ahvaz, Iran. b Electrical Engineering, Shahid Chamran, Golestan, 83135161357, Ahvaz, Iran. * Corresponding author e-mail: reza.zayeri@yahoo.com Abstract Vibration signals resulting from rolling element bearing defects, present a rich content of physical information, the appropriate analysis of which can lead to the clear identification of the nature of the fault. The bearing characteristic frequencies (BCF) contain very little ener- gy, and are usually overwhelmed by noise and higher levels of macro-structural vibrations. They are difficult to find in their frequency spectra when using the common technique of fast fourier transforms (FFT). Therefore, Envelope Detection (ED) has always been used with FFT to identify faults occurring at the BCF. In this paper procedure presents for fault diagno- sis of rolling element bearings through artificial neural network (ANN). The characteristic features of time-domain vibration signals of the rotating machinery with normal and defec- tive bearings have been used as inputs to the ANN consisting of input, hidden and output lay- ers. The features are obtained from envelope analysis of the signals. The input layer consists of nodes, one each for root mean square, skewness, kurtosis, standard deviation and combina- tive feature which called 'comb' of the envelope spectrum of the vibration signals. The results show the effectiveness of the ANN in diagnosis of the machine condition. The proposed pro- cedure requires only a few features extracted from the measured vibration data either directly or with simple preprocessing. The reduced number of inputs leads to faster training requiring far less iterations making the procedure suitable for on-line condition monitoring and diag- nostics of machines. Also results show that 'comb' feature is better than other features, be- cause the distance between classes increases considerably with this feature from envelop analysis. Keywords: envelope; artificial neural network; on-line condition monitoring; bearings. 1. Introduction Rolling element bearings are widely used in various types of machines ranging from simple electric fans to complex manufacturing facilities. Bearing faults, in fact, are a common cause of machinery failures. Therefore, an effective bearing fault diagnostic technique is critically needed for a wide array of industries for early detection of bearing defects so as to prevent machinery perform- ance degradation and malfunction. Several methods have been proposed in the literature for bearing fault detection. To inspect raw vibration signals, a wide variety of techniques have been introduced