Authors: M. Amarnath; Deepak Jain; V. Sugumaran; Hemantha Kumar
Addresses: Indian Institute of Information Technology, Design and Manufacturing, Dumna Airport Road, P.O. Khamaria, Jabalpur-482005, Madhya Pradesh, India ' SMBS, VIT University, Chennai Campus, Vandalur-kelambakam Road, Chennai-600048, India ' SMBS, VIT University, Chennai Campus, Vandalur-kelambakam Road, Chennai-600048, India ' National Institute of Technology Karnataka, Surathkal, Mangalore-575025, Karnataka, India
Abstract: Gears are one of the vital transmission elements, finding numerous applications in small, medium and large machinery. The vibration signals of a rotating machine contain dynamic information about its health condition. There are many articles in the literature reporting the suitability of vibration signals for fault diagnosis applications. Many of them are based on FFT, and have their own drawbacks with non-stationary signals like the ones from gears. Hence, there is a need for the development of new methodologies to infer diagnostic information from such signals. This paper uses the vibration signals acquired from gears in good and simulated faulty conditions for the purpose of fault diagnosis through the machine learning approach. A vibration-based condition monitoring system is presented for the helical gear box as it plays a relatively critical role in most of the industries. This approach has mainly three steps, namely, feature extraction, classification, and comparison of classification. This paper presents the use of the naïve Bayes algorithm and Bayes net algorithm, for fault diagnosis through statistical features extracted from the vibration signals of good and faulty components of the helical gear box.
Keywords: helical gears; gearbox faults; fault diagnosis; statistical analysis; naive Bayes; Bayes net; simulation; vibration signals; rotating machinery; machine learning; condition monitoring.
International Journal of Decision Support Systems, 2015 Vol.1 No.1, pp.4 - 17
Received: 06 Nov 2012
Accepted: 22 Sep 2013
Published online: 02 Feb 2015 *