Fault diagnosis of helical gear box using naïve Bayes and Bayes net. (5th February 2015)

• Record Type: Journal Article
• Authors: Amarnath, M.; Jain, Deepak; Sugumaran, V.; Kumar, Hemantha
• Is Part Of: International journal of decision support systems. Volume 1:Number 1(2015)
• Page Start: 4
• Page End: 17
• Publication Date: 2015-02-05
• Subjects: gear fault diagnosis -- fault diagnosis -- statistical analysis -- naïve Bayes -- Bayes net; Decision making -- Data processing -- Periodicals; 658.40302856312
• Languages: English
• ISSNs: 2050-6988

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.