Acoustic Emission and Artificial Intelligent Methods in Condition Monitoring of Rotating Machine – A Review

Machinery condition monitoring has become one of the essential components in the industry due to the ability of providing insight to the machine condition during operation as well as enhancing productivity and increasing machine reliability. This paper provides a review on using acoustic emission (AE) technique combined with artificial intelligence (AI) methods in the field of machinery condition monitoring and fault diagnosis. Even though many papers have been published in the area of machinery condition monitoring, this paper puts emphasis on gears and bearing only. Furthermore, the paper attempts to summarize and evaluate the recent condition monitoring research that utilizing AI includes fuzzy logic, artificial neural network (ANN), support vector machine (SVM), and genetic algorithms (GA) in fault diagnosis, fault classification, fault localization and fault size estimation in gear and bearing based on features extraction from AE signal. Machine condition monitoring philosophy and techniques have evolved based on intellectual systems. However, the acquired AE signal was found to be complicated in the application of gear and bearing monitoring, therefore it is required more attention. In addition, the use of AI methods in gear and bearing fault diagnosis still in the growing stage that requires lots of encouragement as it has a promising future in the field of machinery condition monitoring