Classifier fusion of vibration and acoustic signals for fault diagnosis and classification of planetary gears based on Dempster–Shafer evidence theory

Abstract

Nowadays, the ever increasing need for higher accuracy, reliability and security in modern industries has given rise intensively to the use of multi-sensor data fusion method in fault diagnosis of industrial equipment. In this article, an effective and powerful method for precise fault diagnosis of planetary gearbox based on fusion of vibration and acoustic data using the Dempster–Shafer theory is presented. For this purpose, the vibration and acoustic signals in different modes of the gears were first received simultaneously by two separate sensors and then were transmitted from time domain to time–frequency domain using wavelet analysis. After signal processing, each sensor's data were transferred to a local classifier for primary fault diagnosis. Local classification was performed by artificial neural network classifier. The outputs of the local classification were used as the inputs into Dempster–Shafer rules for fusion of classifiers and achieving the final accuracy of the classification. In primary fault diagnosis, the accuracy of fault classification based on vibration and acoustic signals was obtained as 86% and 88%, respectively. After incorporating the outcomes of two sensors, the final accuracy of the classification was calculated as 98% which indicates a 10% jump compared to single-sensor mode. These results indicate the effectiveness of the data fusion method in condition monitoring and fault diagnosis of the equipment. Moreover, in this article, the capability of Dempster–Shafer theory in the fusion of uncertain data and the increase of accuracy in the classification was demonstrated to a quiet acceptable level.