Intelligent Prediction of Fault Severity of Tractor’s Gearbox by Time-domain and Frequency-domain (FFT phase angle and PSD) Statistics Analysis and ANFIS

Abstract

This study presents an approach to intelligent fault prediction based on time-domain and frequency-domain (FFT phase angle and PSD) statistical analysis, Principal component analysis (PCA) and adaptive Neuro-fuzzy inference system (ANFIS). After vibration data acquisition, the approach consists of three stages is conducted. First, different features, including time-domain statistical characteristics, and frequency-domain statistical characteristics are extracted to get more fault detection information. Second, three components by a principal component analysis are obtained from the original feature set. Finally, these three components are inputted into ANFIS for a development model of identifying different abnormal cases. The proposed approach is applied to fault diagnosis of gearbox's number one gear of MF285 tractor, and the testing results show that the proposed model can reliably predict different fault categories and severities.