Vibration-Based Intelligent Fault Diagnosis for Roller Bearings in Low-Speed Rotating Machinery

This paper proposes a new signal feature extraction and fault diagnosis method for fault diagnosis of low-speed machinery. Statistic filter (SF) and wavelet package transform (WPT) are combined with moving-peak-hold method (M-PH) to extract features of a fault signal, and special bearing diagnostic symptom parameters (SSPs) in a frequency domain that are sensitive to bearing fault diagnosis are defined to recognize fault types. The SF is first used to adaptively cancel noises, and then fault detection is performed by exploiting the optimum symptom parameters in a time domain to identify a normal or fault state. For precise diagnosis, the SSPs are calculated after the signals are processed by M-PH and WPT. A decision tree is used to structure intelligent diagnosis rules in each step until the states are fully and automatically detected. The efficacy of this method was confirmed by applying it to an experimental low-speed rotation machine.

I. Introduction

Rotating machinery is a crucial industrial component of the modern society. For example, motors currently supply over 50% of the mechanical energy supply to industrial applications in the United States [1]. About 40% of electrical motor failure events occur due to bearing faults [2]; bearings have a significant influence on the performance and operating efficiency of rotating machines. To date, the condition monitoring of roller bearings and other rotating equipment using vibratory analysis is an established technique and the industry standard. If bearing problems can be diagnosed quickly and accurately, equipment and components can be better protected from breakage [3]–[5].