Bearing fault detection with application to PHM Data Challenge

Abstract

Mechanical faults in production lines can result in partial or total breakdown of a production line, destruction of equipment and even catastrophes. Implementation of an adequate fault detection system represents an important step towards early detection of such faults, thus reducing the risk of unexpected failures. Traditionally, fault detection process is done by comparing the observed machine state with a set of historical data representing the fault--free state. However, such historical data are rarely available. In such cases, the fault detection process is performed by examining whether a particular pre--modeled fault signature can be matched within the signals acquired from the monitored machine. In this paper we propuse a solution to a problem of fault detection without any prior data, presented at PHM'09 Data Challenge. The solution is based on a two step algorithm. The first step, based on the spectral kurtosis method, is used to determine whether a particular experimental run is likely to contain a faulty element. In case of a positive decision, fault isolation procedure is applied as the second step. The fault isolation procedure was based on envelope analysis of filtered vibration signals. The filtering of the vibration signals was performed in the frequency band that maximizes the spectral kurtosis. The effectiveness of the proposed approach was evaluated for bearing fault detection, on the vibration data obtained from the PHM'09 Data Challenge.

Keywords

• Data-driven methods for fault detection
• diagnosis
• and prognosis