This thesis investigates the development of an automated fault detection system developed for a novel lightweight railway material haulage system;​ in particular, the study aims to detect railway track faults at the incipient stage to determine the feasibility of maintenance decision support, ultimately with the function of preventing catastrophic failure. The proposed approach is an extension of the current state of the art in fault detection of unsteady machinery.

The most common railway track faults associated with train derailment were considered;​ namely, horizontal and transverse crack propagation, mechanical looseness, and railbed washout were the faults of interest. A series of field experiments were conducted to build a database of vibration, speed, and localization data in healthy and faulted states. These data were used to develop, investigate, and validate the effectiveness of various approaches for fault detection.

A variety of feature sets and classification approaches were investigated to determine the best overall configuration for the fault detector. The feature sets were used to condense data segments and extract characteristics that were sensitive to damage, but insensitive to healthy variations due to unsteady operation. The pattern recognition classifiers were used to categorize new data members as belonging to the healthy class or faulted class.

The fault detection results from the proposed approach were promising. The feasibility of an automated online fault detection system for the lightweight material haulage system examined in this study was confirmed. The conclusions of this research outline the major potential for an effective fault detection system and address future work for the practical implementation of this system.