Fault Diagnosis of Machines via Parameter Estimation and Knowledge Processing

Abstract

Abstract For further improvement of the reliability and safety of machines the automatic early detection and localization of faults is of high interest. The conventional approach is to monitor some important variables like temperatures, pressures, vibrations and to generate alarms if certain limits are exeeded. However, developing internal faults are in this way only detected at a rather late stage. By applying static and dynamic process models and common process input and output measurements the inherent relationships and redundancies can be used to detect faults earlier and to localize them better. Changes in process and signal parameters are very well suited for fault detection. The paper describes a general methodology for machines and other processes by using few measurements, dynamic process and signal models and parameter estimation to generate symptoms. The detected symptoms are fed into a knowledge based fault diagnosis procedure. Analytical and heuristic knowledge is treated via fault-symptom trees, process history and plausibility measures. The considered machines consist of a motor, a drive chain and a working process or load. They may be electrical motor or combustion engine driven pumps, fans or machine tools with gear or belt drive chains. The described methodology was developed and tested experimentally for several machines. As one example, experimental results are shown for a d.c. motor powered feed drive of a machine tool.