This paper is the second part of a two-part series on an integrated machine performance
monitoring and fault diagnostics system. The entire project represents substantial
research and development efforts taking place at The University of Iowa. The objective of
the project was to develop a system with the following capabilities: 1) on-line machine
monitoring, 2) rapid and robust machine fault diagnostics, 3) detection of multiple faults,
and 4) fusion of multiple sensory inputs. It is believed that this integrated machine
monitoring and fault diagnostics system will provide a solid foundation for rational
predictive maintenance.
This paper focuses on the theoretical foundation and applications of those technologies
adopted/developed for machine fault detection. It also explains the implementation
procedures of those technologies. In order for the readers to better understand how the
on-line machine monitoring system operates, a simple sample session is provided.
