HYDES: A Web-based hydro turbine fault diagnosis system

Abstract

The hydro turboset is the key equipment of the electric power system. Thus, it is very important and necessary to monitor and diagnose the running conditions and the faults of the hydro turboset for the safe and normal running of the electric power system. Fault diagnosis of the hydro turbine is a complicated process and requires a high level of expertise. In order to significantly reduce the cost consumed in the fault diagnosis, to increase the consistency of diagnosing decision-making, and to better utilize the turbine's management information resource, in this paper, an integrated Web-based expert system of the fault diagnosis has been developed for the hydro turbine of a power station. Moreover, it can be regarded as an advisory tool to those who have much technical experience and as a training tool for the less-experienced personnel who seek guidance and advice. This paper describes a research project aiming to develop a Web-based intelligent diagnosis system for the hydro turbine and discusses the process of the fault diagnosis and the difficulties involved in developing the system. The paper also includes several practical issues related to the architectures of the intelligent Web-based applications. The system is built on a three-tier architecture, including the following components: knowledge base, inference engine, knowledge administration interface, user interface, knowledge administration unit and integrated database. The expert system employs heuristic rules to diagnose the hydro turbine fault. Some issues on developing Web-based expert systems are also discussed.