Automation of Troubleshooting and Diagnostics of Power Plant Equipment Faults

Improving the use of power plant information sources for equipment fault diagnosis will help electric utilities meet plant availability goals and reduce operations and maintenance costs. The combination of data from multiple information sources--such as data historians, predictive maintenance technologies, and operator rounds-can provide a holistic view of condition for a given item of equipment. The Electric Power Research Institute (EPRI) has designed a new diagnostic analysis software application that assists electric power generation plant staff in identifying equipment faults early, enabling rapid incident response and the prevention of failures for critical power generation equipment. This paper describes EPRI’s work on designing a set of software products that combine features from multiple sources of plant information to assist with troubleshooting and diagnostics. INTRODUCTION In competitive environments, power plants must operate under reduced operations and maintenance budgets while maintaining high reliability and availability. Early detection of equipment faults and subsequent planning of maintenance actions help reduce costs while maximizing availability. However, detection of equipment faults and subsequent troubleshooting often requires additional information outside of what traditional process instrumentation provides. In a new plant design, it is desirable to install sensors based not only on process control design, but also on equipment fault detection needs as identified through a structured failure modes effects analysis (FMEA) and/or fault tree analysis. For existing plants, however, information obtained manually through predictive maintenance or operator rounds can be used alongside process data for detecting and diagnosing equipment faults. This paper describes a set of diagnostic applications that has been designed for use by power industry personnel that have a role in troubleshooting and diagnosis of plant equipment.