Integrated Diagnostic System for the Equipment of Power Plants: Part I — Formulation and Algorithms

Abstract

The output capacity of combined cycle power plants is reduced in many cases, and sometimes forced to outages, when its main components are affected by faults, i.e., when the rotating equipment such as turbines, generators, compressors, pumps and fans suffer a failure. Normally, the overall reduction of the efficiency, and sometimes the component efficiencies, is monitored but it is difficult to identify the primary causes of the fault of the specific equipment that causes the reduction of plant efficiency. Therefore, to reduce the time of faulty operation, a precise diagnostic tool is needed. One such tool is an expert system approach, which is presented in this work. It consists of several expert systems for the identification of the faults caused by deterioration of the inner parts of the equipment, Fig. 1. Such faults not only reduce the plant efficiency but in many cases also increase the vibrations of the rotor-bearing system. Based on knowledge, the various expert systems have been constructed and their algorithms (efficiency reduction) developed for the following equipment: steam turbines, gas turbines and compressors, condenser, pumps and water cooling system. An expert system for detecting faults that increase the vibration of the rotor–bearing system is also presented. As far as the turbo compressor expert system is concerned the fault hybrid patterns previously developed were implemented and described elsewhere [1].