Improving Power Plant Availability Through Advanced Engine Diagnostic Techniques

Technological advances and high cost of ownership have resulted in considerable interest in advanced maintenance techniques. Quantifying fault and consequently availability requires the use of gas turbine and combined cycle models able to undertake appropriate diagnostics and life cycle costing. These are complex areas as they include the simulation of such issues as performance and assessment of degraded gas turbines, life usage and risk analysis. This paper describes how the recent developments in engine diagnostics using advanced techniques like Artificial Neural Networks (ANN) and Genetic Algorithm (GA) based technique have opened new opportunities in the field of engine fault diagnostics. It also discusses the potential of advanced engine diagnostics using such features as ANN and GA in contributing to the management of availability for industrial gas turbines.