Automated Decision-Analytic Diagnosis of Thermal Performance in Gas Turbines

Abstract

We have developed an expert system for diagnosis of efficiency problems for large gas turbines. The system relies on a model-based approach that combines an expert’s probabilistic assessments with statistical data and thermodynamic analysis. The system employs a causal probabilistic graph, called a belief network, to update the likelihoods of alternative faults given information about diverse classes of information. In response to any subset of findings or reported observations, the system suggests the most cost-effective tests to perform to determine the source of a performance problem. We discuss the decision-analytic methodology that underlies the development of the system and present results of an initial version of the system. Finally, we discuss future planned development and evaluation, toward the ultimate goal of applying the system in the day-to-day maintenance of gas-turbine power plants.