Comparative analysis of two gas turbine diagnosis approaches

Gas turbine diagnostics that relies on gas path measurements is a well-developed area with many algorithms developed. They follow two general approaches, data-driven, and physics-based. The first approach uses deviations of monitored variables from their baseline values. A diagnostic decision is traditionally made in the space of these deviations (diagnostic features) by pattern recognition techniques, for example, artificial neural networks. The necessary fault classes can be constructed from deviation vectors (patterns) using the displays of real faults, and the approach has a theoretical possibility to exclude a complex physics-based model and its inherent errors from a diagnostic process. For the second approach known as a gas path analysis, a nonlinear physics-based model (a.k.a. thermodynamic model) is an integral part of a diagnostic process. The thermodynamic model (or the corresponding linear model) relates monitored variables with operational conditions and model's internal quantities called fault parameters. The identification of the thermodynamic model on the basis of known measurements of the monitored variables and operational conditions allows estimating unknown fault parameters. The knowledge of these parameters drastically simplifies a final diagnostic decision because great values of these parameters indicate damaged engine components and give us the measure of damage severity. As the diagnostic decision seems to be simple, the studies following this approach are usually completed by the analysis of fault parameter estimation accuracy, and complex pattern recognition techniques are not employed. Instead, simple tolerance-based fault detection and isolation is sometimes performed. It is not clear from known comparative studies which of the two approaches is more accurate, and the issue of seems to be challenging. This paper tries to solve this problem, being grounded on the following principles. We consider that a key difference of the second approach is a transformation from the diagnostic space of the deviations of monitored variables to the space of fault parameters. To evaluate the influence of this transformation on diagnostic accuracy, the other steps of the approaches should be equal. To this end, the pattern recognition technique employed in the data-driven approach is also included in the physics-based approach where it is applied to recognize fault parameter patterns instead of a tolerance-based rule. To realize and compare the data-driven and modified physics-based approaches, two corresponding diagnostic procedures differing only by the mentioned transformation have been developed. They use the same set of deviation vectors of healthy and faulty engines as input data and finally compute true classification rates that are employed to compare the procedures. The results obtained for different cases of the present comparative study show that the classification rates are practically the same for these procedures, and this is true for both fault detection and fault isolation. That is, correct classification does not depend on the mentioned transformation, and both approaches are equal from the standpoint of the classification accuracy of engine states.