Model-based fault identification of power generation turbine engines using optimal pursuit

This work presents the results of applying an advanced fault detection and isolation technique to two ground-based power generation turbine engines. The advanced technique uses physics-based model with an optimal pursuit solution method. The technique automatically finds the best fault scenario to match measured (or test) data. The best fault scenario provides information about parameter deviations (i.e., fault detection) and fault-contributing components (i.e., isolation). The technique is independent of the thresholds used in fault detection as in some other techniques. The technique is effective even under the condition where data are scarce and widely spaced in time. Operational data from two Ishikawajima-Harima Heavy Industries (1H1) 1M270 engines were made available to Scientific Monitoring, Inc. (SMI). The purpose of the data is to apply SMI's model-based fault identification expertise to industrial power generation turbines. The investigation was conducted with extremely limited knowledge of the engines and their maintenance histories. The measured variables, provided in the data set, only include speed, air inlet temperature, power, exhaust temperature, fuel flow, and compressor discharge pressure. With these limited engine data, we modified an existing, generic model for turbine engines and developed the optimal pursuit method to "hunt" for suspicious fault states. The detection results were confirmed by the engine manufacturer IH1. The detection accuracy of this technique can be improved with additional data and knowledge about the IHI-IM270 engine. This technique can be readily generalized to fault/state detection of other types of equipment or assets in all industries.