Synergistic use of soft computing technologies for fault detection in gas turbine engines

In this paper, we present a synergistic approach to startup fault detection and diagnosis (FDD) in gas turbine engines. The method employs statistics, signal processing, and soft computing techniques in a complementary manner to address fault detection at transient conditions. Traditional turbine engine FDD methods are based on engine data collected at steady-state conditions. However, incipient faults are difficult to diagnose using steady-state engine data; only engine faults that are fairly developed can be detected using conventional methods. Because incipient engine component faults are often manifest in the engine startup characteristics, we present a method to characterize the engine transient startup. Engine sensor data during engine startup are recorded in time series format. The sensor profiles corresponding to "good" and "bad" engine startups are sampled using the bootstrap technique. A feature vector is extracted in two steps, and signal processing is followed by the feature vector selection. In the signal processing step, principal component analysis (PCA) is applied to reduce the samples consisting of sensor profiles into a smaller set. In the feature vector selection step, a cost function is defined, and important discriminating features for fault diagnosis are distilled from the PCA output vector. The features obtained from this step are then classified using neural-network-based methods. The "leave-one-out" approach to cross validation is applied to obtain an objective evaluation of the neural network training. The proposed FDD method is evaluated using actual engine startup data, and the results are presented.