GAS TURBINE TRANSIENT SYSTEM EMPIRICAL MODELING FOR INCIPIENT FAULT DETECTION AND DIAGNOSIS USING ECHO STATE NETWORKS

摘要

We present a method of fault detection and diagnosis in turbine engines using a type of temporal neural network called the Echo State network (ESN). Temporal neural networks allow us to represent the complete engine operating range by complementing the first-principle models, which are usually restricted to takeoff and cruise phases. This complete coverage leads to more accurate anomaly detection and fault diagnosis systems because faults that are manifest only in particular phases can be detected. The time series sensor data from the engine is collected during particular aircraft flight phases such as startup, takeoff, cruise, and shutdown.rnWe use the echo state network to develop an incipient fault detection and diagnosis system. Echo state networks have several advantages over conventional types of temporal neural networks, including accuracy and ease of training. We demonstrate the efficacy of using the echo state networks to focus on flight phases that are difficult to model. In addition, using actual propulsion engine transient flight data, we compare the accuracy of the ESN with other methods of dynamic system modeling such as the autoregressive with exogenous (ARX) inputs, neural network ARX models, and the Elman recurrent neural network. The ESN is found to outperform other types of dynamic system models.