Dynamic neural network-based fault diagnosis of gas turbine engines

• Published in: Neurocomputing (Amsterdam) Vol. 125; pp. 153 - 165
• Main Authors: Sina Tayarani-Bathaie, S., Sadough Vanini, Z.N., Khorasani, K.
• Format: Journal Article Conference Proceeding
• Language: English
• Published: Amsterdam Elsevier B.V 01.02.2014; Elsevier
• Subjects: Aerospace engines; Aircraft jet engine; Applied sciences; Artificial intelligence; Bank of filters; Computational intelligence; Computer science; control theory; systems; Computer simulation; Connectionism. Neural networks; Continuous cycle engines: steam and gas turbines, jet engines; Control theory. Systems; Detection, estimation, filtering, equalization, prediction; Dynamic neural networks; Engines and turbines; Exact sciences and technology; Fault detection; Fault detection and isolation; Fault diagnosis; Gas turbine engines; Information, signal and communications theory; Mechanical engineering. Machine design; Modelling and identification; Multiple model schemes; Networks; Neural networks; Nonlinear dynamics; Signal and communications theory; Signal, noise; Telecommunications and information theory; Fault diagnosis; Bank of filters; Multiple model schemes; Dynamic neural networks; Fault detection and isolation; Aircraft jet engine; Computational intelligence; Infinite impulse response filter; Input output; Operating mode; Dynamical system; Filter bank; System identification; Dynamic model; Input output model; Capability index; Multimodel; Multimodel control; Turbojet; Jet engine; Neural network; Fan; Multilayer perceptrons; Gas turbine; Non linear effect; Aircraft; Artificial intelligence; Fault diagnostic; Multilayer network
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2012.06.050

In this paper, a neural network-based fault detection and isolation (FDI) scheme is presented to detect and isolate faults in a highly nonlinear dynamics of an aircraft jet engine. Towards this end, dynamic neural networks (DNN) are first developed to learn the input–output map of the jet engine. The DNN is constructed based on a multi-layer perceptron network which uses an IIR (infinite impulse response) filter to generate dynamics between the input and output of a neuron, and consequently of the entire neural network. The trained dynamic neural network is then utilized to detect and isolate component faults that may occur in a dual spool turbo fan engine. The fault detection and isolation schemes consist of multiple DNNs or parallel bank of filters, corresponding to various operating modes of the healthy and faulty engine conditions. Using the residuals that are generated by measuring the difference of each network output and the measured engine output various criteria are established for accomplishing the fault diagnosis task, that is addressing the problem of fault detection and isolation of the system components. A number of simulation studies are carried out to demonstrate and illustrate the advantages, capabilities, and performance of our proposed fault diagnosis scheme.