Performance-based fault diagnosis of a gas turbine engine using an integrated support vector machine and artificial neural network method

Abstract

An effective and reliable gas path diagnostic method that could be used to detect, isolate, and identify gas turbine degradations is crucial in a gas turbine condition-based maintenance. In this paper, we proposed a new combined technique of artificial neural network and support vector machine for a two-shaft industrial gas turbine engine gas path diagnostics. To this end, an autoassociative neural network is used as a preprocessor to minimize noise and generate necessary features, a nested support vector machine to classify gas path faults, and a multilayer perceptron to assess the magnitude of the faults. The necessary data to train and test the method are obtained from a performance model of the case engine under steady-state operating conditions. The test results indicate that the proposed method can diagnose both single- and multiple-component faults successfully and shows a clear advantage over some other methods in terms of multiple fault diagnosis. Moreover, 5-8 sets of measurements have been used to assess the prediction accuracy, and only a 2.3% difference was observed. This result indicates that the proposed method can be used for multiple fault diagnosis of gas turbines with limited measurements.

Development of the method for estimating the technical condition of gas pumping units by their accelerating characteristic

“…No less scientific papers [13][14][15][16][17][18] are devoted to parametric diagnostic methods. So, in [13] it was shown that information integration methods, such as Bayesian networks, fuzzy logic or probabilistic neural networks, can be used to implement a decision support system that can be used for parametric diagnostics of gas turbines.…”

“…The disadvantages of the work are similar to [14]. The methods of diagnosing defects in the gas path of gas turbine units (GTU) are the subject of [17,18]. A new methodology for the classification model for diagnosing faults in the gas path of a gas turbine in the form of a probabilistic neural network (PNN) is considered in [17].…”

“…It is compared with previously proposed methods, the results of which show that PNN is not inferior to other methods. In [18], a new combined method was proposed based on an artificial neural network and a support vector machine for diagnosing the gas path of a two-shaft gas turbine engine. The test results showed that the proposed method can be used to diagnose multiple malfunctions of gas turbines with limited measurements of technological parameters.…”

“…The test results showed that the proposed method can be used to diagnose multiple malfunctions of gas turbines with limited measurements of technological parameters. Diagnosing the technical condition of the gas path of the gas-turbine set-up using the methods considered [17,18] is carried out without taking into account the technical condition of other components of the gas-turbine set-point, including its automatic control system, which can affect the diagnostic result, which requires additional research.…”

An intelligent data filtering and fault detection method for gas turbine engines

“…On another study, Loboda [24] compared the gas turbine fault classification performance of KNN, multilayer perceptron (MLP), and PNN. In general, combining two or more methods showed different advantages in gas turbine diagnostics than using the methods individually [25,26].…”