Study on Fault Diagnostics of a Turboprop Engine Using Inverse Performance Model and Artificial Intelligent Methods

Abstract

Recently, the health monitoring system of major gas path components of gas turbine uses mostly the model based method like the Gas Path Analysis (GPA). This method is to find quantity changes of component performance characteristic parameters such as isentropic efficiency and mass flow parameter by comparing between measured engine performance parameters such as temperatures, pressures, rotational speeds, fuel consumption, etc. and clean engine performance parameters without any engine faults which are calculated by the base engine performance model. Currently, the expert engine diagnostic systems using the artificial intelligent methods such as Neural Networks (NNs), Fuzzy Logic and Genetic Algorithms (GAs) have been studied to improve the model based method. Among them the NNs are mostly used to the engine fault diagnostic system due to its good learning performance, but it has a drawback due to low accuracy and long learning time to build learning data base if there are large amount of learning data. In addition, it has a very complex structure for finding effectively single type faults or multiple type faults of gas path components. This work builds inversely a base performance model of a turboprop engine to be used for a high altitude operation UAV using measured performance data, and proposes a fault diagnostic system using the base engine performance model and the artificial intelligent methods such as Fuzzy logic and Neural Network. The proposed diagnostic system isolates firstly the faulted components using Fuzzy Logic, then quantifies faults of the identified components using the NN leaned by fault learning data base, which are obtained from the developed base performance model. In leaning the NN, the Feed Forward Back Propagation (FFBP) method is used. Finally, it is verified through several test examples that the component faults implanted arbitrarily in the engine are well isolated and quantified by the proposed diagnostic system.

Study on Gas Turbine Gas-Path Fault Diagnosis Method Based on Quadratic Entropy Feature Extraction

“…Nowadays pattern recognition and machine learning based on data-driven artificial intelligence technology, such as neural network (NN) [5], Bayesian network [6], [7], fuzzy logic [8], [9], support vector basis and rough set theory [10], have been used for gas path diagnosis based on existing fault sample sets or maintenance experience, as shown in fig.2. However, for the types of faults not involved in the sample set, it is often difficult to obtain accurate diagnostic results by these methods.…”

Review on Advanced Health Monitoring Methods for Aero Gas Turbines using Model Based Methods and Artificial Intelligent Methods

“…An effective diagnostic system using the accurate base engine performance model of the PWC PT6A-67 turboprop engine, Fuzzy Logic and NNs has been proposed [58][59]. Figure 9 shows the flow of the proposed diagnostic system.…”

“…Moreover it has a 2 stage reduction gear box, and the power is flat-rated to 1200 hp. Table 4 illustrates the design point performance data of this engine [58].…”

A performance degradation evaluation method for a turbocharger in a diesel engine

“…Therefore, it is necessary to adopt a new method based on the existing fault diagnosis theory and technology, to obtain a diagnostic model that can solve practical problems. The data-driven methods [1,2], such as pattern recognition [3][4][5][6] and machine learning [7], neural networks (NN) [8,9], Bayesian networks [10,11], fuzzy logic [12], support vector machine [13] and rough set theory [14], often need to be built on existing equipment fault sample sets. And these methods are often difficult to give accurate diagnostic results for fault types not covered in the sample.…”