Gas Path Performance Research Articles

Intelligent Reasoning for Gas Turbine Fault Isolation and Ambiguity Resolution

An engine health management (EHM) system typically consists of automated logic for data acquisition, parameter calculation, anomaly detection and eventually, fault identification (or isolation). Accurate fault isolation is pivotal to timely and cost-effective maintenance but is often challenging due to limited fault symptom observability and the intricacy of reasoning with heterogeneous parameters. Traditional fault isolation methods often utilize a single fault isolator (SFI) that primarily relies on gas path performance parameters. While effective for many performance-related faults, such approaches often suffer from ambiguity when two or more faults have signatures that are very similar when monitored by a rather limited number of gas path sensors. In these cases, the ambiguity often has to be resolved by experienced analysts using additional information that takes many different forms, such as various nongas path symptoms, full authority digital engine control fault codes, comparisons with the companion engine, maintenance records, and quite often, the analyst's gas turbine domain knowledge. This paper introduces an intelligent reasoner that combines the strength of an optimal, physics-based SFI and a fuzzy expert system that mimics the analytical process of human experts for ambiguity resolution. A prototype diagnostic reasoner software has been developed and evaluated using existing flight data. Significant performance improvements were observed as compared with traditional SFI results. As a generic reasoning framework, this approach can be applied not only to traditional snapshot data, but to full flight data analytics as well.

An Iterative Reduced KPCA Hidden Markov Model for Gas Turbine Performance Fault Diagnosis

To improve gas-path performance fault pattern recognition for aircraft engines, a new data-driven diagnostic method based on hidden Markov model (HMM) is proposed. A redundant sensor somewhat interferes with fault diagnostic results of the HMM, and it also increases the computational burden. The contribution of this paper is to develop an iterative reduced kernel principal component analysis (IRKPCA) algorithm to extract fault features from original high-dimension observation without large additional calculation load and combine it with the HMM for engine gas-path fault diagnosis. The optimal kernel features are obtained by iterative sequential forward selection of the IRKPCA, and the features with lower dimensions are contracted through a trade-off between the fault information and modeling data scale in reduced kernel space. The similarity degree is designed to simplify the HMM modeling data using fault kernel features. Test results show that the proposed methodology brings a significant improvement in diagnostic confidence and computational efforts in the applications of a turbofan engine fault diagnosis during its steady and dynamic process.

Active Fault Tolerant Control with self-enrichment capability for gas turbine engines

In this paper, an Active Fault Tolerant Control (AFTC) system with self-enrichment capability is proposed to deal with both the anticipated and unanticipated gas-path performance deteriorations in the industrial gas turbine engines. For this purpose, a hybrid fault diagnosis system with self-enrichment capability is proposed to take advantage of the positive features of fuzzy-based and global optimization-based Fault Detection and Identification (FDI) methods. The proposed FDI system provides the possibility of dealing with the unanticipated or unknown deteriorations. In order to design the proposed AFTC system, the parameters of the control system are optimized for a set of predefined deteriorations and through this a bank of control system parameters is created for the anticipated health conditions. The proposed FDI system verifies whether the detected health condition is an anticipated condition or not. In the case of the anticipated deteriorations, the proposed AFTC system selects the controller parameters from the bank of control system parameters, according to the current health condition; while in the case of the unanticipated deteriorations, the controller parameters will be determined through the optimization process. By adding the new set of optimized parameters to the bank of control system parameters, the database of the proposed AFTC system will gradually enrich to cope with a broader range of the engine deteriorations. The results obtained in the present work reveal that, the proposed AFTC system can preserve the engine safety and operational constraints; in the case of some deteriorations at the expense of a drop in the availability (due to a necessary trip or load shedding) and in some other cases even without losing the engine availability (by avoiding any unnecessary trip or load shedding). This is while, according to the results obtained, in the case of some health conditions, employing the controller designed for clean condition may cause the turbine over-temperature, loss of surge margin, and also a drop in the availability.

A Fault Diagnosis Approach for Gas Turbine Exhaust Gas Temperature Based on Fuzzy C-Means Clustering and Support Vector Machine

As an important gas path performance parameter of gas turbine, exhaust gas temperature (EGT) can represent the thermal health condition of gas turbine. In order to monitor and diagnose the EGT effectively, a fusion approach based on fuzzy C-means (FCM) clustering algorithm and support vector machine (SVM) classification model is proposed in this paper. Considering the distribution characteristics of gas turbine EGT, FCM clustering algorithm is used to realize clustering analysis and obtain the state pattern, on the basis of which the preclassification of EGT is completed. Then, SVM multiclassification model is designed to carry out the state pattern recognition and fault diagnosis. As an example, the historical monitoring data of EGT from an industrial gas turbine is analyzed and used to verify the performance of the fusion fault diagnosis approach presented in this paper. The results show that this approach can make full use of the unsupervised feature extraction ability of FCM clustering algorithm and the sample classification generalization properties of SVM multiclassification model, which offers an effective way to realize the online condition recognition and fault diagnosis of gas turbine EGT.

Gas Path Health Monitoring for a Turbofan Engine Based on a Nonlinear Filtering Approach

Different approaches for gas path performance estimation of dynamic systems are commonly used, the most common being the variants of the Kalman filter. The extended Kalman filter (EKF) method is a popular approach for nonlinear systems which combines the traditional Kalman filtering and linearization techniques to effectively deal with weakly nonlinear and non-Gaussian problems. Its mathematical formulation is based on the assumption that the probability density function (PDF) of the state vector can be approximated to be Gaussian. Recent investigations have focused on the particle filter (PF) based on Monte Carlo sampling algorithms for tackling strong nonlinear and non-Gaussian models. Considering the aircraft engine is a complicated machine, operating under a harsh environment, and polluted by complex noises, the PF might be an available way to monitor gas path health for aircraft engines. Up to this point in time a number of Kalman filtering approaches have been used for aircraft turbofan engine gas path health estimation, but the particle filters have not been used for this purpose and a systematic comparison has not been published. This paper presents gas path health monitoring based on the PF and the constrained extend Kalman particle filter (cEKPF), and then compares the estimation accuracy and computational effort of these filters to the EKF for aircraft engine performance estimation under rapid faults and general deterioration. Finally, the effects of the constraint mechanism and particle number on the cEKPF are discussed. We show in this paper that the cEKPF outperforms the EKF, PF and EKPF, and conclude that the cEKPF is the best choice for turbofan engine health monitoring.

Data-Driven Based Gas Path Fault Diagnosis for Turbo-Shaft Engine

In order to improve diagnostic accuracy and reduce the rate of misdiagnosis to the aircraft engine gas path faulty, the methods based on data-driven and information fusion are developed and analyzed. BP neural network (NN) and RBF neural network based on data-driven single gas path fault diagnosis method is introduced firstly. Design gas path performance estimators and the fault type classification for turbo-shaft engine. Then the gas path fused diagnostic structure based on D-S evidence theory and least squares support vector machine are developed. Comparisons of the turbo-shaft engine gas path fault diagnosis verify the feasibility and effectiveness of the gas path fault diagnosis based on information fusion.

A Foreign Object Damage Event Detector Data Fusion System for Turbofan Engines

Abstract : A Data Fusion System designed to provide a reliable assessment of the occurrence of Foreign Object Damage (FOD) in a turbofan engine is presented. The FOD-event feature level fusion scheme combines knowledge of shifts in engine gas path performance obtained using a Kalman filter., with bearing accelerometer signal features extracted via wavelet analysis, to positively identify a FOD event. A fuzzy inference system provides basic probability assignments (bpa) based on features extracted from the gas path analysis and bearing accelerometers to a fusion algorithm based on the Dempster-Shafer-Yager Theory of Evidence. Details are provided on the wavelet transforms used to extract the foreign object strike features from the noisy data and on the Kalman filter-based gas path analysis. The system is demonstrated using a turbofan engine combined-effects model (CEM), providing both gas path and rotor dynamic structural response, and is suitable for rapid-prototyping of control and diagnostic systems. The fusion of the disparate data can provide significantly more reliable detection of a FOD event than the use of either method alone. The use of fuzzy inference techniques combined with Dempster-Shafer-Yager Theory of Evidence provides a theoretical justification for drawing conclusions based on imprecise or incomplete data.

A Gas Path Performance Diagnostic System to Reduce J75-P-17 Engine Overhaul Costs

The objective of this program was to develop a performance diagnostic system to analyse gas path performance and to recommend economical component replacement and/or modifications to minimize overhaul costs by increasing post-overhaul acceptance rates at the Oklahoma City Air Logistics Center (OCALC). The diagnostic system utilizes a computer simulation of the J75-P-17 engine which was developed using experimental data from five J75-P-17 engine builds tested at the AEDC. The computer simulation is the heart of the diagnostic system and provides performance partial derivatives to aid in evaluating changes in component behavior. Implementation of the diagnostic system at the OCALC is in progress.

Closure to “Discussion of ‘A Gas Path Performance Diagnostic System to Reduce J75-P-17 Engine Overhaul Costs’” (1978, ASME J. Eng. Power, 100, p. 697)

Closure to “Discussion of ‘A Gas Path Performance Diagnostic System to Reduce J75-P-17 Engine Overhaul Costs’” (1978, ASME J. Eng. Power, 100, p. 697)