Evaluation of Aircraft Engine Gas Path Diagnostic Methods Through ProDiMES

Koskoletos, Anastasios Orestis; Aretakis, N.; Alexiou, A.; Romesis, C.; Mathioudakis, K.

doi:10.1115/1.4040909

Cited by 12 publications

(18 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…c. For users of gas turbine power plants, another practical problem is that users often do not have any gas turbine thermodynamic modeling technology, let alone a thermodynamic model decision-making based diagnostic technology. For the existing data-driven artificial intelligence diagnosis methods that are commonly used, such as neural networks [22][23][24][25], and fuzzy logic [26][27][28][29], as illustrated in the fig. 2, it is often necessary to build on an existing component fault data sample set.…”

Section: Fig1 Thermodynamic Model Decision-making Based Gas-path Diagnosis Methodsmentioning

confidence: 99%

Gas Path Fault Diagnosis of Gas Turbine Engine Based on Knowledge Data-Driven Artificial Intelligence Algorithm

Jin

Ying

et al. 2021

IEEE Access

View full text Add to dashboard Cite

As the core power for the aviation industry, shipbuilding industry, and power station industry, it is essential to ensure that the gas turbines operate safely, reliably, greenly and efficiently. Learn from the advantages and disadvantages of the thermodynamic model based and data-driven artificial intelligence based gas-path diagnosis methods, a newfangled gas turbine gas-path diagnosis approach on the basis of knowledge data-driven artificial intelligence is proposed. That is a hybrid method of deep learning and gas path analysis. First, gas turbine thermodynamic model of the object to be diagnosed is constructed by adaptation modeling strategy. And the engine thermodynamic model is taken as the basal model to simulate various gas path faults. Secondly, a large number of knowledge data corresponding to component health parameters and gas turbine boundary condition parameters & gas-path measurable parameters are simulated by setting different component health parameter values and different boundary conditions based on this basal model. And next, define the vector composed of the boundary condition parameters & the gas path measurable parameters in the knowledge database as the input vector, and the component health parameter vector as the output vector, and a deep learning model for regression modeling of this knowledge database is designed. At last, along with the gas turbine engine runs, the trained model outputs component health parameters in real time after trained deep learning model is deployed to the corresponding gas turbine power plant. The simulation experiment results show that, accurate and quantified health parameters of each gas path component can be obtained by the proposed method in this paper, and the overall root mean square error does not exceed 0.033%, and the maximum relative error does not exceed 0.36%, which illustrates the proposed method has great application potential. INDEX TERMSGas turbine; thermodynamic model; component health parameter; gas path analysis; deep learning; SYMBOLS AND ABBREVIATIONS GPA Gas path analysis EOH Equivalent operating hour GRNN Generalized regression neural network BP Back propagation neural network RBF Radial basis function neural network DNN Deep learning model ANN Artificial neural network FC Fully connected layer SF Component health parameters u Boundary condition parameters Z Gas-path measurable parameters

show abstract

Section: Fig1 Thermodynamic Model Decision-making Based Gas-path Diagnosis Methodsmentioning

confidence: 99%

Gas Path Fault Diagnosis of Gas Turbine Engine Based on Knowledge Data-Driven Artificial Intelligence Algorithm

Jin

Ying

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Next, in order to accept an engine during pass-off testing, the performance parameters are monitored by analyzing their behaviour and trends. Different visualization techniques are being used, amongst them trend plots 27,28 and Cumulative Sum (CUSUM) plots. 29,30 Trend plots represent the mean engine performance and general scatter for each engine over a time period.…”

Section: Pass-off Real Test Data Analysismentioning

confidence: 99%

Three-spool turbofan pass-off test data analysis using an optimization-based diagnostic technique

Saias

Pellegrini

Brown

et al. 2021

Proceedings of the Institution of Mechanical Engineers, Part A:

View full text Add to dashboard Cite

Production engine pass-off testing is a compulsory technique adopted to ensure that each engine meets the required performance criteria before entering into service. Gas turbine performance analysis greatly supports this process and substantial economic benefits can be achieved if an effective and efficient analysis is attained. This paper presents the use of an integrated method to enable engine health assessment using real pass-off test data of production engines obtained over a year. The proposed method is based on a well-established diagnostic technique enhanced for a highly-complex problem of a three-spool turbofan engine. It makes use of a modified optimization algorithm for the evaluation of the overall engine performance in the presence of component degradation, as well as, sensor noise and bias. The developed method is validated using simulated data extracted from a representative adapted engine performance model. The results demonstrate that the method is successful for 82% of the fault scenarios considered. Next, the pass-off test data are analyzed in two stages. Initially, correlation and trend analyses are conducted using the available measurements to obtain diagnostic information from the raw data. Subsequently, the method is utilized to predict the condition of 264 production turbofan engines undergoing a compulsory pass-off test.

show abstract

“…Combined with machine learning and pattern-recognition techniques, the GPA approach can be an efficient tool to diagnose complex and hidden engine faults. Many machine-learning techniques have been employed for gas turbine diagnostics, for example, support vector machines (SVM) [8], genetic algorithms [9], fuzzy logic [10] and neuro-fuzzy inference systems [11], multi-layer perceptron (MLP) [12], probabilistic neural network (PNN) [13], and extreme learning machines (ELM) [14,15].…”

Section: Introductionmentioning

confidence: 99%

“…The output neuron receives a sum (a probability of the class) of the responses related to the training vectors of the corresponding class and a competitive transfer function chooses the class that produces the maximum probability; and (3) a nonlinear SVM. Koskoletos et al [13] proposed a diagnostic framework that integrated the stages of data processing, fault detection based on a cumulative sum algorithm, and fault identification intended to evaluate six different gas-path methods: PNN, KNN, estimation of health parameters with an optimization algorithm, a combinatorial approach through the examination of all possible combinations of health parameters and measurements, a method based on an adaptive engine model, and a hybrid method using PNN and adaptive model. This last hybrid approach uses an adaptive engine model and the a-priori information about the occurrence of a component fault in the engine.…”

Section: Introductionmentioning

confidence: 99%

Aircraft Engine Gas-Path Monitoring and Diagnostics Framework Based on a Hybrid Fault Recognition Approach

2021

View full text Add to dashboard Cite

Considering the importance of continually improving the algorithms in aircraft engine diagnostic systems, the present paper proposes and benchmarks a gas-path monitoring and diagnostics framework through the Propulsion Diagnostic Methodology Evaluation Strategy (ProDiMES) software developed by NASA. The algorithm uses fleet-average and individual engine baseline models to compute feature vectors that form a fault classification with healthy and faulty engine classes. Using this classification, a hybrid fault-recognition technique based on regularized extreme learning machines and sparse representation classification was trained and validated to perform both fault detection and fault identification as a common process. The performance of the system was analyzed along with the results of other diagnostic frameworks through four stages of comparison based on different conditions, such as operating regimes, testing data, and metrics (detection, classification, and detection latency). The first three stages were devoted to the independent algorithm development and self-evaluation, while the final stage was related to a blind test case evaluated by NASA. The comparative analysis at all stages shows that the proposed algorithm outperforms all other diagnostic solutions published so far. Considering the advantages and the results obtained, the framework is a promising tool for aircraft engine monitoring and diagnostic systems.

show abstract

Evaluation of Aircraft Engine Gas Path Diagnostic Methods Through ProDiMES

Cited by 12 publications

References 8 publications

Gas Path Fault Diagnosis of Gas Turbine Engine Based on Knowledge Data-Driven Artificial Intelligence Algorithm

Gas Path Fault Diagnosis of Gas Turbine Engine Based on Knowledge Data-Driven Artificial Intelligence Algorithm

Three-spool turbofan pass-off test data analysis using an optimization-based diagnostic technique

Aircraft Engine Gas-Path Monitoring and Diagnostics Framework Based on a Hybrid Fault Recognition Approach

Contact Info

Product

Resources

About