A novel integrated modeling approach for filter diagnosis in gas turbine air intake system

Jin, Yunfeng; Liu, Chao; Tian, Xin; Deng, Gaofeng; Guan, Yunlong; Jiang, Dongxiang

doi:10.1177/09576509211044392

Cited by 7 publications

(2 citation statements)

References 28 publications

(41 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Convolutional neural networks (CNN) 11 , 12 have also been employed in RUL prediction to attain improved accuracy. In addition to neural networks, researchers are investigating statistical probability methods like particle filtering (PF) and extended Kalman filtering (EKF) 13 .…”

Section: Introductionmentioning

confidence: 99%

Advancing aircraft engine RUL predictions: an interpretable integrated approach of feature engineering and aggregated feature importance

Alomari,

Andó,

Baptista

2023

Sci Rep

View full text Add to dashboard Cite

In this study, we present a comprehensive approach for predicting the remaining useful life (RUL) of aircraft engines, incorporating advanced feature engineering, dimensionality reduction, feature selection techniques, and machine learning models. The process begins with a rolling time series window, followed by the extraction of a multitude of statistical features, and the application of principal component analysis for dimensionality reduction. We utilize a variety of feature selection methods, such as Genetic Algorithm, Recursive Feature Elimination, Least Absolute Shrinkage and Selection Operator Regression, and Feature Importances from a Random Forest model. As a significant contribution, we introduce the novel aggregated feature importances with cross-validation (AFICv) technique, which ranks features based on their mean importance. We establish a selection criterion that retains features with a cumulative mean sum equal to 70%, thereby reducing the complexity of machine learning models and enhancing their generalizability. Four machine learning regression models—Natural and Extreme Gradient Boosting, Random Forest, and Multi-Layer Perceptron—were employed to evaluate the effectiveness of the selected features. The performance of our proposed method is assessed by the evaluation metrics Root Mean Square Error (RMSE) and R2 Score, and also considered within-interval percentages and relative accuracy metrics. Importantly, a novel PCA interpretability was introduced to provide real-world context and enhance the utility of our findings for domain experts. Our results indicate that the proposed AFICv technique efficiently achieves competitive performance across the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) sub-datasets using a significantly smaller subset of features, thus contributing to a more effective and interpretable RUL prediction methodology for aircraft engines.

show abstract

Section: Introductionmentioning

confidence: 99%

Advancing aircraft engine RUL predictions: an interpretable integrated approach of feature engineering and aggregated feature importance

Alomari,

Andó,

Baptista

2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…This prevent frequent shout downs and save a considerable cost of labour required for cleaning required in the case of non-self-cleaning filters [102,103]. More over due to the complex and harsh conditions prevailing in the desert type climate, often the filters used don't get in actual the useful life prescribed by the manufacturer [104]. Thus, for efficient operation and longer life of the GTPG operating in Middle Eastern region, filtration of the incoming air is very essential…”

Section: Filtration and Filter Requirements For Air Entering The Gas ...mentioning

confidence: 99%

Gas turbine suitable for the ambient conditions prevailing in Arab Gulf countries: A prognostic analysis

Alaabidy,

Antipov,

Al-Rubaiawi

et al. 2023

J Appl Eng Science

View full text Add to dashboard Cite

The present study conducted a prognostic analysis with the aim of understanding the problems associated with the operation of gas turbines in hot climatic regions like the Middle Eastern region. In addition to the hot and dry climatic condition, the region experiences frequent dust storms which can result in operational problems, shorter life span and very high maintenance costs, making air filtration a mandatory operation. Due to this condition and taking into consideration the high humidity of the coastline region, for better effective operation, longer useful life and reduced operating cost the gas turbines have to be located away from the coastline region. To get better power output from the gas turbines, the ambient air has to be cooled. Among the different options available for cooling, evaporative cooling system was found to be more suitable and cost effective for the region. Analyzing the performance of the gas turbine, it was found that adopting the cooling system will result in enhancing the output power up to 7.12%.

show abstract

Experimental study on the performance of micro gas turbines under different intake environments

Cong,

Zhijun,

Yimin

et al. 2024

Case Studies in Thermal Engineering

View full text Add to dashboard Cite

A novel integrated modeling approach for filter diagnosis in gas turbine air intake system

Cited by 7 publications

References 28 publications

Advancing aircraft engine RUL predictions: an interpretable integrated approach of feature engineering and aggregated feature importance

Advancing aircraft engine RUL predictions: an interpretable integrated approach of feature engineering and aggregated feature importance

Gas turbine suitable for the ambient conditions prevailing in Arab Gulf countries: A prognostic analysis

Experimental study on the performance of micro gas turbines under different intake environments

Contact Info

Product

Resources

About