Exhaust Gas Temperature Prediction of Aero-Engine via Enhanced Scale-Aware Efficient Transformer
This research introduces the Enhanced Scale-Aware efficient Transformer (ESAE-Transformer), a novel and advanced model dedicated to predicting Exhaust Gas Temperature (EGT). The ESAE-Transformer merges the Multi-Head ProbSparse Attention mechanism with the established Transformer architecture, signi...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-02-01
|
Series: | Aerospace |
Subjects: | |
Online Access: | https://www.mdpi.com/2226-4310/11/2/138 |
_version_ | 1797299198491623424 |
---|---|
author | Sijie Liu Nan Zhou Chenchen Song Geng Chen Yafeng Wu |
author_facet | Sijie Liu Nan Zhou Chenchen Song Geng Chen Yafeng Wu |
author_sort | Sijie Liu |
collection | DOAJ |
description | This research introduces the Enhanced Scale-Aware efficient Transformer (ESAE-Transformer), a novel and advanced model dedicated to predicting Exhaust Gas Temperature (EGT). The ESAE-Transformer merges the Multi-Head ProbSparse Attention mechanism with the established Transformer architecture, significantly optimizing computational efficiency and effectively discerning key temporal patterns. The incorporation of the Multi-Scale Feature Aggregation Module (MSFAM) further refines 2 s input and output timeframe. A detailed investigation into the feature dimensionality was undertaken, leading to an optimized configuration of the model, thereby improving its overall performance. The efficacy of the ESAE-Transformer was rigorously evaluated through an exhaustive ablation study, focusing on the contribution of each constituent module. The findings showcase a mean absolute prediction error of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mn>3.47</mn><mo>∘</mo></msup><mi>R</mi></mrow></semantics></math></inline-formula>, demonstrating strong alignment with real-world environmental scenarios and confirming the model’s accuracy and relevance. The ESAE-Transformer not only excels in predictive accuracy but also sheds light on the underlying physical processes, thus enhancing its practical application in real-world settings. The model stands out as a robust tool for critical parameter prediction in aero-engine systems, paving the way for future advancements in engine prognostics and diagnostics. |
first_indexed | 2024-03-07T22:46:13Z |
format | Article |
id | doaj.art-09bc761267024994ba30ca3b43bfee43 |
institution | Directory Open Access Journal |
issn | 2226-4310 |
language | English |
last_indexed | 2024-03-07T22:46:13Z |
publishDate | 2024-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Aerospace |
spelling | doaj.art-09bc761267024994ba30ca3b43bfee432024-02-23T15:03:22ZengMDPI AGAerospace2226-43102024-02-0111213810.3390/aerospace11020138Exhaust Gas Temperature Prediction of Aero-Engine via Enhanced Scale-Aware Efficient TransformerSijie Liu0Nan Zhou1Chenchen Song2Geng Chen3Yafeng Wu4School of Power and Energy, Northwestern Polytechnical University, Xi’an 710072, ChinaSchool of Power and Energy, Northwestern Polytechnical University, Xi’an 710072, ChinaSchool of Power and Energy, Northwestern Polytechnical University, Xi’an 710072, ChinaSchool of Power and Energy, Northwestern Polytechnical University, Xi’an 710072, ChinaSchool of Power and Energy, Northwestern Polytechnical University, Xi’an 710072, ChinaThis research introduces the Enhanced Scale-Aware efficient Transformer (ESAE-Transformer), a novel and advanced model dedicated to predicting Exhaust Gas Temperature (EGT). The ESAE-Transformer merges the Multi-Head ProbSparse Attention mechanism with the established Transformer architecture, significantly optimizing computational efficiency and effectively discerning key temporal patterns. The incorporation of the Multi-Scale Feature Aggregation Module (MSFAM) further refines 2 s input and output timeframe. A detailed investigation into the feature dimensionality was undertaken, leading to an optimized configuration of the model, thereby improving its overall performance. The efficacy of the ESAE-Transformer was rigorously evaluated through an exhaustive ablation study, focusing on the contribution of each constituent module. The findings showcase a mean absolute prediction error of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mn>3.47</mn><mo>∘</mo></msup><mi>R</mi></mrow></semantics></math></inline-formula>, demonstrating strong alignment with real-world environmental scenarios and confirming the model’s accuracy and relevance. The ESAE-Transformer not only excels in predictive accuracy but also sheds light on the underlying physical processes, thus enhancing its practical application in real-world settings. The model stands out as a robust tool for critical parameter prediction in aero-engine systems, paving the way for future advancements in engine prognostics and diagnostics.https://www.mdpi.com/2226-4310/11/2/138exhaust gas temperature predictionESAE-TransformerMulti-Scale Feature Aggregation |
spellingShingle | Sijie Liu Nan Zhou Chenchen Song Geng Chen Yafeng Wu Exhaust Gas Temperature Prediction of Aero-Engine via Enhanced Scale-Aware Efficient Transformer Aerospace exhaust gas temperature prediction ESAE-Transformer Multi-Scale Feature Aggregation |
title | Exhaust Gas Temperature Prediction of Aero-Engine via Enhanced Scale-Aware Efficient Transformer |
title_full | Exhaust Gas Temperature Prediction of Aero-Engine via Enhanced Scale-Aware Efficient Transformer |
title_fullStr | Exhaust Gas Temperature Prediction of Aero-Engine via Enhanced Scale-Aware Efficient Transformer |
title_full_unstemmed | Exhaust Gas Temperature Prediction of Aero-Engine via Enhanced Scale-Aware Efficient Transformer |
title_short | Exhaust Gas Temperature Prediction of Aero-Engine via Enhanced Scale-Aware Efficient Transformer |
title_sort | exhaust gas temperature prediction of aero engine via enhanced scale aware efficient transformer |
topic | exhaust gas temperature prediction ESAE-Transformer Multi-Scale Feature Aggregation |
url | https://www.mdpi.com/2226-4310/11/2/138 |
work_keys_str_mv | AT sijieliu exhaustgastemperaturepredictionofaeroengineviaenhancedscaleawareefficienttransformer AT nanzhou exhaustgastemperaturepredictionofaeroengineviaenhancedscaleawareefficienttransformer AT chenchensong exhaustgastemperaturepredictionofaeroengineviaenhancedscaleawareefficienttransformer AT gengchen exhaustgastemperaturepredictionofaeroengineviaenhancedscaleawareefficienttransformer AT yafengwu exhaustgastemperaturepredictionofaeroengineviaenhancedscaleawareefficienttransformer |