Prediction and sensitivity analysis of pressure pulsation in a LDI combustor based on a fully connected neural network

This paper presents a pressure pulsation prediction model and conducts sensitivity analysis on pressure pulsation. Experiments are performed on a multi-swirl lean direct injection (LDI) combustor under varied operating conditions to establish a comprehensive dataset. The raw data undergo fast Fourie...

Full description

Saved in:
Bibliographic Details
Main Authors: Qian Yao, Shize Tian, Wei Pan, Wu Jin, Jianzhong Li, Li Yuan
Format: Article
Language:English
Published: Elsevier 2025-07-01
Series:Case Studies in Thermal Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2214157X25004113
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849387184504700928
author Qian Yao
Shize Tian
Wei Pan
Wu Jin
Jianzhong Li
Li Yuan
author_facet Qian Yao
Shize Tian
Wei Pan
Wu Jin
Jianzhong Li
Li Yuan
author_sort Qian Yao
collection DOAJ
description This paper presents a pressure pulsation prediction model and conducts sensitivity analysis on pressure pulsation. Experiments are performed on a multi-swirl lean direct injection (LDI) combustor under varied operating conditions to establish a comprehensive dataset. The raw data undergo fast Fourier transform (FFT) and phase space reconstruction to determine combustion mode (stable/unstable), dominant frequency, and amplitude. A fully connected neural network (FCNN) is utilized to predict these pressure parameters, and it demonstrates superior performance compared to support vector regression (SVR) and random forest (RF) models. For test data, the FCNN achieves an average relative error (MRE) of 2.54 % for dominant frequency and a mean absolute error (MAE) of 0.64 % for pressure amplitude, suggesting high accuracy and generalization ability. Furthermore, the FCNN model is assessed for its alignment with physical laws by varying input features. Results indicate that the FCNN model exhibits the best physical consistency among the models. Employing the FCNN model as the surrogate, Sobol’ sensitivity analysis identifies the fuel-air ratio as the most influential parameter, with significant impacts also from inlet flow rate and inlet temperature, while nozzle position exerts a minor influence. Additionally, individual parameter effects on combustion instability are minimal, and instability is primarily driven by parameter interactions.
format Article
id doaj-art-938248fa1acb41bb87ad0e7735fc3f0a
institution Kabale University
issn 2214-157X
language English
publishDate 2025-07-01
publisher Elsevier
record_format Article
series Case Studies in Thermal Engineering
spelling doaj-art-938248fa1acb41bb87ad0e7735fc3f0a2025-08-20T03:55:17ZengElsevierCase Studies in Thermal Engineering2214-157X2025-07-017110615110.1016/j.csite.2025.106151Prediction and sensitivity analysis of pressure pulsation in a LDI combustor based on a fully connected neural networkQian Yao0Shize Tian1Wei Pan2Wu Jin3Jianzhong Li4Li Yuan5College of Energy and Power, Nanjing University of Aeronautics and Astronautics, Nanjing, 210016, ChinaBeijing Electro-mechanical Engineering Institute of CASIC, Beijing, 100048, ChinaCollege of Energy and Power, Nanjing University of Aeronautics and Astronautics, Nanjing, 210016, ChinaCollege of Energy and Power, Nanjing University of Aeronautics and Astronautics, Nanjing, 210016, China; Corresponding author.College of Energy and Power, Nanjing University of Aeronautics and Astronautics, Nanjing, 210016, ChinaSchool of National Defense Engineering, Army Engineering University of PLA, Nanjing, 210007, ChinaThis paper presents a pressure pulsation prediction model and conducts sensitivity analysis on pressure pulsation. Experiments are performed on a multi-swirl lean direct injection (LDI) combustor under varied operating conditions to establish a comprehensive dataset. The raw data undergo fast Fourier transform (FFT) and phase space reconstruction to determine combustion mode (stable/unstable), dominant frequency, and amplitude. A fully connected neural network (FCNN) is utilized to predict these pressure parameters, and it demonstrates superior performance compared to support vector regression (SVR) and random forest (RF) models. For test data, the FCNN achieves an average relative error (MRE) of 2.54 % for dominant frequency and a mean absolute error (MAE) of 0.64 % for pressure amplitude, suggesting high accuracy and generalization ability. Furthermore, the FCNN model is assessed for its alignment with physical laws by varying input features. Results indicate that the FCNN model exhibits the best physical consistency among the models. Employing the FCNN model as the surrogate, Sobol’ sensitivity analysis identifies the fuel-air ratio as the most influential parameter, with significant impacts also from inlet flow rate and inlet temperature, while nozzle position exerts a minor influence. Additionally, individual parameter effects on combustion instability are minimal, and instability is primarily driven by parameter interactions.http://www.sciencedirect.com/science/article/pii/S2214157X25004113Combustion instabilityLean direct injectionDeep learningSensitivity analysis
spellingShingle Qian Yao
Shize Tian
Wei Pan
Wu Jin
Jianzhong Li
Li Yuan
Prediction and sensitivity analysis of pressure pulsation in a LDI combustor based on a fully connected neural network
Case Studies in Thermal Engineering
Combustion instability
Lean direct injection
Deep learning
Sensitivity analysis
title Prediction and sensitivity analysis of pressure pulsation in a LDI combustor based on a fully connected neural network
title_full Prediction and sensitivity analysis of pressure pulsation in a LDI combustor based on a fully connected neural network
title_fullStr Prediction and sensitivity analysis of pressure pulsation in a LDI combustor based on a fully connected neural network
title_full_unstemmed Prediction and sensitivity analysis of pressure pulsation in a LDI combustor based on a fully connected neural network
title_short Prediction and sensitivity analysis of pressure pulsation in a LDI combustor based on a fully connected neural network
title_sort prediction and sensitivity analysis of pressure pulsation in a ldi combustor based on a fully connected neural network
topic Combustion instability
Lean direct injection
Deep learning
Sensitivity analysis
url http://www.sciencedirect.com/science/article/pii/S2214157X25004113
work_keys_str_mv AT qianyao predictionandsensitivityanalysisofpressurepulsationinaldicombustorbasedonafullyconnectedneuralnetwork
AT shizetian predictionandsensitivityanalysisofpressurepulsationinaldicombustorbasedonafullyconnectedneuralnetwork
AT weipan predictionandsensitivityanalysisofpressurepulsationinaldicombustorbasedonafullyconnectedneuralnetwork
AT wujin predictionandsensitivityanalysisofpressurepulsationinaldicombustorbasedonafullyconnectedneuralnetwork
AT jianzhongli predictionandsensitivityanalysisofpressurepulsationinaldicombustorbasedonafullyconnectedneuralnetwork
AT liyuan predictionandsensitivityanalysisofpressurepulsationinaldicombustorbasedonafullyconnectedneuralnetwork