神经网络宽度对燃烧室排放预测的影响
收稿日期: 2021-12-14
修回日期: 2021-12-30
录用日期: 2022-01-10
网络出版日期: 2022-01-18
基金资助
国家级项目
Effect of neural network width on combustor emission prediction
Received date: 2021-12-14
Revised date: 2021-12-30
Accepted date: 2022-01-10
Online published: 2022-01-18
Supported by
National Level Project
为研究神经网络宽度对航空发动机燃烧室排放预测的影响，基于录取的全环燃烧室排放试验数据，构建了以燃烧室进口空气温度、进口空气压力、供油流量和油气比为输入，CO和NO x 排放指数为输出的神经网络预测模型，确定了最优网络宽度。结果表明，存在一个最优的网络宽度值，使得神经网络预测模型的拟合优度和预测精度达到最佳，本文最优的网络宽度为24。通过拟合优度、误差分析和敏感性分析验证了构建的神经网络模型的准确性和泛化性。基于最优网络宽度的神经网络预测模型能够很好地挖掘输入参数与排放指数之间的映射关系，可作为给定工况参数下燃烧室排放预测工具。最后，基于敏感性分析，结合燃烧物理机理和试验现象对构建的神经网络可解释性进行了探讨。
王志凯 , 陈盛 , 范玮 . 神经网络宽度对燃烧室排放预测的影响[J]. 航空学报, 2023 , 44(5) : 126816 -126816 . DOI: 10.7527/S1000-6893.2022.26816
To study the effect of neural network width on aero-engine combustor emission prediction， a neural network prediction model is established based on the experimental data of full annular combustor emission. The inlet air temperature， inlet air pressure， fuel flow rate and fuel-air ratio are defined as the input parameters， and CO and NO x emission index as the output parameters of the model. Results indicate that there is an optimal network width value， which makes the best goodness of fit and prediction accuracy of the neural network prediction model， and the optimal network width in this study is 24. The accuracy and generalization of the neural network model are verified by goodness of fit， error analysis and sensitivity analysis. The neural network prediction model based on the optimal network width can well mine the mapping relationship between input parameters and emission index， and can be used as a prediction tool for combustor emission with given operating parameters. Finally， based on sensitivity analysis， the interpretability of the constructed neural network is discussed in combination with the combustion physical mechanism and experimental phenomena.
| 1 | DHANUKA S K， TEMME J E， DRISCOLL J F. Unsteady aspects of lean premixed prevaporized gas turbine combustors： Flame-flame interactions［J］. Journal of Propulsion and Power， 2011， 27（3）： 631-641. |
| 2 | HEATH C M. Characterization of swirl-venturi lean direct injection designs for aviation gas turbine combustion［J］. Journal of Propulsion and Power， 2014， 30（5）： 1334-1356. |
| 3 | CHEN J， LI J Z， YUAN L， et al. Flow and flame characteristics of a RP-3 fuelled high temperature rise combustor based on RQL［J］. Fuel， 2019， 235： 1159-1171. |
| 4 | MONGIA H. TAPS： A fourth generation propulsion combustor technology for low emissions［C］∥ AIAA International Air and Space Symposium and Exposition： The Next 100 Years. Reston： AIAA， 2003. |
| 5 | WANG Z K， ZENG Z X， LI K， et al. Effect of structure parameters of the flow guide vane on cold flow characteristics in trapped vortex combustor［J］. Journal of Hydrodynamics， Ser B， 2015， 27（5）： 730-737. |
| 6 | DENG Y B， WU H W， SU F M. Combustion and exhaust emission characteristics of low swirl injector［J］. Applied Thermal Engineering， 2017， 110： 171-180. |
| 7 | ZHANG C， HUI X， LIN Y Z， et al. Recent development in studies of alternative jet fuel combustion： Progress， challenges， and opportunities［J］. Renewable and Sustainable Energy Reviews， 2016， 54： 120-138. |
| 8 | LI J Z， YUAN L， MONGIA H C. Simulation of combustion characteristics in a hydrogen fuelled lean single-element direct injection combustor［J］. International Journal of Hydrogen Energy， 2017， 42（5）： 3536-3548. |
| 9 | MEZIANE S， BENTEBBICHE A. Numerical study of blended fuel natural gas-hydrogen combustion in rich/quench/lean combustor of a micro gas turbine［J］. International Journal of Hydrogen Energy， 2019， 44（29）： 15610-15621. |
| 10 | 张伟伟， 寇家庆， 刘溢浪. 智能赋能流体力学展望［J］. 航空学报， 2021， 42（4）： 524689. |
| ZHANG W W， KOU J Q， LIU Y L. Prospect of artificial intelligence empowered fluid mechanics［J］. Acta Aeronautica et Astronautica Sinica， 2021， 42（4）： 524689 （in Chinese）. | |
| 11 | 范周伟， 余雄庆， 王朝， 等. 基于深度神经网络的客机总体设计参数敏感性分析［J］. 航空学报， 2021， 42（4）： 524353. |
| FAN Z W， YU X Q， WANG C， et al. Sensitivity analysis of key design parameters of commercial aircraft using deep neural network［J］. Acta Aeronautica et Astronautica Sinica， 2021， 42（4）： 524353 （in Chinese）. | |
| 12 | AGHBASHLO M， PENG W X， TABATABAEI M， et al. Machine learning technology in biodiesel research： A review［J］. Progress in Energy and Combustion Science， 2021， 85： 100904. |
| 13 | KOU J Q， ZHANG W W. Data-driven modeling for unsteady aerodynamics and aeroelasticity［J］. Progress in Aerospace Sciences， 2021， 125： 100725. |
| 14 | ZHOU L， SONG Y T， JI W Q， et al. Machine learning for combustion［J］. Energy and AI， 2022， 7： 100128. |
| 15 | FU J H， YANG R M， LI X， et al. Application of artificial neural network to forecast engine performance and emissions of a spark ignition engine［J］. Applied Thermal Engineering， 2022， 201： 117749. |
| 16 | AZZAM M， AWAD M， ZEAITER J. Application of evolutionary neural networks and support vector machines to model NOx emissions from gas turbines［J］. Journal of Environmental Chemical Engineering， 2018， 6（1）： 1044-1052. |
| 17 | BENDU H， DEEPAK B， MURUGAN S. Application of GRNN for the prediction of performance and exhaust emissions in HCCI engine using ethanol［J］. Energy Conversion and Management， 2016， 122： 165-173. |
| 18 | WANG G Y， AWAD O I， LIU S Y，et al. NOx emissions prediction based on mutual information and back propagation neural network using correlation quantitative analysis［J］. Energy， 2020， 198： 117286. |
| 19 | 赵刚， 朱华昕， 李苏辉， 等. 基于数据和神经网络的燃气轮机NOx排放预测与优化［J］. 动力工程学报， 2021， 41（1）： 22-27. |
| ZHAO G， ZHU H X， LI S H， et al. NOx emission prediction and optimization for gas turbines based on data and neural network［J］. Journal of Chinese Society of Power Engineering， 2021， 41（1）： 22-27 （in Chinese）. | |
| 20 | KUTZ J N. Deep learning in fluid dynamics［J］. Journal of Fluid Mechanics， 2017， 814： 1-4. |
| 21 | LING J L， KURZAWSKI A， TEMPLETON J. Reynolds averaged turbulence modelling using deep neural networks with embedded invariance［J］. Journal of Fluid Mechanics， 2016， 807： 155-166. |
| 22 | LECUN Y， BENGIO Y， HINTON G. Deep learning［J］. Nature， 2015， 521（7553）： 436-444. |
| 23 | DUFERA T T. Deep neural network for system of ordinary differential equations： Vectorized algorithm and simulation［J］. Machine Learning with Applications， 2021， 5： 100058. |
| 24 | BOUWMANS T， JAVED S， SULTANA M， et al. Deep neural network concepts for background subtraction： A systematic review and comparative evaluation［J］. Neural Networks， 2019， 117： 8-66. |
| 25 | CHEN C L P， LIU Z L. Broad learning system： an effective and efficient incremental learning system without the need for deep architecture［J］. IEEE Transactions on Neural Networks and Learning Systems， 2018， 29（1）： 10-24. |
| 26 | LU Z， PU H， WANG F，et al. The expressive power of neural networks：A view from the width［C］∥ Proceedings of the 31st International Conference on Neural Information Processing Systems， 2017：6231-6239. |
| 27 | FUJITA O. Statistical estimation of the number of hidden units for feedforward neural networks［J］. Neural Networks， 1998， 11（5）： 851-859. |
| 28 | SHEELA K G， DEEPA S N. Review on methods to fix number of hidden neurons in neural networks［J］. Mathematical Problems in Engineering， 2013， 2013： 425740. |
| 29 | RUMELHART D E， HINTON G E， WILLIAMS R J. Learning representations by back-propagating errors［J］. Nature， 1986， 323（6088）： 533-536. |
| 30 | BA L M， XIONG X Y， YANG Z B， et al. A novel multi-physics and multi-dimensional model for solid oxide fuel cell stacks based on alternative mapping of BP neural networks［J］. Journal of Power Sources， 2021， 500： 229784. |
| 31 | LIANG W， WANG G W， NING X J， et al. Application of BP neural network to the prediction of coal ash melting characteristic temperature［J］. Fuel， 2020， 260： 116324. |
| 32 | HAN Z Z， MOINUL HOSSAIN M， WANG Y W， et al. Combustion stability monitoring through flame imaging and stacked sparse autoencoder based deep neural network［J］. Applied Energy， 2020， 259： 114159. |
| 33 | HORNIK K， STINCHCOMBE M， WHITE H. Multilayer feedforward networks are universal approximators［J］. Neural Networks， 1989， 2（5）： 359-366. |
| 34 | 成科扬， 王宁， 师文喜， 等. 深度学习可解释性研究进展［J］. 计算机研究与发展， 2020， 57（6）： 1208-1217. |
| CHENG K Y， WANG N， SHI W X， et al. Research advances in the interpretability of deep learning［J］. Journal of Computer Research and Development， 2020， 57（6）： 1208-1217 （in Chinese）. | |
| 35 | 纪守领， 李进锋， 杜天宇， 等. 机器学习模型可解释性方法、应用与安全研究综述［J］. 计算机研究与发展， 2019， 56（10）： 2071-2096. |
| JI S L， LI J F， DU T Y， et al. Survey on techniques， applications and security of machine learning interpretability［J］. Journal of Computer Research and Development， 2019， 56（10）： 2071-2096 （in Chinese）. | |
| 36 | PAHLAVAN R. Energy input-output analysis and application of artificial neural networks for predicting greenhouse basil production［J］. Energy， 2012， 37（1）： 171-176. |
| 37 | LEFEBVRE A H. Gas turbine combustion［M］. New York： Hemisphere Publishing Corporation，1983. |
/
| 〈 |
|
〉 |
CJA