基于卷积时序网络的防冰翼面瞬态温度场预测

陈志勇; 杨先凤; 陈宁立; 易贤; 彭博

doi:10.7638/kqdlxxb-2024.0099

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于卷积时序网络的防冰翼面瞬态温度场预测

研究论文 | 更新时间：2026-05-28

- 基于卷积时序网络的防冰翼面瞬态温度场预测
- Transient temperature field prediction on anti-icing wing surface based on convolutional temporal networks
- 空气动力学学报 2025年43卷第12期页码：99-108
- 作者机构：
  
  1. 西南石油大学计算机与软件学院,成都,610500
  2. 中国空气动力研究与发展中心结冰与防除冰重点实验室,绵阳,621000
- 作者简介：
  
  陈志勇（1999—），男，四川乐山人，硕士研究生，研究方向：深度学习与飞机结冰. E-mail：chenzy_xc0406@163.com
  陈宁立*（1989—），男，江苏盐城人，高级工程师，研究方向：飞机结冰与防除冰技术研究. E-mail：chen04@foxmail.com
- 基金信息：
  
  四川省自然基金青年基金（2023NSFSC1332）;国家重大科技专项（J2019-III-0010-0054）
- DOI：10.7638/kqdlxxb-2024.0099
  中图分类号： V211.3;TP399
- 纸质出版：2025
- 稿件说明：
移动端阅览
陈志勇, 杨先凤, 陈宁立, 等. 基于卷积时序网络的防冰翼面瞬态温度场预测[J]. 空气动力学学报, 2025, 43(12): 99−108.

CHEN Zhiyong, YANG Xianfeng, CHEN Ningli, et al. Transient temperature field prediction on anti-icing wing surface based on convolutional temporal networks[J]. 2025, 43(12): 99-108.
陈志勇, 杨先凤, 陈宁立, 等. 基于卷积时序网络的防冰翼面瞬态温度场预测[J]. 空气动力学学报, 2025, 43(12): 99−108. DOI： 10.7638/kqdlxxb-2024.0099

CHEN Zhiyong, YANG Xianfeng, CHEN Ningli, et al. Transient temperature field prediction on anti-icing wing surface based on convolutional temporal networks[J]. 2025, 43(12): 99-108. DOI： 10.7638/kqdlxxb-2024.0099.

摘要

电加热防冰是防止飞机机翼结冰的关键技术之一，快速准确预测防冰翼面瞬态温度场对电加热系统的优化设计具有重要意义。为实现对防冰翼面瞬态温度场的快速预测，缩短电加热防冰系统优化设计周期，提出了一种结合本征正交分解（proper orthogonal decomposition

POD）和卷积时序网络的预测方法。该方法首先利用POD对温度数据做降维处理，随后以工作条件参数作为输入，使用降维后的模态时间系数作为输出，构建了基于一维卷积和时间卷积的卷积时序网络，并且引入多头注意力机制突出关键特征，最后使用样本准确率来评估模型对瞬态温度场预测的准确性。此外，为探究模型超参数对预测性能的影响，设置消融试验验证了提出的网络结构的有效性。结果表明，所提出的网络模型对防冰翼面瞬态温度场的预测具有较高的准确性，在测试集上的预测精度达94.4%。

Abstract

Electric heating for anti-icing is a crucial technique to prevent icing on aircraft wings. Accurate prediction of transient temperature fields on the anti-icing surface of a wing is essential for optimizing the design of electric heating systems. To achieve a quick prediction of these transient temperature fields and shorten the optimization cycle of electric anti-icing systems

we propose a predictive method that couples the proper orthogonal decomposition (POD) with the convolutional temporal networks. This method first utilizes POD to perform dimensionality reduction on the temperature data. Subsequently

with the

operation parameters as input and the reduced modal time coefficients as output

we construct a convolutional temporal network based on the 1D convolutional neural networks and the temporal convolutional networks

incorporating a multi-head attention mechanism to highlight key features. We introduce the sample accuracy (

) evaluation metric to evaluate the accuracy of transient temperature field predictions. Additionally

we explore the impact of model hyperparameters on the prediction performance and validate the effectiveness of the network structure through ablation experiments. Experimental results demonstrate that the proposed method achieves an

of 94.4% on the test set

indicating a high accuracy in predicting transient temperature fields on anti-icing wing surfaces.

关键词

Keywords

references

LYNCH F T, KHODADOUST A. Effects of ice accretions on aircraft aerodynamics[J]. Progress in Aerospace Sciences, 2001, 37(8): 669−767. doi: 10.1016/s0376-0421(01)00018-5

GREEN S. A Study of U. S. Inflight icing accidents and incidents, 1978 to 2002[C]//44th AIAA Aerospace Sciences Meeting and Exhibit. Reno, Nevada: American Institute of Aeronautics and Astronautics, 2006. doi: 10.2514/6.2006-82

SILVA G, SILVARES O, ZERBINI E. Airfoil anti-ice system modeling and simulation[C]//41st Aerospace Sciences Meeting and Exhibit. Reno, Nevada: American Institute of Aeronautics and Astronautics, 2003. doi: 10.2514/6.2003-734

LIU Z H, BU X Q, LIN G P, et al. Simulation of unsteady electrothermal deicing process based on PHengLEI[J]. Acta Aerodynamica Sinica, 2023, 41(2): 53−63 (in Chinese). doi: 10.7638/kqdlxxb-2021.0353

YANG S K, YI X, GUO Q L, et al. Numerical research on the effect of synthetic heat jet on the temperature characteristics of airfoil[J]. Acta Aerodynamica Sinica, 2022, 40(2): 59−66 (in Chinese). doi: 10.7638/kqdlxxb-2020.0146

URANAI S, FUKUDOME K, MAMORI H, et al. Numerical simulation of the anti-icing performance of electric heaters for icing on the NACA 0012 airfoil[J]. Aerospace, 2020, 7(9): 123. doi: 10.3390/aerospace7090123

CHEN N L, YI X, WANG Q, et al. Method for simulating heat conduction inside multilayer thin wall[J]. Journal of Thermophysics and Heat Transfer, 2024, 38(3): 446−451. doi: 10.2514/1.T6907

SEKEROGLU B, EVER Y K, DIMILILER K, et al. Comparative evaluation and comprehensive analysis of machine learning models for regression problems[J]. Data Intelligence, 2022, 4(3): 620−652. doi: 10.1162/dint_a_00155

RAN L, XIONG J J, ZHAO Z, et al. Prediction of surface temperature change trend of electric heating anti-icing and de-icing based on machine learning[J]. Equipment Environmental Engineering, 2021, 18(8): 29−35 (in Chinese). doi: 10.7643/issn.1672-9242.2021.08.006

YANG Q, GUO X F, LI Q, et al. Hot air anti-icing performance estimation method based on POD and surrogate model[J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(1): 142−156 (in Chinese). doi: 10.7527/S1000-6893.2022.26992

KUTZ J N. Deep learning in fluid dynamics[J]. Journal of Fluid Mechanics, 2017, 814: 1−4. doi: 10.1017/jfm.2016.803

HU L W, ZHANG J, XIANG Y, et al. Neural networks-based aerodynamic data modeling: A comprehensive review[J]. IEEE Access, 2020, 8: 90805−90823. doi: 10.1109/ACCESS.2020.2993562

HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735−1780. doi: 10.1162/neco.1997.9.8.1735

LEE K, CARLBERG K T. Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders[J]. Journal of Computational Physics, 2020, 404: 108973. doi: 10.1016/j.jcp.2019.108973

MAULIK R, LUSCH B, BALAPRAKASH P. Reduced-order modeling of advection-dominated systems with recurrent neural networks and convolutional autoencoders[J]. Physics of Fluids, 2021, 33(3): 037106. doi: 10.1063/5.0039986

XU L, ZHOU G H, ZHAO F F, et al. A data-driven reduced order modeling for fluid flow analysis based on series forecasting intelligent algorithm[J]. IEEE Access, 2022, 10: 60163−60176. doi: 10.1109/ACCESS.2022.3177223

AHMED S E, SAN O, RASHEED A, et al. A long short-term memory embedding for hybrid uplifted reduced order models[J]. Physica D: Nonlinear Phenomena, 2020, 409: 132471. doi: 10.1016/j.physd.2020.132471

NAKAMURA T, FUKAMI K, HASEGAWA K, et al. Convolutional neural network and long short-term memory based reduced order surrogate for minimal turbulent channel flow[J]. Physics of Fluids, 2021, 33(2): 025116. doi: 10.1063/5.0039845

KONG C Y, LI X R, DU J. Prediction of aeroengine exhaust gas temperature based on Autoencoder-TCN model[J]. Journal of Air Force Engineering University, 2020, 21(5): 55−61 (in Chinese).

曹熠云, 茅大钧, 陈思勤. 基于TCN-Attention-BiGRU的锅炉受热面壁温预测[J]. 计算机仿真, 2025, 42(07): 91−98.

LIN Y, XU X A. Prediction of temperature distribution on piston crown surface of dual-fuel engines via a hybrid neural network[J]. Applied Thermal Engineering, 2023, 218: 119269. doi: 10.1016/j.applthermaleng.2022.119269

CHEN N L, YI X, WANG Q, et al. Three-dimensional model for ice accretion in NNW-ICE software and validation of its precision[J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(12): 54−66 (in Chinese).

CHEN N L, YI X, WANG Q, et al. Numerical study on wind-driven thin water film runback on an airfoil[J]. AIAA Journal, 2023, 61(6): 2517−2525. doi: 10.2514/1.J062618

CHEN N L, YI X, WANG Q, et al. An analysis of heat transfer inside the ice layer and solid wall during ice accretion[J]. International Communications in Heat and Mass Transfer, 2022, 137: 106276. doi: 10.1016/j.icheatmasstransfer.2022.106276

ROWLEY C W. Model reduction for fluids, using balanced proper orthogonal decomposition[J]. International Journal of Bifurcation and Chaos, 2005, 15(3): 997−1013. doi: 10.1142/s0218127405012429

LU K, JIN Y, CHEN Y, et al. Review for order reduction based on proper orthogonal decomposition and outlooks of applications in mechanical systems[J]. Mechanical Systems and Signal Processing, 2019, 123: 264−297. doi: 10.1016/j.ymssp.2019.01.018

CHATTERJEE A. An introduction to the proper orthogonal decomposition[J]. Current Science, 2000, 78(7): 808−817.

GUO J W, WANG W, TANG Y Y, et al. A CNN-Bi_LSTM parallel network approach for train travel time prediction[J]. Knowledge-Based Systems, 2022, 256: 109796. doi: 10.1016/j.knosys.2022.109796

ZHU Y L, YANG J, ZHONG S X, et al. Research on temperature forecast correction by dynamic weight integration based on multi-neural networks[J]. Journal of Tropical Meteorology, 2024, 40(1): 156−168 (in Chinese).

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

飞行器模型表面三维温度场重建方法

预冷器微细管束流动换热的模态分解与快速预测

基于神经网络的线性稳定性分析方法

基于深度学习的超分辨率重构方法在CAARC标模绕流流场重构中的应用

基于卷积神经网络的Bolund岛流场重构