Optimization of hot-air anti-icing structures based on neural networks and genetic algorithms

Chu Ziying; Geng Ji; Yang Qian; Yi Xian

doi:10.7638/kqdlxxb-2024.0211

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Optimization of hot-air anti-icing structures based on neural networks and genetic algorithms

更新时间：2026-05-28

- Optimization of hot-air anti-icing structures based on neural networks and genetic algorithms
- Vol. 44, Issue 4, Pages: 18-28(2026)
- 作者机构：
  
  1. 电子科技大学信息与软件工程学院,成都,611731
  2. 空天飞行空气动力科学与技术全国重点实验室,绵阳,621000
  3. 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：
- 基金信息：
- DOI：10.7638/kqdlxxb-2024.0211
  CLC： V221+.92
- Published：2026
- 稿件说明：
移动端阅览
楚紫滢, 耿技, 杨倩, 等. 基于神经网络与遗传算法的热气防冰结构优化[J]. 空气动力学学报, 2026, 44(4): 18−28.

Chu Ziying, Geng Ji, Yang Qian, et al. Optimization of hot-air anti-icing structures based on neural networks and genetic algorithms[J]. 2026, 44(4): 18-28.
楚紫滢, 耿技, 杨倩, 等. 基于神经网络与遗传算法的热气防冰结构优化[J]. 空气动力学学报, 2026, 44(4): 18−28. DOI： 10.7638/kqdlxxb-2024.0211

Chu Ziying, Geng Ji, Yang Qian, et al. Optimization of hot-air anti-icing structures based on neural networks and genetic algorithms[J]. 2026, 44(4): 18-28. DOI： 10.7638/kqdlxxb-2024.0211.

摘要

热气防冰是飞行器结冰防护的重要技术手段，但传统设计方法多通过数值模拟预测防冰表面温度来实现其结构参数优化，存在设计周期长、设计效率低等问题。本文提出了一种基于混合卷积神经网络（convolutional neural network

CNN）和门控循环单元（gate recurrent unit

GRU）的飞行器防冰表面温度分布预测模型，建立了基于该预测模型和遗传算法的多目标优化设计方法，并将其应用于涡扇发动机进气道热气防冰系统。结果表明：所建立的神经网络模型能够快速且准确地预测防冰表面的温度分布，平均绝对误差小于1.5 K，预测准确度高于95%；基于快速非支配排序遗传算法获得了进气道热气防冰系统一系列满足约束条件的防冰结构优化设计方案。与传统设计方法相比，该优化方法所得结构设计在显著降低引气量的同时提高了防冰区域平均温度，有效提升了热气防冰系统设计效率。本文研究为热气防冰系统的快速高效优化设计提供了一种具有工程应用潜力的数据驱动创新方法。

Abstract

Hot-air anti-icing systems are critical for ensuring the safety and reliability of aircraft operations in icing conditions. Traditional design methods for these systems depend heavily on numerical simulations to predict the surface temperature distribution and optimize the structural parameters

which are inefficient. This study proposed an innovative optimization method that integrated neural networks with genetic algorithms to address these challenges. A multi-objective optimization method based on the Non-dominated Sorting Genetic Algorithm II (NSGA-II) was applied to minimize the required bleed air quantity and maximize the average temperature within the anti-icing region. The method efficiently identifies a Pareto-optimal solution set

offering diverse design options that meet the constraints. Experimental results show that the optimized designs significantly reduce the required air bleed while enhancing the anti-icing performance. A data-driven prediction model

named Multi-CNNs with GRU (MCG)

for the surface temperature distribution

was developed using optimized Latin Hypercube Sampling (OLHS) and high-dimensional numerical simulation data. The proposed neural network model demonstrates high accuracy

achieving a mean absolute error of less than 1.5 K and a mean prediction accuracy exceeding 96%. The optimization framework used the MCG model as an individual evaluation algorithm to achieve fast prediction of high-dimensional temperature distributions with a computation time of about 5.5 ms per sample

which is thousands of times more efficient compared to traditional numerical simulations. Comparative analysis with a reduced-order model

POD-AlexNet

highlights the superior accuracy and stability of the MCG model

particularly in predicting complex three-dimensional surface temperature distributions. Additionally

the optimization results demonstrate that the proposed method provides a reliable trade-off between improving anti-icing performance and minimizing energy consumption

thereby enhancing the practical applicability. This study provides an efficient tool for optimizing hot-air anti-icing structures

enabling rapid and accurate decision-making in engineering design. The proposed framework holds significant potential for advancing the development of anti-icing systems in aviation and related fields. This study presents a novel data-driven approach with potential for engineering application

facilitating rapid and efficient optimization design of hot-air-anti-icing systems.

关键词

Keywords

references

Yang Qian, Zheng Haoran, Cheng Xianda, et al. Optimal design method of hot gas anti-icing based on air entrainment control[J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(S2): 729285(in Chinese). doi: 10.7527/S10006893.2023.29285

Chen Yong, Kong Weiliang, Liu Hong. Challenge of aircraft design under operational conditions of supercooled large water droplet icing[J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(1): 626973(in Chinese). doi: 10.7527/S1000-6893.2022.26973

Zuo Chenglin, Ma Jun, Wei Longtao, et al. Investigation and application of ice accretion shape online measurement system for large-scale icing wind tunnel[J]. Acta Aerodynamica Sinica, 2024, 42(11): 110−120(in Chinese). doi: 10.7638/kqdlxxb-2023.0213

Filburn T. Anti-ice and deice systems for wings, nacelles, and instruments[M]//Commercial Aviation in the Jet Era and the Systems that Make it Possible. Cham: Springer International Publishing, 2019: 99−109. doi: 10.1007/978-3-030-20111-1_8

Hannat R, WEISS J, GARNIER F, et al. Application of the dual Kriging method for the design of hot-air-based aircraft wing anti-icing system[J]. Engineering Applications of Computational Fluid Mechanics, 2014, 8(4): 530−548. doi: 10.1080/19942060.2014.11083305

Hoffmann Domingos R, Da Cunha Brandão Reis B, Martins Da Silva D, et al. Numerical simulation of hot-air piccolo tubes for icing protection systems[M]//Handbook of Numerical Simulation of In-Flight Icing. Cham: Springer International Publishing, 2023: 971−1000. doi: 10.1007/978-3-031-33845-8_42

Li L K, Liu Y, Tian L C, et al. An experimental study on a hot-air-based anti-/de-icing system for aero-engine inlet guide vanes[J]. Applied Thermal Engineering, 2020, 167: 114778. doi: 10.1016/j.applthermaleng.2019.114778

Guo Z Q, Zheng M, Yang Q, et al. Effects of flow parameters on thermal performance of an inner-liner anti-icing system with jets impingement heat transfer[J]. Chinese Journal of Aeronautics, 2021, 34(9): 119−132. doi: 10.1016/j.cja.2021.01.015

Liu Senyun, Wang Qiao, Yi Xian, et al. New progress of 3 m × 2 m icing wind tunnel test technology from 2020 to 2022[J]. Acta Aerodynamica Sinica, 2023, 41(1): 57−65(in Chinese). doi: 10.7638/kqdlxxb-2022.0167

Liu Y Y, Yi X. Investigations on hot air anti-icing characteristics with internal jet-induced swirling flow[J]. Aerospace, 2024, 11(4): 270. doi: 10.3390/aerospace11040270

Ni Zhangsong, Liu Senyun, Zhang Jun, et al. Influence of environmental parameters on thermal load of aircraft anti-icing[J]. Journal of Aerospace Power, 2021, 36(1): 8−14(in Chinese). doi: 10.13224/j.cnki.jasp.2021.01.002

Abdelghany E S, Farghaly M B, Almalki M M, et al. Machine learning and IoT trends for intelligent prediction of aircraft wing anti-icing system temperature[J]. Aerospace, 2023, 10(8): 676. doi: 10.3390/aerospace10080676

Ran Lin, Xiong Jianjun, Zhao Zhao, 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).

Jung S, Raj L P, Rahimi A, et al. Performance evaluation of electrothermal anti-icing systems for a rotorcraft engine air intake using a meta model[J]. Aerospace Science and Technology, 2020, 106: 106174. doi: 10.1016/j.ast.2020.106174

Zhang W C, Liang Z C, Wu W X, et al. Design and optimization of a hybrid battery thermal management system for electric vehicle based on surrogate model[J]. International Journal of Heat and Mass Transfer, 2021, 174: 121318. doi: 10.1016/j.ijheatmasstransfer.2021.121318

Ge Y, He Q, Lin Y S, et al. Multi-objective optimization of a mini-channel heat sink with non-uniform fins using genetic algorithm in coupling with CFD models[J]. Applied Thermal Engineering, 2022, 207: 118127. doi: 10.1016/j.applthermaleng.2022.118127

Liu J, Ke P. Aero-engine inlet vane structure optimization for anti-icing with hot air film using neural network and genetic algorithm[C]// International Conference on Icing of Aircraft, Engines, and Structures, 2019. doi: 10.4271/2019-01-2021

Niu J J, Sang W M, Qiu A X, et al. An optimization of anti-icing chamber based on POD and Kriging[C]// 32nd Congress of the International Council of the Aeronautical Sciences, Shanghai, 2021.

Li R J, Zhu G Y, Zhang D L. Investigation on the mechanism of heat load reduction for the thermal anti-icing system[J]. Energies, 2020, 13(22): 5911. doi: 10.3390/en13225911

Yang Q, Guo X F, Zheng H R, et al. Single- and multi-objective optimization of an aircraft hot-air anti-icing system based on reduced order method[J]. Applied Thermal Engineering, 2023, 219: 119543. doi: 10.1016/j.applthermaleng.2022.119543

Mckay M D, Beckman R J, Conover W J. A comparison of three methods for selecting values of input variables in the analysis of output from a computer code[J]. Technometrics, 2000, 42(1): 55−61. doi: 10.1080/00401706.2000.10485979

Damblin G, Couplet M, Iooss B. Numerical studies of space-filling designs: optimization of Latin hypercube samples and subprojection properties[J]. Journal of Simulation, 2013, 7(4): 276−289. doi: 10.1057/jos.2013.16

Morris M D, Mitchell T J. Exploratory designs for computational experiments[J]. Journal of Statistical Planning and Inference, 1995, 43(3): 381−402. doi: 10.1016/0378-3758(94)00035-T

Yang Q, Zheng H R, Guo X F, et al. Experimental validation and tightly coupled numerical simulation of hot air anti-icing system based on an extended mass and heat transfer model[J]. International Journal of Heat and Mass Transfer, 2023, 217: 124645. doi: 10.1016/j.ijheatmasstransfer.2023.124645

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Engine cooling fan layout study of a medium size pickup truck

Optimal design and performance analysis of aircraft trim configuration with redundant control surfaces

Aerodynamic design optimization of wide-Mach-number-range airfoils for hypersonic vehicles

Rotor airfoil aerodynamic design and evaluation software HRADesign

Aerodynamic prediction for waveriders using deep residual learning

Related Author

ZHANG Zebin

LI Bin

SHAN Wangzhen

LIU Sisi

QIN Dongchen

ZHANG Houjun

LI Xiang

FAN Yiming

Related Institution

School of Mechanical and Power Engineering, Zhengzhou University, Zhengzhou

Vehicle Technology section, Model Development Department, Technology Center, Zhengzhou Nissan Automobile CO. , LTD, Zhengzhou

北京理工大学宇航学院

北京机电工程研究所

Institute of Aerodynamic and Multidisciplinary Design Optimization, Northwestern Polytechnical University, Xi'an

AI问答

⁰