基于麻雀搜索算法优化BP神经网络的飞机停放局部温度预测

doi:10.12305/j.issn.1001-506X.2025.11.14

摘要/Abstract

摘要：

为准确预计飞机内部环境温度，从而提供更精确的输入完善机载设备环境适应性设计和试验验证流程，提出基于麻雀搜索算法的反向传播（sparrow search algorithm-back propagation，SSA-BP）神经网络模型的飞机内部温度预测方法。用卡尔曼滤波对输入的环境变量数据进行处理以减少噪声的影响，在相关性分析和考虑热惯性的影响的基础上构建用于温度预测的BP神经网络，同时使用SSA来对其进行优化。通过平均绝对误差可知SSA-BP模型的预测精度高于随机森林模型和高斯过程回归模型，实际预测结果的最大误差不大于3 ℃，均方根误差平均值为0.297 8 ℃。结果说明SSA-BP模型具备准确预测飞机内部环境温度的能力，可用于飞机停放局部温度预测工作，为确定机载设备环境适应性要求提供参考。

关键词: 飞机停放, 麻雀搜索算法, 热惯性, 温度预测

Abstract:

To accurately predict the internal temperature of the aircraft and provide more precise inputs to improve the environmental adaptability design and experimental verification process of airborne equipment, a method for predicting the internal temperature of the aircraft the sparrow search algorithm-back propagation （SSA-BP） neural network model is proposed. Process the input environmental variable data using Kalman filtering to reduce the influence of noise, construct a BP neural network for temperature prediction based on correlation analysis and consideration of thermal inertia, and optimize it using SSA. According to the average absolute error, the prediction accuracy of SSA-BP model is higher than that of random forest （RF） model and Gaussian process regression （GPR） model. The maximum error of the actual prediction results is no more than 3 ℃, and the average root mean square error is 0.297 8 ℃. The results show that ssa-bp model has the ability to accurately predict the internal ambient temperature of aircraft, and can be used to predict the local temperature of aircraft parking, which provides a reference for determining the environmental adaptability requirements of airborne equipment.

Key words: aircraft parking, sparrow search algorithm （SSA）, thermal inertia, temperature prediction

中图分类号:

V 246.5

何宇珩, 袁宏杰, 李贺, 李直声. 基于麻雀搜索算法优化BP神经网络的飞机停放局部温度预测[J]. 系统工程与电子技术, 2025, 47(11): 3655-3662.

Yuheng HE, Hongjie YUAN, He LI, Zhisheng LI. Local temperature prediction for aircraft parking based on BP neural network optimized by sparrow search algorithm[J]. Systems Engineering and Electronics, 2025, 47(11): 3655-3662.

图/表 13

表1

图1

表2

图2

表3

表4

图3

表5

图4

图5

表6

图6

表7

参考文献 20

1	刘文珽, 李玉海. 飞机结构日历寿命体系评定技术[M]. 北京: 航空工业出版社, 2004.
	LIU W T, LI Y H. Aircraft structure calendar life evolution technology[M]. Beijing: Aeronautic Industry Press, 2004.
2	赵海军, 金平, 陈跃良. 飞机地面局部气候环境研究[J]. 航空学报, 2006, 27 (5): 873- 876.
	ZHAO H J, JIN P, CHEN Y L. Investigation of local climate environment of aircraft in ground service[J]. Acta Aeronautica et Astronautica Sinica, 2006, 27 (5): 873- 876.
3	傅耘, 常海娟, 武月琴, 等. 基于实测数据的飞机平台动态温度预计模型[J]. 航空学报, 2014, 35 (9): 2472- 2480.
	FU Y, CHANG H J, WU Y Q, et al. Dynamic temperature predicted model for airplane platform based on measured data[J]. Acta Aeronautica et Astronautica Sinica, 2014, 35 (9): 2472- 2480.
4	张腾, 何宇廷, 李昌范, 等. 地面停放飞机局部温度环境研究[J]. 航空学报, 2015, 36 (2): 538- 547.
	ZHANG T, HE Y T, LI C F, et al. Research on local temperature environment of ground parking aircraft[J]. Acta Aeronautica et Astronautica Sinica, 2015, 36 (2): 538- 547.
5	李贺, 张建军, 傅耘, 等. 严寒地区飞机温度环境分析与预测方法研究[J]. 环境技术, 2022, 40 (2): 174- 182.
	LI H, ZHANG J J, FU Y, et al. Research on the analysis and prediction method of aircraft temperature environment in severe cold areas[J]. Environmental Technology, 2022, 40 (2): 174- 182.
6	盛智勇, 付硕, 王彦平, 等. RVFL神经网络模型在设备舱温度预测中的应用[J]. 中国科技论文, 2018, 13 (8): 887- 892.
	SHENG Z Y, FU S, WANG Y P, et al. Application of RVFL neural network in temperature prediction of equipment cabin[J]. China Sciencepaper, 2018, 13 (8): 887- 892.
7	LIU R X, SONG J Z, LUO P J, et al. Analysis and prediction of temperature of an assembly frame for aircraft based on BP neural network[J]. International Journal of Computational Materials Science and Engineering, 2023, 12 (3): 2350006.
8	李贺, 蔡良续, 钟勇, 等. 飞机停放平台综合环境预计与加速试验谱编制[EB/OL]. [2024-02-11]. https://doi.org/10.13700/j.bh.1001-5965.2024.0633.
	LI H, CAI L X, ZHONG Y, et al. Aircraft platform comprehensive environmental prediction and accelerated test spectrum compilation in parking[EB/OL]. [2024-02-11]. https://doi.org/10.13700/j.bh.1001-5965.2024.0633.
9	洪烨, 杨溢炜, 刘虔, 等. POD算法在飞机RAT舱温度预测中的应用研究[J]. 航空工程进展, 2024, 15 (1): 127- 134.
	HONG Y, YANG Y W, LIU Q, et al. Application of POD algorithm for temperature prediction in aircraft RAT bay[J]. Advances in Aeronautical Science and Engineering, 2024, 15 (1): 127- 134.
10	鹿瑶, 张建军, 傅耘, 等. 基于Elman网络的导引头舱停放温度环境条件预计[J]. 装备环境工程, 2020, 17 (7): 21- 26.
	LU Y, ZHANG J J, FU Y, et al. Seeker cabin temperature prediction based on elman neural network in airport parking conditions[J]. Equipment Environmental Engineering, 2020, 17 (7): 21- 26.
11	李会兵. 基于BP神经网络的温度预测方法[J]. 电子测试, 2013, (19): 62- 64.
	LI H B. BP neural network prediction method based on temperature[J]. Electronic Test, 2013, (19): 62- 64.
12	刘治国, 李旭东, 孙强. 航空装备典型舱室结构环境数据预测方法研究[J]. 环境技术, 2019, 37 (4): 141- 144.
	LIU Z G, LI X D, SUN Q. Research on environment data prediction method of aeronautical equipment typical cabin[J]. Environmental Technology, 2019, 37 (4): 141- 144.
13	LI H, ZHANG J J, FU Y, et al. Research on data-driven integrated environment prediction method for the typical cabin of helicopter[C]// Proc. of the Global Reliability and Prognostics and Health Management Conference, 2023.
14	LI H, ZHANG J J, FU Y, et al. Research on dynamic prediction method of temperature environment of unmanned aerial vehicle platform based on physical information and neural network[C]//Proc. of the 14th International Conference on Reliability, Maintainability and Safety, 2023.
15	金志凤, 符国槐, 黄海静, 等. 基于BP神经网络的杨梅大棚内气温预测模型研究[J]. 中国农业气象, 2011, 32 (3): 362- 367.
	JIN Z F, FU G H, HUANG H J, et al. Simulation and forecast of air temperature inside the greenhouse planted myica rubra based on bp neural network[J]. Chinese Journal of Agrometeorology, 2011, 32 (3): 362- 367.
16	张永芳, 王芳. 基于SSA-RBF网络的日光温室温湿度预测模型研究[J]. 河北农业大学学报, 2021, 44 (3): 115- 121.
	ZHANG Y F, WANG F. Study on temperature and humidity prediction model of solar greenhouse based on SSA-RBF network[J]. Journal of Hebei Agricultural University, 2021, 44 (3): 115- 121.
17	ZHAO H, SHI L R, WANG H J. Sunlight greenhouse temperature prediction model based on Bayesian regularization BP neural network[J]. Applied Mechanics and Materials, 2015, 740, 871- 874. doi: 10.4028/www.scientific.net/AMM.740.871
18	王嵘冰, 徐红艳, 李波, 等. BP神经网络隐含层节点数确定方法研究[J]. 计算机技术与发展, 2018, 28 (4): 31- 35.
	WANG R B, XU H Y, LI B, et al. Research on method of determining hidden layer nodes in BP neural network[J]. Computer Technology and Development, 2018, 28 (4): 31- 35.
19	XUE J K, SHEN B. A novel swarm intelligence optimization approach: sparrow search algorithm[J]. Systems Science Control Engineering, 2020, 8 (1): 22- 34. doi: 10.1080/21642583.2019.1708830
20	刘湲, 王芳. 麻雀搜索算法优化BP神经网络的短期风功率预测[J]. 上海电机学院学报, 2022, 25 (3): 132- 136. doi: 10.3969/j.issn.2095-0020.2022.03.002
	LIU Y, WANG F. BP neural networks optimized by sparrow search algorithm for short term wind power prediction[J]. Journal of Shanghai Dianji University, 2022, 25 (3): 132- 136. doi: 10.3969/j.issn.2095-0020.2022.03.002

测量区域	测点对应编号	温度测量点位置
驾驶舱	T1	驾驶舱内部（舱内温度测点）
雷达舱	T2	雷达舱内部（舱内温度测点）
设备舱	T3	设备舱内部（舱内温度测点）
外部环境大气	T	飞机外部距地面1 m以上，温度测点
	H	飞机外部距地面1 m以上，湿度测点
	WS	飞机外部距地面1 m以上，风速测点
	PRESSURE	飞机外部距地面1 m以上，气压测点
	SR1	飞机上部，太阳辐射测点
	GR1	飞机底部，地表辐射测点

测点	外部温度	外部湿度	外部风速	外部气压	外部太阳辐射	外部地表辐射
T1	0.9715	−0.9512	−0.1501	−0.8203	−0.2371	−0.4218
T2	0.9864	−0.9815	−0.2962	−0.8834	−0.3266	−0.5114
T3	0.9321	−0.8937	−0.1213	−0.7301	−0.1611	−0.2663

测点	延迟时间/min
T1	8
T2	2
T3	5

条件	平均绝对误差/℃
考虑热惯性	0.8671
不考虑热惯性	2.0384

测点	RMSE	MAE
T1	0.2573	1.2653
T2	0.5074	1.8467
T3	0.1288	0.5936