基于 PSO-BP 神经网络的机坪泛光照明优化预测模型

中国民航大学学报 ›› 2025, Vol. 43 ›› Issue (6): 54-60.

基于 PSO-BP 神经网络的机坪泛光照明优化预测模型

1. 温州商学院信息工程学院，浙江温州

325035； 2. 中国民航大学交通科学与工程学院，天津 300300

收稿日期:2025-01-22 修回日期:2025-04-07 出版日期:2025-12-20 发布日期:2026-01-10
作者简介:郑美春（1998— ），男，湖北黄冈人，助教，硕士，研究方向为机场智慧化.
基金资助:
太原武宿国际机场科技研发项目（H01420210340）

Optimization and prediction model of apron floodlighting based on PSO-BP neural

network

1. College of Information Engineering, Wenzhou Business College, Wenzhou 325035, Zhejiang, China;

2. College of Transportation Science and Engineering, CAUC, Tianjin 300300, China

Received:2025-01-22 Revised:2025-04-07 Online:2025-12-20 Published:2026-01-10

1. 基于 PSO-BP 神经网络的机坪泛光照明优化预测模型.pdf(7187KB)

摘要/Abstract

摘要：

机坪泛光照明设计的影响因素众多，影响着泛光照明效率与安全。本研究在 DIALux evo 软件中模拟了 315

组仿真照明方案，用来开发照度预测模型。以水平照度、垂直照度、均匀度、眩光值以及分区照度指标作为

模型输入，以高杆灯安装高度、LED 灯数、垂直俯仰角作为模型输出，基于粒子群优化（PSO，particle swarm

optimization）和反向传播（BP，back propagation）神经网络构建预测模型，并与 BP 神经网络构建的预测模

型对比分析。结果表明：与 BP 神经网络算法相比，本研究所提出的 PSO-BP 神经网络的效率更高，模型拟

合精度更高，且避免了 BP 神经网络算法易陷入局部最优解的问题。本文建立的优化模型对预设场景的

照度预测结果与仿真试验结果高度一致，表明该模型在工程应用中具有较好的预测精度。

关键词:

PSO-BP 神经网络, 机坪泛光照明, 高杆灯, LED 灯, 优化模型

Abstract:

The design of apron floodlighting is influenced by numerous factors, which affect the efficiency and safety of

floodlighting. In this study, 315 sets of lighting schemes were simulated in DIALux evo software to develop an illuminance prediction model. Horizontal illuminance, vertical illuminance, uniformity, glare rating, and zonal illuminance were used as model inputs, while the installation height of high-mast lights, number of LEDs, and

vertical tilt angle were used as model outputs. A prediction model based on particle swarm optimization (PSO)

and back propagation (BP) neural network was constructed and compared with a model built using BP neural

network. The results show that the proposed PSO-BP neural network is more efficient and has higher model fitting accuracy than the BP neural network algorithm, and it avoids the problem of local optima inherent in the BP

neural network algorithm. The predicted illuminance results for the preset scenes using the established optimized

model were highly consistent with the simulation test results, indicating that the model has good predictive accuracy in engineering applications.

Key words:

PSO-BP neural network, apron floodlighting, high-mast light, LED light, optimization model

中图分类号:

V351.32

郑美春, 沈良忠, 李岳, 蔡靖 .

基于 PSO-BP 神经网络的机坪泛光照明优化预测模型

[J]. 中国民航大学学报, 2025, 43(6): 54-60.

ZHENG Meichun , SHEN Liangzhong , LI Yue , CAI Jing.

Optimization and prediction model of apron floodlighting based on PSO-BP neural

network

[J]. Journal of Civil Aviation University of China, 2025, 43(6): 54-60.

参考文献 16

[1]	DAVIS R G, WILKERSON A M. Philadelphia international airport
	apron lighting: led system performance in a trial installation[R]. Richland: Pacific Northwest National Lab, 2015.
[2]	陈强. 机坪泛光照明高杆灯 LED 改造及智慧化控制建设探讨[J].
	光源与照明，2020(11): 22-24.
[3]	MUBARAK R R, LAMTIAR S, CALLISTA A B. Prototipe kontrol dan
	monitoring remote apron floodlight berbasis mikrokontroler dengan
	modul dimmer[J]. Journal of Airport Engineering Technology (JAET),2022, 3(1): 37-47.
[4]	WAYAN S Y I. Analisis konsumsi energi untuk efisiensi kelistrikan pada penggunaan sistem tata cahaya apron flood light Bandar udara [J].Jurnal Kajian Teknik Elektro, 2022, 6(2): 54-61.
[5]	沈俊超. 基于粒子群算法的配电系统照明设备节能控制方法研究[J]. 光源与照明, 2023(10): 151-153.
[6]	朱菊香, 谷卫, 罗丹悦, 等. 基于 PSO 优化 BP 神经网络的多传感器数据融合[J]. 中国测试, 2022, 48(8): 94-100.
[7]	BARTSEV A A. Apr on lighting design including aircraft shadows[J].
	Light & Engineering, 2002, 10(2): 47-52.
[8]	ICAO. Annex 14 to the convention on international civil aviation aerodromes: volume i—aerodrome design and operations: 8th ed [S].Montreal: ICAO, 2018.
[9]	中国民用航空局. 民用机场机坪泛光照明技术要求：MH/T 6108—2014[S]. 北京: 中国民航出版社, 2014.
[10]	范勇, 裴勇, 杨广栋, 等. 基于改进 PSO-BP 神经网络的爆破振动速度峰值预测[J]. 振动与冲击, 2022, 41(16): 194-203.
[11]	石宸睿, 田露, 徐湛, 等. 基于 PSO-BP 的应急通信感知装备效
	能评价方法[J]. 系统工程与电子技术, 2022, 44(11): 3455-3462.
[12]	周中, 张俊杰, 丁昊晖, 等. 基于 PSO-BP 神经网络的隧道绿色建
	造污水处理预测模型[J]. 铁道科学与工程学报, 2022, 19(5): 1450-1458.
[13]	YANG J Y, YANG H, YANG X, et al. Optimal design of digital FIR filters based on back propagation neural network[J]. IEICE Electronics Express, 2023, 20(1): 20220491.
[14]	刘伟吉, 冯嘉豪, 祝效华, 等. 基于动量自适应学习率 PSO-BP 神经网络的钻速预测模型研究[J]. 科学技术与工程, 2023, 23(24):10264-10272.
[15]	杨春宇. 建筑物照明亮度设计引入神经网络算法研究[J]. 建筑科学,2008, 24(12): 81-84.
[16]	PIOTROWSKI A P, NAPIORKOWSKI J J. A comparison of methods to
	avoid overfitting in neural networks training in the case of catchment
	runoff modelling[J]. Journal of Hydrology, 2013, 476: 97-111.