Multi-condition thermal models of avionics pod using stochastic configuration network

doi:10.11949/0438-1157.20191082

Abstract

Abstract:

Avionics pod is a main carrier for multifunctional airborne electronic equipment, which effectively improves the performance of fighter. Increasing power of electronic equipment and low-pressure flight environment can exacerbate thermal environment in pod and can further affects the reliability of electronic equipment, so it is important to predict the thermal response of equipment under different flight conditions. In this paper, a thermal modeling method using thermal network analysis and stochastic configuration network is proposed and is further verified by experimental data of avionics pod with a ram air cooling system. The data of five conditions (high temperature storage, high temperature working, low temperature storage, low temperature accident and low temperature working) is divided into three groups according to heat transfer mechanism and is used to establish the storage thermal models, the working thermal models and the comprehensive thermal models, respectively. Thermal network analysis is used to obtain the input of network. Four-fold cross-validation and gray-scale analysis are used to determine hyper-parameters. The results show that the range sequence can be unified to [1—40] and the maximum number of hidden nodes of three thermal models can be set to 6, 9, and 11, respectively. The modeling results are positive, and the prediction error of electronic equipment temperature in the whole process of multi-conditions is within 3.512℃. Thus, the thermal modeling method that describes the thermal relationship of electronic equipment by data mining can be used to predict the avionics pod temperature in expected flight environment and evaluate the performance of thermal management system.

Key words: avionics pod, thermal response, thermal network, stochastic configuration network, thermodynamics, mathematical modeling, algorithm

摘要：

机载电子吊舱是搭载多功能机载电子设备的主要平台，能够显著提升战机性能。然而，不断增加的电子设备功率和高度低气压力飞行环境会造成吊舱内恶劣的热环境，严重影响电子设备的可靠性。因此，十分有必要建立准确的电子吊舱热模型，用于预测不同飞行工况下的电子设备热响应。综合热网络分析思想和随机网络算法思想，提出一种基于随机配置网络的热模型建立方法，并通过采用冲压空气冷却系统的电子吊舱实验数据加以验证。为了建立准确的舱内温度响应模型，通过传热机制将高温贮存、高温工作、低温贮存、低温故障和低温工作工况下的实验数据分为3组并分别用于建立设备贮存热模型、设备工作热模型和综合热模型，利用热网络分析获取随机配置网络的有效输入，采用四折交叉验证和灰度图分析综合确定了3个热模型的超参数。建模结果表明：3个热模型的范围序列可统一为[1～40]，最大隐含层节点数可分别设为6、9、11，设备温度拟合效果较好，仅在边界条件约束下进行多工况全过程的电子设备温度预测，预测误差在3.512℃内。总体看来，该热建模方法从数据挖掘的角度较为简单、准确、快速地描述了电子设备热关系，可用于开展预期飞行环境下的机载电子吊舱温度预测，用于评估热管理系统的性能。

关键词: 机载电子吊舱, 热响应, 热网络, 随机配置网络, 热力学, 数学模拟, 算法

CLC Number:

V 216.5⁺1

Jie ZHANG, Liping PANG, Hongquan QU, Tianbo WANG. Multi-condition thermal models of avionics pod using stochastic configuration network[J]. CIESC Journal, 2020, 71(S1): 441-447.

张洁, 庞丽萍, 曲洪权, 王天博. 基于随机配置网络的机载电子吊舱多工况热模型[J]. 化工学报, 2020, 71(S1): 441-447.

Figures/Tables 9

Fig.1 Experimental system diagram

Table 1 Condition setting

实验工况	模拟舱设定温度/℃	吊舱设备状态	环控系统状态
高温贮存	70	关	关
高温工作	70	开	开
低温贮存	-55	关	关
低温故障	-55	开	关
低温工作	-55	开	开

Fig.2 Temperature curve

Fig.3 Structure of stochastic configuration network

Fig.4 Modeling process

Fig.5 Hyper-parameters determination of thermal models

Fig.6 Result of comprehensive thermal model

Table 2 Prediction result under whole process of multi-condition

指标	E₁	E₂	E₃	E₄	E₅
最大误差/℃	3.512	1.106	1.676	2.076	0.860
RMSE/℃	1.287	0.507	0.990	1.070	0.506

Fig.7 Prediction temperature curves under whole process of multi-condition

References 30

1	庞利娥, 蒋福根. 一种机载电子吊舱热环境设计与分析[J]. 航天电子对抗, 2013, 29(4): 55-58.
	Pang L E, Jiang F G. Thermal environment design and analysis of the aircraft electronic pod [J]. Aerospace Electronic Warfare, 2013, 29(4): 55-58.
2	王志强. 机载光电吊舱热特性分析[J]. 电光与控制, 2012, 19(8): 70-73.
	Wang Z Q. Analysis on thermal characteristics of airborne electro-optical pod [J]. Electronics Optics & Control, 2012, 19(8): 70-73.
3	Atkey W A, Fiterman C J. High efficiency aircraft cabin air supply cooling system: US7121100B2 [P].2006.
4	Bender D. Integration of exergy analysis into model-based design and evaluation of aircraft environmental control systems [J]. Energy, 2017, 137: 739-751.
5	Chang C W, Dinh N T. Classification of machine learning frameworks for data-driven thermal fluid models [J]. International Journal of Thermal Sciences, 2018, 135: 559-579.
6	Suryanarayana G, Lago J, Geysen D, et al. Thermal load forecasting in district heating networks using deep learning and advanced feature selection methods [J]. Energy, 2018, 157: 141-149.
7	Gunasekar N, Mohanraj M, Velmurugan V. Artificial neural network modeling of a photovoltaic-thermal evaporator of solar assisted heat pumps [J]. Energy, 2015, 93: 908-922.
8	Adewole B Z, Abidakun O A, Asere A A. Artificial neural network prediction of exhaust emissions and flame temperature in LPG (liquefied petroleum gas) fueled low swirl burner [J]. Energy, 2013, 61(6): 606-611.
9	Dhanuskodi R, Kaliappan R, Suresh S, et al. Artificial neural networks model for predicting wall temperature of supercritical boilers [J]. Soft Computing, 2009, 13(3): 291-305.
10	Tian Z, Qian C, Gu B, et al. Electric vehicle air conditioning system performance prediction based on artificial neural network [J]. Applied Thermal Engineering, 2015, 89: 101-114.
11	Korteby Y, Mahdi Y, Azizou A, et al. Implementation of an artificial neural network as a PAT tool for the prediction of temperature distribution within a pharmaceutical fluidized bed granulator [J]. European Journal of Pharmaceutical Sciences, 2016, 88: 219-232.
12	Starkov S O, Lavrenkov Y N. Prediction of the moderator temperature field in a heavy water reactor based on a cellular neural network [J]. Nuclear Energy & Technology, 2017, 3(2): 133-140.
13	刘曙光, 郑崇勋, 刘明远. 前馈神经网络中的反向传播算法及其改进: 进展与展望[J]. 计算机科学, 1996, 23(1): 76-79.
	Liu S G, Zheng C X, Liu M Y. Back propagation algorithm in feedforward neural networks and its improvement: progress and prospects [J]. Computer Science, 1996, 23(1): 76-79.
14	陈格. 人工神经网络技术发展综述[J]. 中国科技信息, 2009, (17): 88-89.
	Chen G. Summary of the research and development of the artificial neural network [J]. Chinese Science and Technology Information, 2009, (17): 88-89.
15	丛爽, 王怡雯. 随机神经网络发展现状综述[J]. 控制理论与应用, 2004, 21(6): 975-980.
	Cong S, Wang Y W. Survey of current progress in random neural network [J]. Control Theory & Applications, 2004, 21(6): 975-980.
16	乔俊飞, 李凡军, 杨翠丽. 随机权神经网络研究现状与展望[J]. 智能系统学报, 2016, 11(6): 758-767.
	Qiao J F, Li F J, Yang C L. Review and prospect on neural networks with random weights [J]. CAAI Transactions on Intelligent Systems, 2016, 11(6): 758-767.
17	Pascanu R, Mikolov T, Bengio Y. On the difficulty of training recurrent neural networks [C]// Proceedings of the 30th International Conference on Machine Learning. USA: ICML， 2013: 1310-1318.
18	康芹, 李世武, 郭建利, 等. 热网络法概论[J]. 工业加热, 2006, 35(5): 19-22.
	Kang Q, Li S W, Guo J L, et al. The thermal network method outline [J]. Industrial Heating, 2006, 35(5): 19-22.
19	Schmidt W F, Kraaijveld M A, Duin R P W. Feed forward neural networks with random weights [C]// Proceedings of 11th IAPR International Conference on Pattern Recognition Methodology and Systems. Netherlands: Hague, 1992: 1-4.
20	Li M, Wang D. Insights into randomized algorithms for neural networks: practical issues and common pitfalls [J]. Information Sciences, 2017, 382/383: 170-178.
21	Wang D, Li M. Stochastic configuration networks: fundamentals and algorithms [J]. IEEE Transactions on Cybernetics, 2017, 47(10): 3466-3479.
22	Wang D, Li M. Robust stochastic configuration networks with kernel density estimation for uncertain data regression [J]. Information Sciences, 2017, 412/413: 210-222.
23	Wang D, Cui C. Stochastic configuration networks ensemble with heterogeneous features for large-scale data analytics [J]. Information Sciences, 2017, 417: 55-71.
24	Rong A, Liu M, Pang L, et al. Kinetics study of gas pollutant adsorption and thermal desorption on silica gel [J]. Applied Sciences, 2017, 7(6): 609.
25	毕小平, 王普凯, 周国印. 基于集总参数法的坦克稳态热分析模型[J]. 装甲兵工程学院学报, 2012, 26(3): 25-29.
	Bi X P, Wang P K, Zhou G Y. A thermal analysis model based on lumped parameter for tank stable working conditions [J]. Journal of Academy of Armored Force Engineering, 2012, 26(3): 25-29.
26	兰志勇, 魏雪环, 李虎如, 等. 基于集总参数热网络法的永磁同步电机温度场分析[J]. 电气工程学报, 2017, 12(1): 17-21, 32.
	Lan Z Y, Wei X H, Li H R, et al. Thermal analysis of PMSM based on lumped parameter thermal network method [J]. Journal of Electrical Engineering, 2017, 12(1): 17-21, 32.
27	Harrington P. Machine Learning in Action [M]. USA: Manning Publications, 2012.
28	周志华. 机器学习[M]. 北京: 清华大学出版社, 2016.
	Zhou Z H. Machine Learning [M]. Beijing: Tsinghua University Press, 2016.
29	Scardapane S, Wang D, Uncini A. Bayesian random vector functional-link networks for robust data modeling[J]. IEEE Transactions on Cybernetics, 2018, 48(7): 2049-2059.
30	Chai T, Draxler R R. Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature [J]. Geoscientific Model Development, 2014, 7(3): 1247-1250.

[1]	Xin YANG, Wen WANG, Kai XU, Fanhua MA. Simulation analysis of temperature characteristics of the high-pressure hydrogen refueling process [J]. CIESC Journal, 2023, 74(S1): 280-286.
[2]	Minghui CHANG, Lin WANG, Jiajia YUAN, Yifei CAO. Study on the cycle performance of salt solution-storage-based heat pump [J]. CIESC Journal, 2023, 74(S1): 329-337.
[3]	Yue CAO, Chong YU, Zhi LI, Minglei YANG. Industrial data driven transition state detection with multi-mode switching of a hydrocracking unit [J]. CIESC Journal, 2023, 74(9): 3841-3854.
[4]	Jianbo HU, Hongchao LIU, Qi HU, Meiying HUANG, Xianyu SONG, Shuangliang ZHAO. Molecular dynamics simulation insight into translocation behavior of organic cage across the cellular membrane [J]. CIESC Journal, 2023, 74(9): 3756-3765.
[5]	Gang YIN, Yihui LI, Fei HE, Wenqi CAO, Min WANG, Feiya YAN, Yu XIANG, Jian LU, Bin LUO, Runting LU. Early warning method of aluminum reduction cell leakage accident based on KPCA and SVM [J]. CIESC Journal, 2023, 74(8): 3419-3428.
[6]	Guoze CHEN, Dong WEI, Qian GUO, Zhiping XIANG. Optimal power point optimization method for aluminum-air batteries under load tracking condition [J]. CIESC Journal, 2023, 74(8): 3533-3542.
[7]	Manzheng ZHANG, Meng XIAO, Peiwei YAN, Zheng MIAO, Jinliang XU, Xianbing JI. Working fluid screening and thermodynamic optimization of hazardous waste incineration coupled organic Rankine cycle system [J]. CIESC Journal, 2023, 74(8): 3502-3512.
[8]	Chengying ZHU, Zhenlei WANG. Operation optimization of ethylene cracking furnace based on improved deep reinforcement learning algorithm [J]. CIESC Journal, 2023, 74(8): 3429-3437.
[9]	Zhaoguang CHEN, Yuxiang JIA, Meng WANG. Modeling neutralization dialysis desalination driven by low concentration waste acid and its validation [J]. CIESC Journal, 2023, 74(6): 2486-2494.
[10]	Xuejin GAO, Yuzhuo YAO, Huayun HAN, Yongsheng QI. Fault monitoring of fermentation process based on attention dynamic convolutional autoencoder [J]. CIESC Journal, 2023, 74(6): 2503-2521.
[11]	Xueyan WEI, Yong QIAN. Experimental study on the low to medium temperature oxidation characteristics and kinetics of micro-size iron powder [J]. CIESC Journal, 2023, 74(6): 2624-2638.
[12]	Shumin ZHENG, Pengcheng GUO, Jianguo YAN, Shuai WANG, Wenbo LI, Qi ZHOU. Experimental and predictive study on pressure drop of subcooled flow boiling in a mini-channel [J]. CIESC Journal, 2023, 74(4): 1549-1560.
[13]	Laiming LUO, Jin ZHANG, Zhibin GUO, Haining WANG, Shanfu LU, Yan XIANG. Simulation and experiment of high temperature polymer electrolyte membrane fuel cells stack in the 1—5 kW range [J]. CIESC Journal, 2023, 74(4): 1724-1734.
[14]	Sheng’an ZHANG, Guilian LIU. Multi-objective optimization of high-efficiency solar water electrolysis hydrogen production system and its performance [J]. CIESC Journal, 2023, 74(3): 1260-1274.
[15]	Xuerong GU, Shuoshi LIU, Siyu YANG. Research on multi-parameter optimization method based on parallel EGO and surrogate-assisted model [J]. CIESC Journal, 2023, 74(3): 1205-1215.