基于ISCA-DBN的飞机地面空调能耗预测

刘涵; 林家泉

doi:10.13700/j.bh.1001-5965.2023.0409

基于ISCA-DBN的飞机地面空调能耗预测

doi: 10.13700/j.bh.1001-5965.2023.0409

刘涵,
林家泉^,

中国民航大学电子信息与自动化学院，天津 300300

详细信息

通讯作者:
E-mail：jqlin@cauc.edu.cn

中图分类号: V351.3
计量
- 文章访问数: 229
- HTML全文浏览量: 44
- PDF下载量: 3
- 被引次数: 0
出版历程
- 收稿日期: 2023-06-23
- 录用日期: 2023-08-14
- 网络出版日期: 2023-08-25
- 整期出版日期: 2025-06-30

Energy consumption prediction of aircraft ground air conditioning based on ISCA-DBN

LIU Han,
LIN Jiaquan^,

College of Electronic Information and Automation，Civil Aviation University of China，Tianjin 300300，China

More Information

Corresponding author: E-mail：jqlin@cauc.edu.cn

摘要

摘要:
为提升飞机客舱使用地面空调制冷时地面空调能耗预测精度，提出一种改进正余弦算法(ISCA)优化深度置信网络(DBN)的地面空调能耗预测模型。与标准正余弦优化算法相比，ISCA提出一种改进Logistic混沌映射，提高了种群多样性；引入余弦调节因子，构建了一种新的非线性振荡调整因子，以平衡算法的全局搜索和局部寻优能力；基于变异进化思想提出一种学习策略，避免算法陷入局部最优。将ISCA-DBN模型应用于波音737-800飞机地面空调能耗预测中，与反向传播(BP)、支持向量机(SVM)、DBN等算法进行性能对比，仿真结果表明：基于ISCA-DBN的地面空调能耗预测模型在预测精度和实时性上有一定的提升。
- 飞机客舱 /
- 地面空调 /
- 能耗预测 /
- 正余弦优化 /
- 深度置信网络
Abstract:
An improved sine-cosine optimization (ISCA) deep belief network (DBN) prediction model for ground air conditioning energy consumption is suggested in order to increase the prediction accuracy of ground air conditioning energy consumption when the aircraft cabin is cooled by ground air conditioning. In contrast to the standard sine-cosine optimization algorithm, the improved sine-cosine algorithm introduces a cosine adjustment factor to create a new non-linear oscillation adjustment factor to balance the algorithm's overall performance. It also suggests an improved logistic chaotic map, which increases population diversity. In order to prevent the algorithm from reaching a local optimum, a learning technique based on the concept of mutation evolution is finally suggested.Search and local optimization capabilities; finally, a learning strategy is proposed based on the idea of mutation evolution to avoid the algorithm from falling into local optimum. The ISCA-DBN model is applied to the prediction of ground air-conditioning energy consumption of Boeing 737-800 aircraft, and the performance is compared with back propagation (BP)、support vector machine (SVM)、DBN algorithms. There is a certain improvement in both prediction accuracy and real-time performance.
- aircraft cabin /
- ground air condition /
- energy demands prediction /
- sine cosine algorithm /
- deep belief network

HTML全文

图 1 DBN模型结构

Figure 1. Model structure of DBN

下载: 全尺寸图片幻灯片

图 2 Adam-DBN内部结构

Figure 2. Internal structure of Adam-DBN

下载: 全尺寸图片幻灯片

图 3 不同学习率下模型收敛过程

Figure 3. Comparison of clustering accuracy of algorithms under different model depth conditions

下载: 全尺寸图片幻灯片

图 4 不同映射下的直方图对比

Figure 4. Comparison of Histogram comparison on different maps

下载: 全尺寸图片幻灯片

图 5 振幅调整因子调节过程

Figure 5. Adjustment process of amplitude adjustment factor

下载: 全尺寸图片幻灯片

图 6 ISCA-DBN训练流程

Figure 6. The training flow chart of ISCA-DBN

下载: 全尺寸图片幻灯片

图 7 优化算法迭代过程

Figure 7. Iterative process of optimization algorithms

下载: 全尺寸图片幻灯片

图 8 不同模型下预测值与真实值的对比

Figure 8. Comparison of predicted and real values on different models

下载: 全尺寸图片幻灯片

表 1 部分样本数据

Table 1. Part of sample data

编号	乘客下机的客舱温度/℃	乘客下机的客舱湿度/%	乘客登机的客舱温度/℃	乘客登机的客舱湿度/%	耗电量/ kW
54	33.31	73.88	24.65	37.24	170.43
55	30.11	61.45	27.66	36.48	148.00
56	34.61	58.52	25.72	29.82	172.94
57	30.18	63.06	24.56	32.93	168.12
58	34.27	52.49	24.49	36.29	184.36

下载: 导出CSV

表 2 超参数搜索范围

Table 2. The search range of hyperparameters

超参数	搜索空间
预训练学习率	0.01～0.1
微调学习率	0.01～0.1
预训练次数	1～20
微调次数	1～200
批大小	1～256
隐含层层数	1～3
隐含层节点数	10～100

下载: 导出CSV

表 3 3种算法搜寻结果

Table 3. Three algorithms search results

算法	预训练学习率	微调学习率	预训练次数	微调次数	批大小	隐含层层数	隐含层节点数
GA	0.018 5	0.036 2	19	192	12	3	[35,61,31]
SCA	0.051 2	0.055 6	8	100	5	3	[82,44,28]
ISCA	0.042 4	0.082 6	7	147	15	3	[67,46,34]

下载: 导出CSV

表 4 不同模型评价结果

Table 4. Evaluation results for different models

模型	S_ME	A_MPE/%	R²	泛化误差	时间/s
BP	36.77	2.732	0.733	0.024	2.01
SVM	35.31	2.831	0.743	0.023	1.33
DBN	13.56	1.540	0.901	0.016	2.13
GA-DBN	4.91	0.731	0.964	0.024	7.55
SCA-DBN	4.29	0.719	0.968	0.050	6.97
ISCA-DBN	3.27	0.706	0.976	0.012	2.78

下载: 导出CSV

参考文献(22)

[1]	WANG J Q, DU Y, WANG J. LSTM based long-term energy consumption prediction with periodicity[J]. Energy, 2020, 197: 117197. doi: 10.1016/j.energy.2020.117197
[2]	王修岩, 刘艳敏, 张革文, 等. 基于改进协同PSO的神经网络飞机客舱能耗预测[J]. 系统仿真学报, 2018, 30(4): 1535-1541. WANG X Y, LIU Y M, ZHANG G W, et al. Prediction of aircraft cabin energy consumption based on improved cooperative PSO neural network[J]. Journal of System Simulation, 2018, 30(4): 1535-1541 (in Chinese).
[3]	林家泉, 孙凤山, 李亚冲, 等. 基于IPSO-Elman神经网络的飞机客舱能耗预测[J]. 航空学报, 2020, 41(7): 323614. doi: 10.7527/S1000-6893.2020.23614 LIN J Q, SUN F S, LI Y C, et al. Prediction of aircraft cabin energy consumption based on IPSO-Elman neural network[J]. Acta Aeronautica et Astronautica Sinica, 2020, 41(7): 323614 (in Chinese). doi: 10.7527/S1000-6893.2020.23614
[4]	周璇, 林家泉. 基于改进长短时记忆网络的地面空调能耗预测[J]. 北京航空航天大学学报, 2023, 49(10): 2750-2760. ZHOU X, LIN J Q. Prediction of ground air conditioner energy consumption based on improved long short-term memory neural network[J]. Journal of Beijing University of Aeronautics and Astronautics, 2023, 49(10): 2750-2760 (in Chinese).
[5]	刘艳敏. 基于组合预测方法的波音737飞机客舱能耗预测研究[D]. 天津: 中国民航大学, 2017: 33-38. LIU Y M. Research on energy consumption prediction of Boeing 737 cabin based on combined forecasting method[D]. Tianjin: Civil Aviation University of China, 2017: 33-38 (in Chinese).
[6]	HINTON G E, OSINDERO S, TEH Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554.
[7]	张程, 林谷青, 黄靖, 等. 基于AMBOA-DBN结合相似日的短期光伏功率预测[J]. 太阳能学报, 2023, 44(6): 290-299. ZHANG C, LIN G Q, HUANG J, et al. Short-term pv power prediction based on amboa-dbn combined with similar days[J]. Acta Energiae Solaris Sinica, 2023, 44(6): 290-299 (in Chinese).
[8]	SHAO H D, JIANG H K, ZHANG H Z, et al. Electric locomotive bearing fault diagnosis using a novel convolutional deep belief network[J]. IEEE Transactions on Industrial Electronics, 2017, 65(3): 2727-2736.
[9]	HAN D Y, ZHAO N, SHI P M. A new fault diagnosis method based on deep belief network and support vector machine with Teager–Kaiser energy operator for bearings[J]. Advances in Mechanical Engineering, 2017, 9(12): 168781401774311.
[10]	梁智, 孙国强, 李虎成, 等. 基于VMD与PSO优化深度信念网络的短期负荷预测[J]. 电网技术, 2018, 42(2): 598-606. LIANG Z, SUN G Q, LI H C, et al. Short-term load forecasting based on VMD and PSO optimized deep belief network[J]. Power System Technology, 2018, 42(2): 598-606 (in Chinese).
[11]	徐先峰, 蔡路路, 张丽. 融合MLP和DBN的光伏发电预测算法[J]. 计算机工程与应用, 2021, 57(3): 266-272. XU X F, CAI L L, ZHANG L. Photovoltaic power generation prediction algorithm based on MLP and DBN[J]. Computer Engineering and Applications, 2021, 57(3): 266-272 (in Chinese).
[12]	李益兵, 王磊, 江丽. 基于PSO改进深度置信网络的滚动轴承故障诊断[J]. 振动与冲击, 2020, 39(5): 89-96. LI Y B, WANG L, JIANG L. Rolling bearing fault diagnosis based on DBN algorithm improved with PSO[J]. Journal of Vibration and Shock, 2020, 39(5): 89-96 (in Chinese).
[13]	SHAN H T, SUN Y Y, ZHANG W J, et al. Reliability analysis of power distribution network based on PSO-DBN[J]. IEEE Access, 2020, 8: 224884-224894. doi: 10.1109/ACCESS.2020.3007776
[14]	MIRJALILI S. SCA: a sine cosine algorithm for solving optimization problems[J]. Knowledge-Based Systems, 2016, 96: 120-133. doi: 10.1016/j.knosys.2015.12.022
[15]	徐松金, 龙文. 求解高维优化问题的改进正弦余弦算法[J]. 计算机应用研究, 2018, 35(9): 2574-2577. doi: 10.3969/j.issn.1001-3695.2018.09.003 XU S J, LONG W. Improved sine cosine algorithm for solving high-dimensional optimization problems[J]. Application Research of Computers, 2018, 35(9): 2574-2577 (in Chinese). doi: 10.3969/j.issn.1001-3695.2018.09.003
[16]	何庆, 徐钦帅, 魏康园. 基于改进正弦余弦算法的无线传感器节点部署优化[J]. 计算机应用, 2019, 39(7): 2035-2043. doi: 10.11772/j.issn.1001-9081.2018112282 HE Q, XU Q S, WEI K Y. Enhanced sine cosine algorithm based node deployment optimization of wireless sensor network[J]. Journal of Computer Applications, 2019, 39(7): 2035-2043 (in Chinese). doi: 10.11772/j.issn.1001-9081.2018112282
[17]	NENAVATH H, JATOTH R K. Hybridizing sine cosine algorithm with differential evolution for global optimization and object tracking[J]. Applied Soft Computing, 2018, 62: 1019-1043. doi: 10.1016/j.asoc.2017.09.039
[18]	ATTIA A F, EL SEHIEMY R A, HASANIEN H M. Optimal power flow solution in power systems using a novel sine-cosine algorithm[J]. International Journal of Electrical Power & Energy Systems, 2018, 99: 331-343.
[19]	李正明, 梁彩霞, 王满商. 基于PSO-DBN神经网络的光伏短期发电出力预测[J]. 电力系统保护与控制, 2020, 48(8): 149-154. LI Z M, LIANG C X, WANG M S. Short-term power generation output prediction based on a PSO-DBN neural network[J]. Power System Protection and Control, 2020, 48(8): 149-154 (in Chinese).
[20]	刘帼巾, 刘达明, 缪建华, 等. 基于变分模态分解和改进灰狼算法优化深度置信网络的自动转换开关故障识别[J]. 电工技术学报, 2024, 39(4): 1221-1233. LIU G J, LIU D M, MIAO J H, et al. Fault identification of automatic transfer switching equipment based on VMD-WPE and IGWO optimized DBN[J]. Transactions of China Electrotechnical Society, 2024, 39(4): 1221-1233 (in Chinese).
[21]	孙凤山, 范孟豹, 曹丙花, 等. 基于混沌映射与差分进化自适应教与学优化算法的太赫兹图像增强模型[J]. 仪器仪表学报, 2021, 42(4): 92-101. SUN F S, FAN M B, CAO B H, et al. The terahertz image enhancement model based on adaptive teaching-learning based optimization algorithm with chaotic mapping and differential evolution[J]. Chinese Journal of Scientific Instrument, 2021, 42(4): 92-101 (in Chinese).
[22]	刘公致, 吴琼, 王光义, 等. 改进型Logistic混沌映射及其在图像加密与隐藏中的应用[J]. 电子与信息学报, 2022, 44(10): 3602-3609. LIU G Z, WU Q, WANG G Y, et al. A improved logistic chaotic map and its application to image encryption and hiding[J]. Journal of Electronics & Information Technology, 2022, 44(10): 3602-3609 (in Chinese).