Optimization Design of Indoor Substation Ventilation and Noise Reduction Based on Deep Reinforcement Learning

doi:10.11930/j.issn.1004-9649.202211051

Abstract

Abstract: In view of the equipment safety problems caused by the high operation temperature of the indoor substations and the disturbing noise problems caused by relevant heat dissipation measures, this paper proposes a method for optimizing the design parameters of indoor substation air inlets based on finite element simulation and deep reinforcement learning to obtain the optimal ventilation and heat dissipation effects. Firstly, the temperature field, fluid field and sound field of the indoor substations are modeled and simulated with the finite element analysis method. Then, based on a large number of simulation data, the convolutional neural network is used to establish the prediction model of temperature and noise. Finally, considering the noise constraint, the maximum entropy reinforcement learning framework based SAC algorithm is used to optimize the design parameters of the air inlets with the goal of minimizing the indoor temperature of the substation. The research results show that the optimized air inlet design scheme can effectively reduce the indoor temperature in the substation, and at the same time make the noise meet the requirements of national regulations.

Key words: indoor substation, finite element method, ventilation and noise reduction, reinforcement learning, optimization design

TANG Jinhui, WU Fayuan, ZHI Yanli, MAO Mengting, DAI Xiaomin. Optimization Design of Indoor Substation Ventilation and Noise Reduction Based on Deep Reinforcement Learning[J]. Electric Power, 2023, 56(1): 96-105,118.

Add to citation manager EndNote|Ris|BibTeX

URL: https://www.electricpower.com.cn/EN/10.11930/j.issn.1004-9649.202211051

https://www.electricpower.com.cn/EN/Y2023/V56/I1/96

References

[1] 夏泉, 杨然静. 城市户内变电站设计建设与发展趋势[J]. 电力勘测设计, 2018(增刊2): 24–28
XIA Quan, YANG Ranjing. Construction & prospect of urban indoor substations[J]. Electric Power Survey & Design, 2018(S2): 24–28
[2] 张涛, 李丽, 钟伟华, 等. 500 kV户内变电站设计技术研究[J]. 电力勘测设计, 2018(9): 35–39
ZHANG Tao, LI Li, ZHONG Weihua, et al. Design technique of 500 kV indoor substation[J]. Electric Power Survey & Design, 2018(9): 35–39
[3] 朱超, 王永庆, 傅金柱, 等. 基于Icepak的户内变电站通风换热过程模拟及优化[J]. 电力科学与工程, 2020, 36(4): 65–69
ZHU Chao, WANG Yongqing, FU Jinzhu, et al. Simulation and optimization of ventilation and heat exchange process in indoor substation based on icepak[J]. Electric Power Science and Engineering, 2020, 36(4): 65–69
[4] 郭盛, 黄伟, 薛林, 等. 基于综合环境控制的室内变电站通风方式[J]. 北京交通大学学报, 2013, 37(3): 19–26
GUO Sheng, HUANG Wei, XUE Lin, et al. Ventilation mode of indoor substation based on integrated environmental control technology[J]. Journal of Beijing Jiaotong University, 2013, 37(3): 19–26
[5] 徐禄文, 邹岸新. 户内变电站主变室结构优化仿真系统[J]. 计算机仿真, 2017, 34(12): 81–84,114
XU Luwen, ZOU Anxin. A simulation system for the structural optimization of main transformer rooms in the indoor substations[J]. Computer Simulation, 2017, 34(12): 81–84,114
[6] 郭军科, 郑中原, 甘智勇, 等. 城市110 kV变电站噪声来源及降噪措施[J]. 资源节约与环保, 2016(8): 130–131
GUO Junke, ZHENG Zhongyuan, GAN Zhiyong, et al. Noise sources and noise reduction measures of urban 110 kV substation[J]. Resources Economization & Environmental Protection, 2016(8): 130–131
[7] 刘敏, 崔亚兵, 陈聪, 等. 变电站噪声污染分析及优化控制[J]. 电力科技与环保, 2019, 35(4): 1–4
LIU Min, CUI Yabing, CHEN Cong, et al. Analysis and optimization control of noise pollution for substations[J]. Electric Power Technology and Environmental Protection, 2019, 35(4): 1–4
[8] 张峰, 黄霞, 丁军. 户内变电站通风换热的数值模拟与优化分析[J]. 流体机械, 2016, 44(1): 76–80
ZHANG Feng, HUANG Xia, DING Jun. Numerical simulation and optimization on ventilation and heat exchange in indoor substation[J]. Fluid Machinery, 2016, 44(1): 76–80
[9] 唐超, 高岩, 李德英, 等. 基于正交试验的工业厂房自然通风影响因素数值分析[J]. 建筑科学, 2011, 27(12): 81–86
TANG Chao, GAO Yan, LI Deying, et al. Numerical analysis on natural ventilation influence factors of an industrial workshop based on orthogonal test[J]. Building Science, 2011, 27(12): 81–86
[10] STAVRIDOU A D, PRINOS P E. Natural ventilation of buildings due to buoyancy assisted by wind: investigating cross ventilation with computational and laboratory simulation[J]. Building and Environment, 2013, 66(4): 104–119.
[11] YANG H J, YU T F, XU R, et al. Numerical simulation of ventilation for main transformer room of indoor substations[J]. The Open Automation and Control Systems Journal, 2015, 7(1): 630–639.
[12] 王剑, 张峰, 邢海斌, 等. 基于CFD的户内变电站通风换热数值模拟及优化设计[J]. 机械设计与制造, 2016(3): 45–47, 50
WANG Jian, ZHANG Feng, XING Haibin, et al. The numerical simulation and optimization design on ventilation and heat transfer in indoor substation based on CFD[J]. Machinery Design & Manufacture, 2016(3): 45–47, 50
[13] KANAAN M, CHAHINE K. CFD study of ventilation for indoor multi-zone transformer substation[J]. International Journal of Heat and Technology, 2018, 36(1): 88–94.
[14] 耿明昕, 吴健, 安翠翠, 等. 110 kV户内变电站降噪措施及设计优化研究[J]. 陕西电力, 2013, 41(11): 80–85
GENG Mingxin, WU Jian, AN Cuicui, et al. Research on noise reducing measures and design optimization of 110 kV indoor substation[J]. Shaanxi Electric Power, 2013, 41(11): 80–85
[15] 董倩, 魏勇, 郭留明, 等. 330 kV/110 kV合建户内变电站噪声控制分析[J]. 四川环境, 2022, 41(3): 206–211
DONG Qian, WEI Yong, GUO Liuming, et al. Noise control analysis of 330 kV/110 kV indoor substation[J]. Sichuan Environment, 2022, 41(3): 206–211
[16] 金津, 刘巍, 胡钋, 等. 户内变电站通风和降噪模拟与优化[J]. 武汉大学学报(工学版), 2015, 48(4): 495–501
JIN Jin, LIU Wei, HU Po, et al. Simulation and optimization of ventilation and noise reduction for indoor substations[J]. Engineering Journal of Wuhan University, 2015, 48(4): 495–501
[17] 金淋芳. 城市全户内变电站主变压器室通风降噪研究[J]. 供用电, 2010, 27(2): 39–41, 77
JIN Linfang. Research on ventilation and noise reduction of main transformer chamber in urban indoor substation[J]. Distribution & Utilization, 2010, 27(2): 39–41, 77
[18] 马忠, 郭建胜, 顾涛勇, 等. 基于改进卷积神经网络的航空发动机剩余寿命预测[J]. 空军工程大学学报(自然科学版), 2020, 21(6): 19–25
MA Zhong, GUO Jiansheng, GU Taoyong, et al. A remaining useful life prediction for aero-engine based on improved convolution neural networks[J]. Journal of Air Force Engineering University (Natural Science Edition), 2020, 21(6): 19–25
[19] 景惠甜, 韩丽, 高志宇. 基于卷积神经网络特征提取的风电功率爬坡预测[J]. 电力系统自动化, 2021, 45(4): 98–105
JING Huitian, HAN Li, GAO Zhiyu. Wind power ramp forecast based on feature extraction using convolutional neural network[J]. Automation of Electric Power Systems, 2021, 45(4): 98–105
[20] 王臣, 徐天宇, 谢玉林, 等. 数据驱动下流体结构相互作用的卷积神经网络预测[J]. 水动力学研究与进展(A辑), 2021, 36(3): 331–339
WANG Chen, XU Tianyu, XIE Yulin, et al. Data-driven prediction of fluid-structure interaction based on CNN model[J]. Chinese Journal of Hydrodynamics, 2021, 36(3): 331–339
[21] 曹怀刚, 任群言, 郭圣明, 等. 卷积神经网络单矢量水听器方位估计[J]. 哈尔滨工程大学学报, 2020, 41(10): 1524–1529
CAO Huaigang, REN Qunyan, GUO Shengming, et al. Source azimuth estimation with single vector sensor based on convolutional neural network[J]. Journal of Harbin Engineering University, 2020, 41(10): 1524–1529
[22] 屈力刚, 杨忠文, 杨野光, 等. 采用改进粒子群算法的铣削参数优化研究[J]. 机械设计与制造, 2022(7): 187–191
QU Ligang, YANG Zhongwen, YANG Yeguang, et al. Optimization of milling parameters using improved particle swarm optimization algorithm[J]. Machinery Design & Manufacture, 2022(7): 187–191
[23] 侍野, 唐一华, 刘畅, 等. 基于遗传算法的低温推进剂集成管理模块参数优化[J]. 导弹与航天运载技术, 2022(3): 27–31
SHI Ye, TANG Yihua, LIU Chang, et al. Optimization of integrated cryogenic propellant management module based on genetic algorithm[J]. Missiles and Space Vehicles, 2022(3): 27–31
[24] 徐天光, 王永庆, 张勇, 等. 某变电站变压器室进风口数值模拟及优化研究[J]. 电力科学与工程, 2019, 35(11): 37–43
XU Tianguang, WANG Yongqing, ZHANG Yong, et al. Numerical simulation and optimization of air intake in power transformer room of indoor substation[J]. Electric Power Science and Engineering, 2019, 35(11): 37–43
[25] 鞠永强, 王春江, 张石宸, 等. 高速磁浮列车气动噪声分布规律研究[J]. 力学季刊, 2022, 43(2): 331–339
JU Yongqiang, WANG Chunjiang, ZHANG Shichen, et al. Research on the aerodynamic noise distribution laws for high-speed maglev train[J]. Chinese Quarterly of Mechanics, 2022, 43(2): 331–339
[26] 环境保护部. 声环境质量标准: GB 3096—2008[S]. 北京: 中国环境科学出版社, 2008.
Ministry of Environmental Protection of the People's Republic of China. Environmental quality standards for noise: GB 3096—2008[S]. Beijing: China Environmental Science Press, 2008.
[27] HAARNOJA T, ZHOU A, ABBEEL P, et al. Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor[EB/OL]. 2018: arXiv: 1801.01290.https://arxiv.org/abs/1801.01290.
[28] 张晓华, 蔡巍, 武宇平, 等. 基于红外检测的变电站设备热状态诊断[J]. 智慧电力, 2021, 49(9): 109–116
ZHANG Xiaohua, CAI Wei, WU Yuping, et al. Thermal state diagnosis of substation equipment based on infrared detection[J]. Smart Power, 2021, 49(9): 109–116