改进粒子BP神经网络在变电站噪声控制中的应用

doi:10.11930/j.issn.1004-9649.2014.9.71.5

摘要/Abstract

摘要： 为了改善变电站噪声控制中已有自适应降噪滤波算法的自适应能力差、收敛速度慢等弊端,提出了一种新的基于粒子群优化（PSO）的误差反向传播神经网络（BPNN）智能滤波算法。该算法针对PSO算法易出现无法兼顾局部、全局搜索和群体多样性丢失等问题,采用以粒子“亲密”度为依据来自适应调整粒子惯性因子和变异率的改进策略;利用该改进粒子群优化（IPSO）算法取代梯度下降算法,实时优化BPNN的权、阈值,使噪声迅速降低,再用梯度下降算法对BPNN的权、阈值作进一步的精细优化,使噪声得到更大程度上的抑制。文中以某变电站变压器噪声信号为仿真声源,分别利用所提算法、PSO-BPNN算法及BPNN算法对该声源信号进行主动抑制,结果表明所提算法性能明显优于另外2种算法的性能,使变压器降噪系统性能得到较大的改善。

关键词: 电力系统, 变电站, 噪声控制, 误差反向传播神经网络, 改进粒子群优化算法, 粒子亲密度, 惯性因子, 自适应变异

Abstract: In order to overcome the shortcomings of existing adaptive noise filtering algorithms for substation noise control, such as poor adaptive ability and slow convergence speed etc., a new intelligent filter algorithm is proposed based on the error back propagation neural network (BPNN) of particle swarm optimization (PSO). In view of the existing problems of PSO, including difficult reconciliation of local and global search, and the population diversity loss, an improved strategy is used, which uses the particle’s“close” degree to adaptively adjust particle inertia factor and mutat ion rate. The improved particle swarm optimization algorithm is used to replace the gradient descent algorithm for real-time optimization of the weights and thresholds of BPNN, and rapid noise reduction. The gradient descent algorithm is then used for further optimization of the weights and thresholds of BPNN, and as a result, the noise is further subdued. By using the noise signal of a substation transformer for simulation of the sound source, the proposed algorithm, PSO-BPNN algorithm and BPNN algorithm are respectively applied to suppress the sound source. The results show that the performance of the proposed algorithm is superior to the performance of the other two algorithms, and the transformer noise reduction system is improved notably.

Key words: power system, substation, noise control, BPNN, IPSO algorithm, particle intimacy, inertial factor, adaptive mutation

中图分类号:

姜鸿羽, 马宏忠, 梁欢, 姜宁, 李凯. 改进粒子BP神经网络在变电站噪声控制中的应用[J]. 中国电力, 2014, 47(9): 71-76.

JIANG Hong-yu, MA Hong-zhong, LIANG Huan, JIANG Ning, LI Kai. The Application of Improved Particle BP Neural Network for Substation Noise Control[J]. Electric Power, 2014, 47(9): 71-76.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.2014.9.71.5

https://www.electricpower.com.cn/CN/Y2014/V47/I9/71

参考文献

[1] 白宏坤,王磊,李宗,等. 河南省电力需求发展趋势预测分析[J]. 中国电力,2014,47（2）：146-151.
BAI Hong-kun, WANG Lei, LI Zong, et al . Analysis and forecast on electricity demand trend of Henan province [J]. Electric Power, 2014, 47(2): 146-151.
[2] 顾宇桂,司政,单葆国,等. 东部地区近期电力需求走势分析[J]. 中国电力,2012,45（10）：27-29.
GU Yu-gui, SI Zheng, SHAN Bao-guo, et al . Trend of recent power demand in eastern china[J]. Electric Power, 2012, 45(10):27-29.
[3] 丁剑,艾明建,吴安平. 西部大开发第二个十年四川省电力需求预测[J]. 中国电力,2012,45（9）：35-39.
DING Jian, AI Ming-jian, WU An-ping. Electric power demand forecast for sichuan province in the second decade of China’s western development program [J]. Electric Power, 2012, 45(9):35-39.
[4] 潘璠,贾文昭,许柏婷,等. 广东电网需求侧响应潜力分析[J].中国电力,2011,44（12）：21-25.
PAN Fan, JIA Wen-zhao, XU Bai-ting, et al . Analysis on demand-side response potential of Guangdong power grid[J].Electric Power, 2011, 44(12): 21-25.
[5] 郑少鹏,邱建锋,邓若尘,等. 深圳市110 kV草埔全地下变电站建设要点[J]. 电力建设,2010,31（9）：46-51.
ZHENG Shao-peng, QIU Jian-feng, DENG Ruo-chen, et al . Construction essentials of the shenzhen 110 kV underground substation[J]. Electric Power Construction, 2010, 31(9): 46-51.
[6] 王葵,尹成竹,沙智明. 济南特高压变电站500 kV主接线方案[J]. 电力建设,2010,31（10）：43-49.
WANG Kui, YIN Cheng-zhu, SHA Zhi-ming. Study on 500 kV electrical main connections of Ji’nan UHV substation [J]. Electric Power Construction, 2010, 31(10): 43-49.
[7] 林毅,林章岁,蒋朋博. 福州特高压变电站500 kV主接线方案优化[J]. 电力建设, 2014, 35（1）: 24-29.
LIN Yi, LIN Zhang-sui, JIANG Peng-bo. Scheme optimization of 500 kV main electrical connection in Fuzhou UHV substation [J]. Electric Power Construction, 2014, 35(1): 24-29.
[8] 郝阳,贺立斋,张建华,等. 变电站同塔双回进出线电磁环境分析[J]. 电力建设,2011,32（10）：23-26.
HAO Yang, HE Li-zhai, ZHANG Jian-hua, et al . Analysis on the electromagnetic environment under double-circuit in substation [J]. Electric Power Construction, 2011, 32(10): 23-26.
[9] 侯婷. 绿色变电站的电气设计[J]. 电力建设,2012,33（5）：45-48.
HOU Ting. Electrical design of green substation[J]. Electric Power Construction, 2012, 33(5): 45-48.
[10] 肖冰,徐迪. 750 kV变电站噪声预测及防治[J]. 电力建设,2012,33（6）：30-33.
XIAO Bing, XU Di. Noise prediction and control in 750 kV substation [J]. Electric Power Construction, 2012, 33(6): 30-33.
[11] 李永明,王玉强,徐禄文,等. 变电站噪声预测和仿真分析[J]. 电力建设,2013,34（7）：63-67.
LI Yong-ming, WANG Yu-qiang, XU Lu-wen, et al . Audible noise prediction and simulation analysis in substation [J]. Electric Power Construction, 2013, 34(7): 63-67.
[12] 孙宇晗,莫娟,曹枚根,等. 基于噪声控制的变电站平面布置优化设计[J]. 电力建设,2013,34（12）：18-23.
SUN Yu-han, MO Juan, CAO Mei-gen, et al . Optimal design of substation layout based on noise control[J]. Electric Power Construction, 2013, 34(12): 18-23.
[13] 袁聪波,黄家彬. 变电站噪声分析及治理[J]. 上海电力,2002（4）：59-61.
YUAN Cong-bo, HUANG Jia-bing. The substation noise analysis and governance [J]. Shanghai Electric Power, 2002(4): 59-61.
[14] 顾晓安,沈密群,朱振江,等. 变压器铁芯振动和噪声特性的试验研究[J]. 变压器,2003,40（4）：1-4.
GU Xiao-an, SHEN Mi-qun, ZHU Zhen-jiang, et al . Test research on vibrations and noise level in transformer core[J]. Transformer, 2003, 40(4): 1-4.
[15] 祝志祥,韩钰,聂京凯,等. 变电站降噪用铝纤维吸声材料[J]. 中国电力,2012,45（7）：57-61.
ZHU Zhi-xiang, HAN Yu, NIE Jing-kai, et al . Research on sound-absorption material of aluminum fiber for substation noise reduction [J]. Electric Power, 2012, 45(7): 57-61.
[16] 周建国,李莉华,杜茵,等. 变电站、换流站和输电线路噪声及其治理技术[J]. 中国电力,2009,42（3）：75-78.
ZHOU Jian-guo, LI Li-hua, DU Yin, et al . Review on methods of noise reducing for equipment in substations, converter stations and transmission lines [J]. Electric Power, 2009, 42(3): 75-78.
[17] ROSS C F. Experiments on the active control of transformer noise [J]. Journal of Sound and Vibration, 1978, 61（4）: 473-480.
[18] QIU Xiao-jun, LI Xun, AI Yan-ting, et al . A waveform synthesis algorithm for active control of transformer noise: implementation [J]. Applied Acoustics, 2002, 63: 467-479.
[19] 马杰. 基于神经网络的自适应噪声主动控制研究[D]. 杭州：浙江理工大学,2011.
[20] 侯宏,杨建华,孙进才. 神经网络BP算法在有源消声中的应用[J]. 西北工业大学学报,1999,17（1）：25-28.
HOU Hong, YANG Jian-hua, SUN Jin-cai. Neural network BP algorithm applied to adaptive active noise control[J]. Journal of Northwestern Polytechnical University, 1999, 17(1): 25-28.
[21] 李传光,姜丽飞,李长青. RBF网络在履带车辆舱室内有源降噪的实验研究[J]. 北京理工大学学报,2004,24（4）：297-299.
LI Chuan-guang, JIANG Li-fei, LI Chang-qing. Active noise control in military vehicle cabin using RBF neural network[J].Transactions of Beijing Institute of Technology, 2004, 24(4): 297-299.
[22] 姜惠兰,陈平,王敬朋,等. 改进粒子群算法在电网无功优化中的应用[J]. 中国电力,2011,44（12）：11-15.
JIANG Hui-lan, CHEN Ping, WANG Jing-peng, et al . Application of improved particle swarm optimization in power system reactive power control [J]. Electric Power, 2011, 44(12): 11-15.