基于PSO-Elman神经网络的燃煤机组受热面清洁状态预测
|
摘要
随着节能减排政策力度的加大,国家十分重视火电厂节能降耗技术的开发研究。针对目前锅炉受热面吹灰方式不合理的情况,以污染率(FF)表征受热面清洁状态对锅炉受热面传热的影响,建立了基于PSO-Elman神经网络的受热面清洁状态预测模型,实现对受热面清洁状态的预测。采用粒子群算法(PSO)和Elman动态神经网络相结合的预测方法,首先根据输入、输出参数个数确定Elman神经网络结构,然后利用PSO优化网络的权值和阈值,将优化后的最优权值、阈值赋给Elman神经网络作为初始值进行网络训练,建立基于PSO-Elman神经网络的受热面清洁状态预测模型。通过具体实例仿真证实了所提方法的有效性,获得了较满意的预测精度,验证了该方法的有效性。
With the efforts intensified in energy conservation and emission reduction policies, great importance has been attached to the development and research of energy-saving and consumption-reducing technologies for thermal power plants from state level.Aiming at current unreasonable way of boiler blowing on the heating surface of the boiler, the pollution rate(FF) is used to characterize and represent the impacts of the cleanliness of the heated surface on the heat transfer of the boiler heating surface. The forecasting model of the heating surface cleanliness based on PSO-Elman neural network is established. Using the particle swarm optimization(PSO) algorithm in combination with Elman dynamic neural network, the Elman neural network structure is first determined according to the number of input and output parameters. Then by taking advantage of PSO algorithm the weights and thresholds of the neural network are optimized. Finally the derived optimal values and thresholds are assigned to the Elman neural network as the initial value for network training such that the heating surface cleanliness forecast model is established based on PSOElman neural network. Through simulations of specific examples, satisfactory forecasting accuracy is obtained and hence the effectiveness of the proposed method is verified.
With the efforts intensified in energy conservation and emission reduction policies, great importance has been attached to the development and research of energy-saving and consumption-reducing technologies for thermal power plants from state level.Aiming at current unreasonable way of boiler blowing on the heating surface of the boiler, the pollution rate(FF) is used to characterize and represent the impacts of the cleanliness of the heated surface on the heat transfer of the boiler heating surface. The forecasting model of the heating surface cleanliness based on PSO-Elman neural network is established. Using the particle swarm optimization(PSO) algorithm in combination with Elman dynamic neural network, the Elman neural network structure is first determined according to the number of input and output parameters. Then by taking advantage of PSO algorithm the weights and thresholds of the neural network are optimized. Finally the derived optimal values and thresholds are assigned to the Elman neural network as the initial value for network training such that the heating surface cleanliness forecast model is established based on PSOElman neural network. Through simulations of specific examples, satisfactory forecasting accuracy is obtained and hence the effectiveness of the proposed method is verified.
引文
[1] PENA B, TERUEL E, DIEZ L I. Soft-computing models for sootblowing optimization in coal-fired utility boilers[J]. Applied Soft Computing,2011,11(2):1657-1668.
[2] TALER J, TROJAN M, TALER D. Simulation and monitoring of fouling and slagging in coal-fired steam boilers[J]. Rynek Energii,2010, 86(1):137-147.
[3]欧宗现,阎维平,朱予东,等.锅炉吹灰优化系统的研发与应用[J].发电设备,2008, 22(4):228-290.OU Zongxian, YAN Weiping, ZHU Yudong, et al. R&D and application of an optimized boiler soot-blowing system[J]. Power Equipment, 2008, 22(4):228-290.
[4]阎维平,董建聪,高正阳,等.500MW机组塔式锅炉受热面污染特性分析与吹灰系统优化改造[J].热力发电,2011,40(8):51-56.YAN Weiping, DONG Jiancong, GAO Zhengyang, et al. Analysis of heating surface fouling behavior and optimized retrofit of soot-blowing system for tower type boiler of 500 MW unit[J]. Thermal Power Generation, 2011,40(8):51-56.
[5] KALISZ S, PRONOBIS M. Investigations on fouling rate in convective bundles of coal-fired boilers in relation to optimization of sootblower operation[J]. Fuel, 2005, 84(7-8):927-937.
[6] TERUEL E, CRISTOBAL CORTES, LUIS IGNACIO DIEZ, et al.Monitoring and prediction of fouling in coal-fired utility boilers using neural networks[J]. Chemical Engineering Science, 2005,60(18):5035-5048.
[7]陆继东,刘定坡,刘刚,等.电站锅炉优化吹灰模糊模型的研究[J].华中科技大学学报(自然科学版),2005, 33(6):35-37.LU Jidong, LIU Dingbo, LIU Gang, et al. Research on fuzzy model for the soot blowing optimization in utility boilers[J]. Journal of Huazhong University of Science and Technology, 2005, 33(6):35-37.
[8]侯子良.SIS发展到推广应用新时期面临的两大问题[J].中国电力,2005, 38(1):62-64.HOU Ziliang. Two big problems of SIS faced in the new stage of dissemination and application[J]. Electric Power, 2005, 38(1):62-64.
[9]邹金昌,包一鸣.优化软件的应用与SIS的建设[J].中国电力,2005, 38(6):69-72.ZOU Jinchang, BAO Yiming. Application of optimization software and SIS construct ion[J]. Electric Power, 2005, 38(6):69-72.
[10] LIU Hui, TIAN Hongqi, LIANG Xifeng, et al. Wind speed forecasting approach using secondary decomposition algorithm and Elman neural networks[J]. Applied Energy,2015, 157:183-194.
[11]刘远龙,龚文杰,徐超,等.基于PSO-Elman神经网络的电力系统短期负荷预测模型研究[J].青岛大学学报(工程技术版),2010,25(3):43-47.LIU Yuanlong, GONG Wenjie, XU Chao, et al. Research of shortterm load forecasting model based on PSO-Elman neural network[J].Journal of Qingdao University(Engineering&Technology Edition),2010, 25(3):43-47.
[12]丁硕,常晓恒,巫庆辉,等.基于Elman神经网络的传感器故障诊断研究[J].国外电子测量技术,2014, 33(4):72-75.DING Shuo, CHANG Xiaoheng, WU Qinghui, et al. Study of sensor fault diagnosis method based on Elman neural network[J]. Foreign Electronic Measurement Technology, 2014, 33(4):72-75.
[13]史元浩,王景成,王斌.燃煤电站锅炉受热面灰污沉积动态监测模型研究[C]//中国自动化学会控制理论专业委员会B卷,2011.SHI Yuanhao, WANG Jingcheng, WANG Bin. Ash fouling monitoring dynamic models of coal-fired utility boiler's heat transfer surface[C]//China Automation Society Control Theory SpecializedCommittee B volume, 2011.
[14]刘荣,方鸽飞.改进Elman神经网络的综合气象短期负荷预测[J].电力系统保护与控制,2012, 40(22):113-117.LIU Rong,FANG Gefei. Short-term load forecasting with comprehensive weather factors based on improved Elman neural network[J]. Power System Protection and Control, 2012, 40(22):113-117.
[15] LI B B, WANG L, LIU B. An effective PSO-based hybrid algorithm for multi objective permutation flow shop scheduling[J]. IEEE Transactions on Systems, Man, and Cybernetics-Part A:Systems and Humans,2008, 38(4):818-831.
[16] DA Y, GE X. An improved PSO-based ANN with simulated annealing technique[J]. Neurocomputing, 2005, 63:527-533.
[17]浦健,程静.基于PSO-Elman神经网络的汽轮机排汽焓在线预测计算[J].南京师范大学学报(工程技术版),2009, 9(2):35-40.PU Jian, CHENG Jing. On-line prediction and calculation of steam turbine exhaust enthalpy based on PSO-Elman neural network[J].Journal of Nanjing Normal University(Engineering and Technology Edition), 2009, 9(2):35-40.
[18]许洋.基于改进PSO-Elman网络的短期电力负荷预测[D].天津:河北工业大学,2014.
[19]张晓宇,董增寿,宋仁旺.基于EMD和改进PSO-Elman神经网络的液压故障诊断[J].计算机技术与发展,2012, 22(4):29-32.ZHANG Xiaoyu, DONG Zengshou, SONG Renwang. Hydraulic system fault diagnosis based on EMD and modified PSO-Elman ANN[J]. Computer Technology and Development, 2012, 22(4):29-32.
[2] TALER J, TROJAN M, TALER D. Simulation and monitoring of fouling and slagging in coal-fired steam boilers[J]. Rynek Energii,2010, 86(1):137-147.
[3]欧宗现,阎维平,朱予东,等.锅炉吹灰优化系统的研发与应用[J].发电设备,2008, 22(4):228-290.OU Zongxian, YAN Weiping, ZHU Yudong, et al. R&D and application of an optimized boiler soot-blowing system[J]. Power Equipment, 2008, 22(4):228-290.
[4]阎维平,董建聪,高正阳,等.500MW机组塔式锅炉受热面污染特性分析与吹灰系统优化改造[J].热力发电,2011,40(8):51-56.YAN Weiping, DONG Jiancong, GAO Zhengyang, et al. Analysis of heating surface fouling behavior and optimized retrofit of soot-blowing system for tower type boiler of 500 MW unit[J]. Thermal Power Generation, 2011,40(8):51-56.
[5] KALISZ S, PRONOBIS M. Investigations on fouling rate in convective bundles of coal-fired boilers in relation to optimization of sootblower operation[J]. Fuel, 2005, 84(7-8):927-937.
[6] TERUEL E, CRISTOBAL CORTES, LUIS IGNACIO DIEZ, et al.Monitoring and prediction of fouling in coal-fired utility boilers using neural networks[J]. Chemical Engineering Science, 2005,60(18):5035-5048.
[7]陆继东,刘定坡,刘刚,等.电站锅炉优化吹灰模糊模型的研究[J].华中科技大学学报(自然科学版),2005, 33(6):35-37.LU Jidong, LIU Dingbo, LIU Gang, et al. Research on fuzzy model for the soot blowing optimization in utility boilers[J]. Journal of Huazhong University of Science and Technology, 2005, 33(6):35-37.
[8]侯子良.SIS发展到推广应用新时期面临的两大问题[J].中国电力,2005, 38(1):62-64.HOU Ziliang. Two big problems of SIS faced in the new stage of dissemination and application[J]. Electric Power, 2005, 38(1):62-64.
[9]邹金昌,包一鸣.优化软件的应用与SIS的建设[J].中国电力,2005, 38(6):69-72.ZOU Jinchang, BAO Yiming. Application of optimization software and SIS construct ion[J]. Electric Power, 2005, 38(6):69-72.
[10] LIU Hui, TIAN Hongqi, LIANG Xifeng, et al. Wind speed forecasting approach using secondary decomposition algorithm and Elman neural networks[J]. Applied Energy,2015, 157:183-194.
[11]刘远龙,龚文杰,徐超,等.基于PSO-Elman神经网络的电力系统短期负荷预测模型研究[J].青岛大学学报(工程技术版),2010,25(3):43-47.LIU Yuanlong, GONG Wenjie, XU Chao, et al. Research of shortterm load forecasting model based on PSO-Elman neural network[J].Journal of Qingdao University(Engineering&Technology Edition),2010, 25(3):43-47.
[12]丁硕,常晓恒,巫庆辉,等.基于Elman神经网络的传感器故障诊断研究[J].国外电子测量技术,2014, 33(4):72-75.DING Shuo, CHANG Xiaoheng, WU Qinghui, et al. Study of sensor fault diagnosis method based on Elman neural network[J]. Foreign Electronic Measurement Technology, 2014, 33(4):72-75.
[13]史元浩,王景成,王斌.燃煤电站锅炉受热面灰污沉积动态监测模型研究[C]//中国自动化学会控制理论专业委员会B卷,2011.SHI Yuanhao, WANG Jingcheng, WANG Bin. Ash fouling monitoring dynamic models of coal-fired utility boiler's heat transfer surface[C]//China Automation Society Control Theory SpecializedCommittee B volume, 2011.
[14]刘荣,方鸽飞.改进Elman神经网络的综合气象短期负荷预测[J].电力系统保护与控制,2012, 40(22):113-117.LIU Rong,FANG Gefei. Short-term load forecasting with comprehensive weather factors based on improved Elman neural network[J]. Power System Protection and Control, 2012, 40(22):113-117.
[15] LI B B, WANG L, LIU B. An effective PSO-based hybrid algorithm for multi objective permutation flow shop scheduling[J]. IEEE Transactions on Systems, Man, and Cybernetics-Part A:Systems and Humans,2008, 38(4):818-831.
[16] DA Y, GE X. An improved PSO-based ANN with simulated annealing technique[J]. Neurocomputing, 2005, 63:527-533.
[17]浦健,程静.基于PSO-Elman神经网络的汽轮机排汽焓在线预测计算[J].南京师范大学学报(工程技术版),2009, 9(2):35-40.PU Jian, CHENG Jing. On-line prediction and calculation of steam turbine exhaust enthalpy based on PSO-Elman neural network[J].Journal of Nanjing Normal University(Engineering and Technology Edition), 2009, 9(2):35-40.
[18]许洋.基于改进PSO-Elman网络的短期电力负荷预测[D].天津:河北工业大学,2014.
[19]张晓宇,董增寿,宋仁旺.基于EMD和改进PSO-Elman神经网络的液压故障诊断[J].计算机技术与发展,2012, 22(4):29-32.ZHANG Xiaoyu, DONG Zengshou, SONG Renwang. Hydraulic system fault diagnosis based on EMD and modified PSO-Elman ANN[J]. Computer Technology and Development, 2012, 22(4):29-32.