输电线路覆冰厚度智能识别软件开发
|
摘要
2008年年初南方特大冰冻灾害给电网造成了很大的危害,给人民群众的生命财产造成了巨大的损失,其主要原因是输电线路覆冰厚度过大,而覆冰厚度又未能得到预知。为此,论文以山西省电力公司科技项目“减少输电线路覆冰量措施分析与应用其为依托,选定输电线路覆冰厚度智能辨识模型为研究课题。通过对该模型的研究,为覆冰厚度的预测提供必要的理论依据,提高输电线路覆冰厚度预测的精度,减少覆冰对电网的直接和潜在危害,具有较好的理论价值和现实意义。
首先,论文研究了影响输电线路覆冰厚度的主要因素。影响覆冰厚度的主要因素有温度、湿度、雨量、风力、风向、导线悬挂高度、海拔、地理环境等等。研究结果表明,温度、湿度、雨量、风力、风向为输电线路覆冰厚度主要影响因素。
第二,论文利用神经网络理论在MATLAB软件平台上分别建立了两种预测模型,其分别为基于广义回归神经网络(GRNN)的预测模型、基于ELMAN神经网络的预测模型,同时上述两种模型进行了仿真验证。仿真结果显示,GRNN神经网络模型的预测误差为0.0018,ELMAN神经网络的预测误差为0.0631,仿真结果表明,GRNN神经网络模型比ELMAN神经网络模型预测精度高,更适合预测输电线路覆冰厚度。
第三,论文针对神经网络过于依赖初值、存在过学习现象、训练过程容易陷入局部最小值等问题,将支持向量机(SVM)理论引入到覆冰厚度预测模型中,在MATLAB软件平台上建立了基于SVM的覆冰厚度预测模型。针对SVM参数难于选取的问题,将遗传算法(GA)和粒子群算法(PSO)引入到SVM模型中,建立了PSO-SVM输电线路覆冰厚度预测模型以及GA-SVM输电线路覆冰厚度预测模型。参数寻优结果表明,最优参数组合(c,g)分别为(6.2389,1.6113)和(9.3845,0.01),同时利用上述参数对SVM预测模型进行了仿真。仿真结果显示,GA-SVM模型的预测误差达到0.00109729,PSO-SVM模型的预测误差为0.00147842,仿真结果表明,GA-SVM模型比PSO-SVM模型预测精度高,更适合预测输电线路覆冰厚度。
第四,论文利用小波理论和神经网络算法在MATLAB平台上建立了小波神经网络(WNN)模型,将小波算法引用到神经网络的训练过程之中,并对该模型进行了仿真验证,仿真结果显示,WNN模型的预测误差为0.2618。
最后对本文的五个模型的仿真效果进行了分析比较,结果表明,GA-SVM模型的预测误差最小,预测精度最高,因此最适合预测输电线路覆冰的厚度。
The great harm to the grid and huge losses to the lives and property of people caused by large frozing of the south In early 2008.The main reason is the thickness of transmission line icing is too large,while ice thickness has not been predicted.To this end,the research of smart identification model for ice thickness of transmission was selected by the paper based on technology project of grid company of Shanxi province named "the measures analysis and application to reduce the amount of transmission line icing".Through the research of this model,the necessary theoretical foundation of the forecast for the icing thickness was provided,the accuracy of ice thickness prediction of transmission line was improved and the direct and potential hazards caused by icing on the grid was reduced,so the project had a good theoretical and practical significance.
Firstly,the paper studied the main factors which effected the ice thic kness of transmission line.The main factors concluded temperature,humidity, rainfall,wind,direction of wind,wire suspension height,altitude,geography and so on.And the results of research showed that temperature,humidity,rainfall, wind,direction of wind were the main factors which effected ice thickness of the transmission line.
Secondly,two prediction models were established on the MATLAB software platform on the base of neural networks,which were respectively based on generalized regression neural network (GRNN) and ELMAN neural network,then conducted simulation the two models.The results of simulation showed that the error of GRNN prediction model was 0.0018 and the error of ELMAN neural network prediction model was 0.0631.Based on th rerults that the GRNN model was better than the ELMAN neural network model on prediction precision,so GRNN model was better suited to predict the thickness of transmission line icing than ELMAN model.
Thirdly,based on the disadvantages of this paper neural networks included too dependent on the initial value,the phenomenon of existed learn, easy to fall into local minimum during training,the paper introduced the support vector machine (SVM) theory into the ice thickness prediction model,and built SVM-based prediction model on the MATLAB software platform.Then based on the parameter of SVM were difficult to be selected,genetic algorithm (GA) and particle swarm optimization (PSO) were introduced into the SVM model,GA-SVM and PSO-SVM model were established.The parameter optimization results showed that the optimal parameter combination (c, g) were respectively (6.2389,1.6113) and (9.3845,0.01),while conducted simulation to SVM prediction model token advantage of the parameters.The simulation results showed that, the error of GA-SVM model was 0.00109729 and the error of PSO-SVM model was 0.00147842,so GA-SVM model was better suited to predict the thickness of transmission line icing than PSO-SVM model.
Fourthly,wavelet neural network (WNN) model was built on MATLAB platform based on the conbination of wavelet theory and neural network algorithm through brought the wavelet algorithmto into the training process of neural networks,and the results of simulation showed that,the error of WNN model was 0.2618.
Finally,the five models are analyzed and compared by the paper,then the results showed that,the prediction error of GA-SVM model was the most little and the accuracy was highest,therefore GA-SVM model was most suitable for forecasting the ice thickness of transmission line.
首先,论文研究了影响输电线路覆冰厚度的主要因素。影响覆冰厚度的主要因素有温度、湿度、雨量、风力、风向、导线悬挂高度、海拔、地理环境等等。研究结果表明,温度、湿度、雨量、风力、风向为输电线路覆冰厚度主要影响因素。
第二,论文利用神经网络理论在MATLAB软件平台上分别建立了两种预测模型,其分别为基于广义回归神经网络(GRNN)的预测模型、基于ELMAN神经网络的预测模型,同时上述两种模型进行了仿真验证。仿真结果显示,GRNN神经网络模型的预测误差为0.0018,ELMAN神经网络的预测误差为0.0631,仿真结果表明,GRNN神经网络模型比ELMAN神经网络模型预测精度高,更适合预测输电线路覆冰厚度。
第三,论文针对神经网络过于依赖初值、存在过学习现象、训练过程容易陷入局部最小值等问题,将支持向量机(SVM)理论引入到覆冰厚度预测模型中,在MATLAB软件平台上建立了基于SVM的覆冰厚度预测模型。针对SVM参数难于选取的问题,将遗传算法(GA)和粒子群算法(PSO)引入到SVM模型中,建立了PSO-SVM输电线路覆冰厚度预测模型以及GA-SVM输电线路覆冰厚度预测模型。参数寻优结果表明,最优参数组合(c,g)分别为(6.2389,1.6113)和(9.3845,0.01),同时利用上述参数对SVM预测模型进行了仿真。仿真结果显示,GA-SVM模型的预测误差达到0.00109729,PSO-SVM模型的预测误差为0.00147842,仿真结果表明,GA-SVM模型比PSO-SVM模型预测精度高,更适合预测输电线路覆冰厚度。
第四,论文利用小波理论和神经网络算法在MATLAB平台上建立了小波神经网络(WNN)模型,将小波算法引用到神经网络的训练过程之中,并对该模型进行了仿真验证,仿真结果显示,WNN模型的预测误差为0.2618。
最后对本文的五个模型的仿真效果进行了分析比较,结果表明,GA-SVM模型的预测误差最小,预测精度最高,因此最适合预测输电线路覆冰的厚度。
The great harm to the grid and huge losses to the lives and property of people caused by large frozing of the south In early 2008.The main reason is the thickness of transmission line icing is too large,while ice thickness has not been predicted.To this end,the research of smart identification model for ice thickness of transmission was selected by the paper based on technology project of grid company of Shanxi province named "the measures analysis and application to reduce the amount of transmission line icing".Through the research of this model,the necessary theoretical foundation of the forecast for the icing thickness was provided,the accuracy of ice thickness prediction of transmission line was improved and the direct and potential hazards caused by icing on the grid was reduced,so the project had a good theoretical and practical significance.
Firstly,the paper studied the main factors which effected the ice thic kness of transmission line.The main factors concluded temperature,humidity, rainfall,wind,direction of wind,wire suspension height,altitude,geography and so on.And the results of research showed that temperature,humidity,rainfall, wind,direction of wind were the main factors which effected ice thickness of the transmission line.
Secondly,two prediction models were established on the MATLAB software platform on the base of neural networks,which were respectively based on generalized regression neural network (GRNN) and ELMAN neural network,then conducted simulation the two models.The results of simulation showed that the error of GRNN prediction model was 0.0018 and the error of ELMAN neural network prediction model was 0.0631.Based on th rerults that the GRNN model was better than the ELMAN neural network model on prediction precision,so GRNN model was better suited to predict the thickness of transmission line icing than ELMAN model.
Thirdly,based on the disadvantages of this paper neural networks included too dependent on the initial value,the phenomenon of existed learn, easy to fall into local minimum during training,the paper introduced the support vector machine (SVM) theory into the ice thickness prediction model,and built SVM-based prediction model on the MATLAB software platform.Then based on the parameter of SVM were difficult to be selected,genetic algorithm (GA) and particle swarm optimization (PSO) were introduced into the SVM model,GA-SVM and PSO-SVM model were established.The parameter optimization results showed that the optimal parameter combination (c, g) were respectively (6.2389,1.6113) and (9.3845,0.01),while conducted simulation to SVM prediction model token advantage of the parameters.The simulation results showed that, the error of GA-SVM model was 0.00109729 and the error of PSO-SVM model was 0.00147842,so GA-SVM model was better suited to predict the thickness of transmission line icing than PSO-SVM model.
Fourthly,wavelet neural network (WNN) model was built on MATLAB platform based on the conbination of wavelet theory and neural network algorithm through brought the wavelet algorithmto into the training process of neural networks,and the results of simulation showed that,the error of WNN model was 0.2618.
Finally,the five models are analyzed and compared by the paper,then the results showed that,the prediction error of GA-SVM model was the most little and the accuracy was highest,therefore GA-SVM model was most suitable for forecasting the ice thickness of transmission line.
引文
[1]蒋兴良,易辉.输电线路覆冰及防护[M].中国电力出版社,2001.
[2]戚大安.积极防治电网覆冰灾害[J].国家电网,2007,24(1)：18-21.
[3]http://www.chinanews.com/ny/2011/01-30/2821817.shtml.
[4]黄新波等.导线覆冰的力学分析与覆冰在线监测系统[J].电力系统自动化,2007,31(14)：98-101.
[5]汪秀丽.输电线路覆冰浅论[J].水利电力科技,2008,12(3)：35-39.
[6]李政敏,庚振平,胡琰锋.输电线路覆冰的危害及防护[J].电瓷避雷器,2006,27(2),23-28.
[7]杜欣慧,杨尉薇,邹邵峰等.220kV输电线路覆冰厚度模型智能辨识研究[J].电气技术,2009,118：53-57.
[8]李军,禹伟,许源等.摹于湖南省冰冻分布及气候特征的思考[J].湖南电力,2004,24(2)：16-19.
[9]谢运华.二峡地区导线覆冰与气象要素的关系[J].中国电力,2005,38(3)：35-39.
[10]朱宽军,刘超群,任西春.架空输电线路舞动时导线动态张力分析[J].中国电力,2005,38(10)：40-44.
[11]胡红春.冰害、冰闪和舞动的防治措施[J].电力建设,2005,26(9)：31-34.
[12]Chen S.Recursive Hybrid Algorithm For nonlinear identification using radial basis function networks[J].International Journal of Control,1992,55(5):1051-1070.
[13]Sprecht D F A general regression neural network 1991(02)
[14]Sprecht D F The general regression neural network rediscovered 1993(06)
[15]卢冠群.基于广义回归神经网络的公路旅游交通量预测分析[D].长沙：长沙理工大学,2009.
[16]姚李孝,刘学琴,伍利,薛美娟.基于广义回归神经网络的电力系统中长期负荷预测[J].电力自动化设备,2007,27(8)：26-29.
[17]魏晋雁,茹锋.采用GRNN模型进行交通量预测及实现研究[J].长沙交通学院学报,2006,22(2)：46-50.
[18]Du Xinhui,Zheng Zhenhua, Tan Shaoqiong; Wang Jian. The Study on The Predic tion Method of Ice Thickness of Transmission Line Based on The Combination of GA and BP Neural Network[C].The 1st International Conference on Managem -ent Science and Artificial Intelligence (MSAI 2010),2010,vol.2,p2695-2698.Inde-xed by El (20110313604378).
[19]梁凤国,李帅莹,于淼,马宗正.基于GRNN神经网络的参考作物腾发量预测[J].人民长江,2009,40(5)：58-60.
[20]姜长生.基于Elman神经网络的空战威胁排序研究[J].电光与控制,2008,15(8)：1-5.
[21]任丽娜.基于Elman神经网络的中期电力负荷预测模型研究[D].兰州：兰州理工大学,2007.
[22]孙洪波,秦翼鸿,徐国禹.用于短期电力负荷预报的人工神经网络方法[J].重庆大学学报,1995,16(7)：42-47.
[23]王科俊,王克成.神经网络建模、预报与控制[M].哈尔滨：哈尔滨工程大学出版社,1996.
[24]王静娴.基于支持向量机的中短期电力负荷预测[D].北京：华北电力大学,2008.
[25]李涛.基于SVM和PSO的非线性模型预测控制及应用研究[D].上海：上海交通大学,2008.
[26]Burges Christopher J. C.A tutorial on support vector machines for pattern recog-nition[J]. Data Mining and Knowledge Discovery,1998,2; 121-167.
[27]Cortes C, Vapnik V. The Soft Margin Classifier [J]. Technical memorandum 113 59-931209-18TM, AT&T Bell Labs,1993.
[28]Platt J. Sequential Minimal Optimization:A Fast Algorithm for Training Support Vector Machines, Advances in Kernel Methods-Support Vector learning[C].The MIT Press,1999.
[29]庄耿洪.基于遗传支持向量回归的人才需求预测模型[D].广州：中山大学,2010.
[30]刘春芬,基于GA的SVM网络威胁频率预测方法[D].北京：国防科学技术大学研究生院,2006.
[31]宗朝霞,汤宏胜,贺曼,葛忠学,来蔚鹏,李华.基于遗传算法的支持向量机预测含能材料密度的研究[J].计算机与应用化学,2009,26(12)：1529-1533.
[32]齐琚,牛军峰.基于遗传一支持向量机和遗传一径向基神经网络的有机物正辛醇一水分配系数QSPR研究[J].环境科学,2008,29(1)：212-218.
[33]吴景龙,杨淑霞,刘承水.基于遗传算法优化参数的支持向量机短期负荷预测方 法[J].中南大学学报,2009,2：180-184.
[34]Yong-Ling Zheng, Long-Hua Ma, Li-Yan Zhang, Ji-Xin Qian. On the convergenc-e analysis and parameter selectionin particle swarm optimization [J]. IEEE Proce-edings of the Second International Conference on Machine Learning and Cybern-etics, Xi'an,2003; 1802-1807.
[35]Kennedy J. and Eberhart R. C. Particle swarm optimization [J]. Proceedings of I-EEE International Conference on Neural Networks,1995; 1942-1948.
[36]Eberhart R.C., Shi Y. Comparing Inertia Weights and Constriction Factors in Part-icle Swarm Optimization[J].IEEE Congress Evolutionary Computation,2000; 84-88。
[37]Eberhart R. C., Shi Y. Particle swarm optimization developments.applications and resources [J], IEEE,2001; 81-86.
[38]张丽平.粒子群优化算法的理论及实践[D].杭州：浙江大学材料与化学工程学院博士学位论文,2005.
[39]陈震奕.粒子群优化算法研究及其在TSP问题中的应用[D].福州：福州大学博士学位论文,2004.
[40]张培林,钱林方,曹建军,任国全.基于蚁群算法的支持向量机参数优化[J].南京理工大学学报(自然科学版),2009,33(4)：12-16.
[41]姜谙男.基于PSO-SVM非线性时序模型的隧洞围岩变形预报.岩土力学[J],2007,28(6)：1176-1180.
[42]马利华.基于粗集-小波神经网络的建筑工程成本预测方法[D].邯郸：河北工程大学经济管理学院,2007.
[43]费佩燕,刘曙光.小波分析应用的进展与展望[J].纺织高校基础科学学报.2001,14(1)：72-78.
[44]邓宇.基于小波神经网络的重庆市某主城区饮用水源水质参数预测模型研究[D].重庆：重庆医科大学,2009.
[45]葛哲学.小波分析理论与MATLAB R2007实现[M].北京：电子工业出版社,2006,31-40.
[46]王建伟.基于小波分析和神经网络的股票预测方法[D].北京：北京工业大学, 2004.
[47]Daubechies I. Ten lectures on wavelet[M]. Phi ladelphia.PA:SIAM Press,19-88
[48]Hornik K, Stinchcombe M, White H. Multi layer feed forward networks are universal approx imators[J]. Neural Networks,1989,1(2):359—366
[49]蒋霖,李向民等.多小波神经网络在变形预测中的应用[J].山西建筑,2008,34(1)：13-14.
[50]虞和济,陈长征,张省等.基于神经网络的智能诊断[M].北京：冶金工业出版社.2000.
[51]王岭,焦李成.区间估计的FWNN及其区间学习算法[J].电子学报,1998,26(4)：42-45.
[52]Szu n, Telfer B, Kadambe S. Neural network adaptive wavelets for signal repre8entation and classification[J]. Optical Engineering,1992,36(9):1907-1916
[53]代正梅.基于小波神经网络预测控制的加热炉炉温控制策略的研究[D].太原：太原理工大学,2007.
[54]李国勇.智能控制及其MATLAB实现[M].北京：电子工业出版社,2005.
[2]戚大安.积极防治电网覆冰灾害[J].国家电网,2007,24(1)：18-21.
[3]http://www.chinanews.com/ny/2011/01-30/2821817.shtml.
[4]黄新波等.导线覆冰的力学分析与覆冰在线监测系统[J].电力系统自动化,2007,31(14)：98-101.
[5]汪秀丽.输电线路覆冰浅论[J].水利电力科技,2008,12(3)：35-39.
[6]李政敏,庚振平,胡琰锋.输电线路覆冰的危害及防护[J].电瓷避雷器,2006,27(2),23-28.
[7]杜欣慧,杨尉薇,邹邵峰等.220kV输电线路覆冰厚度模型智能辨识研究[J].电气技术,2009,118：53-57.
[8]李军,禹伟,许源等.摹于湖南省冰冻分布及气候特征的思考[J].湖南电力,2004,24(2)：16-19.
[9]谢运华.二峡地区导线覆冰与气象要素的关系[J].中国电力,2005,38(3)：35-39.
[10]朱宽军,刘超群,任西春.架空输电线路舞动时导线动态张力分析[J].中国电力,2005,38(10)：40-44.
[11]胡红春.冰害、冰闪和舞动的防治措施[J].电力建设,2005,26(9)：31-34.
[12]Chen S.Recursive Hybrid Algorithm For nonlinear identification using radial basis function networks[J].International Journal of Control,1992,55(5):1051-1070.
[13]Sprecht D F A general regression neural network 1991(02)
[14]Sprecht D F The general regression neural network rediscovered 1993(06)
[15]卢冠群.基于广义回归神经网络的公路旅游交通量预测分析[D].长沙：长沙理工大学,2009.
[16]姚李孝,刘学琴,伍利,薛美娟.基于广义回归神经网络的电力系统中长期负荷预测[J].电力自动化设备,2007,27(8)：26-29.
[17]魏晋雁,茹锋.采用GRNN模型进行交通量预测及实现研究[J].长沙交通学院学报,2006,22(2)：46-50.
[18]Du Xinhui,Zheng Zhenhua, Tan Shaoqiong; Wang Jian. The Study on The Predic tion Method of Ice Thickness of Transmission Line Based on The Combination of GA and BP Neural Network[C].The 1st International Conference on Managem -ent Science and Artificial Intelligence (MSAI 2010),2010,vol.2,p2695-2698.Inde-xed by El (20110313604378).
[19]梁凤国,李帅莹,于淼,马宗正.基于GRNN神经网络的参考作物腾发量预测[J].人民长江,2009,40(5)：58-60.
[20]姜长生.基于Elman神经网络的空战威胁排序研究[J].电光与控制,2008,15(8)：1-5.
[21]任丽娜.基于Elman神经网络的中期电力负荷预测模型研究[D].兰州：兰州理工大学,2007.
[22]孙洪波,秦翼鸿,徐国禹.用于短期电力负荷预报的人工神经网络方法[J].重庆大学学报,1995,16(7)：42-47.
[23]王科俊,王克成.神经网络建模、预报与控制[M].哈尔滨：哈尔滨工程大学出版社,1996.
[24]王静娴.基于支持向量机的中短期电力负荷预测[D].北京：华北电力大学,2008.
[25]李涛.基于SVM和PSO的非线性模型预测控制及应用研究[D].上海：上海交通大学,2008.
[26]Burges Christopher J. C.A tutorial on support vector machines for pattern recog-nition[J]. Data Mining and Knowledge Discovery,1998,2; 121-167.
[27]Cortes C, Vapnik V. The Soft Margin Classifier [J]. Technical memorandum 113 59-931209-18TM, AT&T Bell Labs,1993.
[28]Platt J. Sequential Minimal Optimization:A Fast Algorithm for Training Support Vector Machines, Advances in Kernel Methods-Support Vector learning[C].The MIT Press,1999.
[29]庄耿洪.基于遗传支持向量回归的人才需求预测模型[D].广州：中山大学,2010.
[30]刘春芬,基于GA的SVM网络威胁频率预测方法[D].北京：国防科学技术大学研究生院,2006.
[31]宗朝霞,汤宏胜,贺曼,葛忠学,来蔚鹏,李华.基于遗传算法的支持向量机预测含能材料密度的研究[J].计算机与应用化学,2009,26(12)：1529-1533.
[32]齐琚,牛军峰.基于遗传一支持向量机和遗传一径向基神经网络的有机物正辛醇一水分配系数QSPR研究[J].环境科学,2008,29(1)：212-218.
[33]吴景龙,杨淑霞,刘承水.基于遗传算法优化参数的支持向量机短期负荷预测方 法[J].中南大学学报,2009,2：180-184.
[34]Yong-Ling Zheng, Long-Hua Ma, Li-Yan Zhang, Ji-Xin Qian. On the convergenc-e analysis and parameter selectionin particle swarm optimization [J]. IEEE Proce-edings of the Second International Conference on Machine Learning and Cybern-etics, Xi'an,2003; 1802-1807.
[35]Kennedy J. and Eberhart R. C. Particle swarm optimization [J]. Proceedings of I-EEE International Conference on Neural Networks,1995; 1942-1948.
[36]Eberhart R.C., Shi Y. Comparing Inertia Weights and Constriction Factors in Part-icle Swarm Optimization[J].IEEE Congress Evolutionary Computation,2000; 84-88。
[37]Eberhart R. C., Shi Y. Particle swarm optimization developments.applications and resources [J], IEEE,2001; 81-86.
[38]张丽平.粒子群优化算法的理论及实践[D].杭州：浙江大学材料与化学工程学院博士学位论文,2005.
[39]陈震奕.粒子群优化算法研究及其在TSP问题中的应用[D].福州：福州大学博士学位论文,2004.
[40]张培林,钱林方,曹建军,任国全.基于蚁群算法的支持向量机参数优化[J].南京理工大学学报(自然科学版),2009,33(4)：12-16.
[41]姜谙男.基于PSO-SVM非线性时序模型的隧洞围岩变形预报.岩土力学[J],2007,28(6)：1176-1180.
[42]马利华.基于粗集-小波神经网络的建筑工程成本预测方法[D].邯郸：河北工程大学经济管理学院,2007.
[43]费佩燕,刘曙光.小波分析应用的进展与展望[J].纺织高校基础科学学报.2001,14(1)：72-78.
[44]邓宇.基于小波神经网络的重庆市某主城区饮用水源水质参数预测模型研究[D].重庆：重庆医科大学,2009.
[45]葛哲学.小波分析理论与MATLAB R2007实现[M].北京：电子工业出版社,2006,31-40.
[46]王建伟.基于小波分析和神经网络的股票预测方法[D].北京：北京工业大学, 2004.
[47]Daubechies I. Ten lectures on wavelet[M]. Phi ladelphia.PA:SIAM Press,19-88
[48]Hornik K, Stinchcombe M, White H. Multi layer feed forward networks are universal approx imators[J]. Neural Networks,1989,1(2):359—366
[49]蒋霖,李向民等.多小波神经网络在变形预测中的应用[J].山西建筑,2008,34(1)：13-14.
[50]虞和济,陈长征,张省等.基于神经网络的智能诊断[M].北京：冶金工业出版社.2000.
[51]王岭,焦李成.区间估计的FWNN及其区间学习算法[J].电子学报,1998,26(4)：42-45.
[52]Szu n, Telfer B, Kadambe S. Neural network adaptive wavelets for signal repre8entation and classification[J]. Optical Engineering,1992,36(9):1907-1916
[53]代正梅.基于小波神经网络预测控制的加热炉炉温控制策略的研究[D].太原：太原理工大学,2007.
[54]李国勇.智能控制及其MATLAB实现[M].北京：电子工业出版社,2005.