多组群教学优化算法-神经网络-支持向量机组合模型在径流预测中的应用
|
摘要
采用5个标准测试函数对多组群教学优化(MGTLO)算法进行仿真验证,并将仿真结果与基本教学优化(TLBO)算法、混合蛙跳算法(SFLA)、差分进化(DE)算法和粒子群优化(PSO)算法的仿真结果进行对比。利用MGTLO算法搜寻基于广义回归神经网络(GRNN)、径向基神经网络(RBF)、支持向量机(SVM)模型单元的组合模型的最佳模型参数和组合权重系数,提出MGTLO-GRNN-RBF、MGTLO-GRNN-SVM、MGTLO-RBF-SVM、MGTLO-GRNN-RBF-SVM 4种组合预测模型,以新疆伊犁河雅马渡水文站和云南省某水文站年径流量预测为例进行了实例分析,并将预测结果与MGTLO-GRNN、MGTLO-RBF、MGTLO-SVM和GRNN、RBF、SVM 6种单一模型的结果进行对比分析。结果表明:MGTLO算法寻优精度优于TLBO、SFLA、DE和PSO算法,具有较好的收敛速度和全局极值寻优能力;组合模型融合了MGTLO算法与GRNN、RBF、SVM模型单元的优点,在预测精度、泛化能力等方面均优于单一模型;MGTLO算法能有效优化各组合模型的相关参数和权重系数,MGTLO-GRNN-RBF-SVM模型预测精度最高。
Five standard test functions were used to verify the multi-group teaching optimization(MGTLO) algorithm, and the simulation results were compared with those of the basic teaching optimization(TLBO) algorithm, shuffled frog leaping algorithm(SFLA), differential evolution(DE) algorithm and particle swarm optimization(PSO) algorithm. MGTLO was used to search for the optimum model parameters and the weight coefficients of the combined model based on the generalized regression neural network(GRNN), the radial basis function neural network(RBF) and the support vector machine(SVM) model elements. Four combined prediction models, including MGTLO-GRNN-RBF, MGTLO-GRNN-SVM, MGTLO-RBF-SVM, and MGTLO-GRNN-RBF-SVM were proposed and case studies of the runoff prediction were performed at the Yamadu Hydrological Station of the Yili River in Xinjiang and a hydrological station in Yunnan Province. The predicted results were compared with the following six single models, MGTLO-GRNN, MGTLO-RBF, MGTLO-SVM, GRNN, RBF and SVM. The results show that the optimization accuracy of MGTLO algorithm is better than that of TLBO, SFLA, DE and PSO, with good convergence speed and global optimization ability. The combined model merges the advantages of MGTLO algorithm, GRNN, RBF, and SVM model elements. It is superior to single models in terms of prediction accuracy and generalization ability. MGTLO algorithm can effectively optimize the parameters and weight coefficients of the combined models and the MGTLO-GRNN-RBF-SVM model has the highest prediction accuracy.
Five standard test functions were used to verify the multi-group teaching optimization(MGTLO) algorithm, and the simulation results were compared with those of the basic teaching optimization(TLBO) algorithm, shuffled frog leaping algorithm(SFLA), differential evolution(DE) algorithm and particle swarm optimization(PSO) algorithm. MGTLO was used to search for the optimum model parameters and the weight coefficients of the combined model based on the generalized regression neural network(GRNN), the radial basis function neural network(RBF) and the support vector machine(SVM) model elements. Four combined prediction models, including MGTLO-GRNN-RBF, MGTLO-GRNN-SVM, MGTLO-RBF-SVM, and MGTLO-GRNN-RBF-SVM were proposed and case studies of the runoff prediction were performed at the Yamadu Hydrological Station of the Yili River in Xinjiang and a hydrological station in Yunnan Province. The predicted results were compared with the following six single models, MGTLO-GRNN, MGTLO-RBF, MGTLO-SVM, GRNN, RBF and SVM. The results show that the optimization accuracy of MGTLO algorithm is better than that of TLBO, SFLA, DE and PSO, with good convergence speed and global optimization ability. The combined model merges the advantages of MGTLO algorithm, GRNN, RBF, and SVM model elements. It is superior to single models in terms of prediction accuracy and generalization ability. MGTLO algorithm can effectively optimize the parameters and weight coefficients of the combined models and the MGTLO-GRNN-RBF-SVM model has the highest prediction accuracy.
引文
[1]覃光华,宋克超,周泽江,等.基于WA-GRNN模型的年径流预测[J].四川大学学报(工程科学版),2013,45(6):39-46.(QIN Guanghua,SONG Kechao,ZHOUZejiang,et al.Research on annual runoff prediction based on WA-GRNN model[J].Journal of Sichuan University(Engineering Science Edition),2013,45(6):39-46.(in Chinese))
[2]崔东文,吴盛华.MVO-GRNN模型在年径流丰枯分类中的应用[J].人民珠江,2015,36(6):50-54.(CUIDongwen,WU Shenghua.Application of MVO-GRNNmodel in the classification of annual runoff bleeding[J].Pearl River,2015,36(6):50-54.(in Chinese))
[3]黄剑竹.改进RBF-Adaboost模型及其在年径流预测中的应用[J].人民珠江,2015,36(1):32-36.(HUANGJianzhu.Modified RBF-Adaboost model and its application in annual runoff prediction[J].Pearl River,2015,36(1):32-36.(in Chinese))
[4]任磊,岳春芳,何训江.RBF神经网络模型在金沟河流域径流预测中的应用水资源与水工程学报[J].水资源与水工程学报,2011,22(1):94-97.(REN Lei,YUEChunfang,HE Xunjiang.Application of RBF neural network model to the prediction of runoff in Jingouhe River Basin[J].Journal of Water Resources and Water Engineering,2011,22(1):94-97.(in Chinese))
[5]崔东文.基于多元变量组合的回归支持向量机集成模型及其应用[J].水利水运工程学报,2014,39(1):66-73.(CUI Dongwen.A regression support vector machine integrated model based on multivariate combinations and its application[J].Hydro-Science and Engineering,2014,39(1):66-73.(in Chinese))
[6]崔东文,金波.基于改进的回归支持向量机模型及其在年径流预测中的应用[J].水力发电学报,2015,34(2):7-14.(CUI Dongwen,JIN Bo.Improved support vector machine regression model and its application to annual runoff forecasting[J].Journal of Hydroelectric Engineering,2015,34(2):7-14.(in Chinese))
[7]崔东文.多重组合神经网络模型在年径流预测中的应用[J].水利水电科技进展,2014,34(2):59-63.(CUIDongwen.Application of multiple combined neural network model in annual runoff prediction[J].Advances in Science and Technology of Water Resources,2014,34(2):59-63.(in Chinese))
[8]韩锐,董增川,王雪薇,等.加权平均集成模型在径流预测中的应用[J].人民黄河,2017,39(6):16-20.(HAN Rui,DONG Zengchuan,WANG Xuewei,et al.Application of weighted average integrated model in runoff forecasting[J].Yellow River,2017,39(6):16-20.(in Chinese))
[9]李佩,彭斯俊.一种新的组合权重在组合预测模型中的应用[J].河南科技大学学报(自然科学版),2018,39(2):87-93.(LI Pei,PENG Sijun.Application of new combination weight to combination forecasting model[J].Journal of Henan University of Science and Technology(Natural Science),2018,39(2):87-93.(in Chinese))
[10]马辉,孙颍桃,肖艳,等.基于灰色-BP神经网络组合模型的水位预测案例[J].人民黄河,2016,38(12):89-92.(MA Hui,SUN Yingtao,XIAO Yan,et al.Case analysis of water level prediction based on grey-BP neural network combinational model[J].Yellow River,2016,38(12):89-92.(in Chinese))
[11]崔东文.加权平均集成神经网络模型在城市需水预测中的应用[J].水资源保护,2014,30(2):27-32.(CUIDongwen.Application of weighted average integrated neural network model tourban water demand forecasting[J].Water Resources Protection,2014,30(2):27-32.(in Chinese))
[12]谢劭峰,佘娣,王新桥.变形预测的一种最优线性组合模型[J].人民黄河,2017,39(6):99-101.(XIEShaofeng,SHE Di,WANG Xinqiao.An optimal linear combined model of deformation prediction[J].Yellow River,2017,39(6):99-101.(in Chinese))
[13]刘翠玲,张璐璐.基于FOA-GRNN油井计量原油含水率的预测[J].计算机仿真,2012,29(11):243-246.(LINCuiling,ZHANG Lulu.Application of FOA-GRNN to prediction of moisture content in crude oil of well metering[J].Computer Simulation,2012,29(11):243-246.(in Chinese))
[14]白继中,师彪,冯民权,等.自我调节蚁群-RBF神经网络模型在短期径流预测中的应用[J].水力发电学报,2011,30(3):50-56.(BAI Jizhong,SHI Biao,FENG Minquan,et al.Short-term runoff prediction based on adaptive regulation ant colony system and radial basis function neural network hybrid algorithm[J].Journal of Hydroelectric Engineering,2011,30(3):50-56.(in Chinese))
[15]赵丽虹,范敬柱.量子鱼群算法优化RBF网络的浮选预测模型[J].辽宁科技大学学报,2015,38(1):46-50.(ZHAOLihong,FAN Jingzhu.Application of RBF-net in flotation prediction model based on quantum artificial fish school algorithm[J].Journal of University of Science and Technology Liaoning,2015,38(1):46-50.(in Chinese))
[16]崔东文.几种智能算法与支持向量机融合模型在中长期月径流预测中的应用[J].华北水利水电大学学报(自然科学版),2016,37(5):51-57.(CUI Dongwen.Application of several intelligent algorithms and support vector machine fusion model in medium and long term runoff forecasting[J].Journal of North China University of Water Resources and Hydropower University(Natural Science),2016,37(5):51-57.(in Chinese))
[17]RAO R V,SAVASNI V J,VAKHARIA D P.Teachinglearning-based optimization:an optimization method for continuous non-linear large scale problems[J].Information Sciences,2012,183(1):1-15.
[18]陈得宝,魏华,邹锋,等.模拟退火教学式优化算法[J].计算机应用研究,2014,31(12):3353-3356.(CHENDebao,WEI Hua,ZOU Feng,et al.Simulated annealing teaching-learning-based optimization algorithm[J].Application Research of Computers,2014,31(12):3353-3356.(in Chinese))
[19]KOMMADATH R,SIVADURGAPRASAD C,KOTECHAP.Single phase multi-group teaching learning algorithm for single objective real-parameter numerical optimization(CEC2016)[C]//2016 IEEE Congress on Evolutionary Computation(CEC).Vancouver:IEEE,2016:1165-1172.
[20]谢习华,徐雷,谭耀,等.基于PSO-GRNN的直升机旋翼不平衡故障诊断[J].噪声与振动控制,2015,35(2):175-179.(XIE Xihua,XU Lei,TAN Yao,et al.Fault diagnosis of helicopter rotor’s unbalance based on PSO-GRNN algorithms[J].Noise and Vibration Control,2015,35(2):175-179.(in Chinese))
[21]王拂晓,谭志祥,邓喀中.基于GA-GRNN的地表下沉系数预测方法研究[J].煤炭工程,2014,46(7):94-96.(WANG Fuxiao,TAN Zhixiang,DENG Kazhong.Study on the prediction method of surface subsidence coefficient using GA-GRNN[J].Coal Engineering,2014,46(7):94-96.(in Chinese))
[22]邱建东,蒋兆远.基于NLAPSO-RBF的铁路货运量预测研究[J].计算机工程与应用,2013,49(22):253-257.(QIU Jiandong,JIANG Zhaoyuan.Research of railway freight volume prediction based on NLA-PSO-RBF[J].Computer Engineering and Applications,2013,49(22):253-257.(in Chinese))
[23]刘伟,王建平,刘长虹,等.基于粒子群寻优的支持向量机番茄红素含量预测[J].农业机械学报,2012,43(4):143-147.(LIU Wei,WANG Jianping,LIUChanghong,et al.Lycopene content prediction based on support vector machine with particle swarm optimization[J].Transactions of the Chinese Society for Agricultural Machinery,2012,43(4):143-147.(in Chinese))
[24]廖杰,王文圣,李跃清.支持向量机及其在径流预测中的应用[J].四川大学学报(工程科学版),2006,38(6):24-29.(LIAO Jie,WANG Wensheng,LI Yueqing.Support vector machine method and its application to prediction of runoff[J].Journal of Sichuan University(Engineering Sciences Edition),2006,38(6):24-28.(in Chinese))
[25]徐纬芳,刘成忠,顾延涛.基于PCA和支持向量机的径流预测应用研究[J].水资源与水工程学报,2010,21(6):72-75.(XU Weifang,LIU Chengzhong,GUYantao.Application research onrunoff forecasting based on PCA and support vector machine[J].Journal of Water Resources and Water Engineering,2010,21(6):72-75.(in Chinese))
[26]李佳,王黎,马光文,等.LS-SVM在径流预测中的应用[J].中国农村水利水电,2008(5):8-11.(LI Jia,WANG Li,MA Guangwen,et al.Application of LS-SVMin runoff forecasting[J].China Rural Water and Hydropower,2008(5):8-11.(in Chinese))
[27]周佩玲,陶小丽,傅忠谦,等.基于遗传算法的RBF网络及应用[J].信号处理,2001,17(3):269-273.(ZHOUPeiling,TAO Xiaoli,FU Zhongqian,et al.RBF network based on genetic algorithm and its application[J]Journal of Signal Processing,2001,17(3):269-273.(in Chinese))
[28]杨易华,罗伟伟.基于KPCA-PSO-SVM的径流预测研究[J].人民长江,2017,48(3):44-47.(YANGYihua,LUO Weiwei.Research on runoff forecast based on KPCA-PSO-SVM[J].Yangtze River,2017,48(3):44-47.(in Chinese))
[2]崔东文,吴盛华.MVO-GRNN模型在年径流丰枯分类中的应用[J].人民珠江,2015,36(6):50-54.(CUIDongwen,WU Shenghua.Application of MVO-GRNNmodel in the classification of annual runoff bleeding[J].Pearl River,2015,36(6):50-54.(in Chinese))
[3]黄剑竹.改进RBF-Adaboost模型及其在年径流预测中的应用[J].人民珠江,2015,36(1):32-36.(HUANGJianzhu.Modified RBF-Adaboost model and its application in annual runoff prediction[J].Pearl River,2015,36(1):32-36.(in Chinese))
[4]任磊,岳春芳,何训江.RBF神经网络模型在金沟河流域径流预测中的应用水资源与水工程学报[J].水资源与水工程学报,2011,22(1):94-97.(REN Lei,YUEChunfang,HE Xunjiang.Application of RBF neural network model to the prediction of runoff in Jingouhe River Basin[J].Journal of Water Resources and Water Engineering,2011,22(1):94-97.(in Chinese))
[5]崔东文.基于多元变量组合的回归支持向量机集成模型及其应用[J].水利水运工程学报,2014,39(1):66-73.(CUI Dongwen.A regression support vector machine integrated model based on multivariate combinations and its application[J].Hydro-Science and Engineering,2014,39(1):66-73.(in Chinese))
[6]崔东文,金波.基于改进的回归支持向量机模型及其在年径流预测中的应用[J].水力发电学报,2015,34(2):7-14.(CUI Dongwen,JIN Bo.Improved support vector machine regression model and its application to annual runoff forecasting[J].Journal of Hydroelectric Engineering,2015,34(2):7-14.(in Chinese))
[7]崔东文.多重组合神经网络模型在年径流预测中的应用[J].水利水电科技进展,2014,34(2):59-63.(CUIDongwen.Application of multiple combined neural network model in annual runoff prediction[J].Advances in Science and Technology of Water Resources,2014,34(2):59-63.(in Chinese))
[8]韩锐,董增川,王雪薇,等.加权平均集成模型在径流预测中的应用[J].人民黄河,2017,39(6):16-20.(HAN Rui,DONG Zengchuan,WANG Xuewei,et al.Application of weighted average integrated model in runoff forecasting[J].Yellow River,2017,39(6):16-20.(in Chinese))
[9]李佩,彭斯俊.一种新的组合权重在组合预测模型中的应用[J].河南科技大学学报(自然科学版),2018,39(2):87-93.(LI Pei,PENG Sijun.Application of new combination weight to combination forecasting model[J].Journal of Henan University of Science and Technology(Natural Science),2018,39(2):87-93.(in Chinese))
[10]马辉,孙颍桃,肖艳,等.基于灰色-BP神经网络组合模型的水位预测案例[J].人民黄河,2016,38(12):89-92.(MA Hui,SUN Yingtao,XIAO Yan,et al.Case analysis of water level prediction based on grey-BP neural network combinational model[J].Yellow River,2016,38(12):89-92.(in Chinese))
[11]崔东文.加权平均集成神经网络模型在城市需水预测中的应用[J].水资源保护,2014,30(2):27-32.(CUIDongwen.Application of weighted average integrated neural network model tourban water demand forecasting[J].Water Resources Protection,2014,30(2):27-32.(in Chinese))
[12]谢劭峰,佘娣,王新桥.变形预测的一种最优线性组合模型[J].人民黄河,2017,39(6):99-101.(XIEShaofeng,SHE Di,WANG Xinqiao.An optimal linear combined model of deformation prediction[J].Yellow River,2017,39(6):99-101.(in Chinese))
[13]刘翠玲,张璐璐.基于FOA-GRNN油井计量原油含水率的预测[J].计算机仿真,2012,29(11):243-246.(LINCuiling,ZHANG Lulu.Application of FOA-GRNN to prediction of moisture content in crude oil of well metering[J].Computer Simulation,2012,29(11):243-246.(in Chinese))
[14]白继中,师彪,冯民权,等.自我调节蚁群-RBF神经网络模型在短期径流预测中的应用[J].水力发电学报,2011,30(3):50-56.(BAI Jizhong,SHI Biao,FENG Minquan,et al.Short-term runoff prediction based on adaptive regulation ant colony system and radial basis function neural network hybrid algorithm[J].Journal of Hydroelectric Engineering,2011,30(3):50-56.(in Chinese))
[15]赵丽虹,范敬柱.量子鱼群算法优化RBF网络的浮选预测模型[J].辽宁科技大学学报,2015,38(1):46-50.(ZHAOLihong,FAN Jingzhu.Application of RBF-net in flotation prediction model based on quantum artificial fish school algorithm[J].Journal of University of Science and Technology Liaoning,2015,38(1):46-50.(in Chinese))
[16]崔东文.几种智能算法与支持向量机融合模型在中长期月径流预测中的应用[J].华北水利水电大学学报(自然科学版),2016,37(5):51-57.(CUI Dongwen.Application of several intelligent algorithms and support vector machine fusion model in medium and long term runoff forecasting[J].Journal of North China University of Water Resources and Hydropower University(Natural Science),2016,37(5):51-57.(in Chinese))
[17]RAO R V,SAVASNI V J,VAKHARIA D P.Teachinglearning-based optimization:an optimization method for continuous non-linear large scale problems[J].Information Sciences,2012,183(1):1-15.
[18]陈得宝,魏华,邹锋,等.模拟退火教学式优化算法[J].计算机应用研究,2014,31(12):3353-3356.(CHENDebao,WEI Hua,ZOU Feng,et al.Simulated annealing teaching-learning-based optimization algorithm[J].Application Research of Computers,2014,31(12):3353-3356.(in Chinese))
[19]KOMMADATH R,SIVADURGAPRASAD C,KOTECHAP.Single phase multi-group teaching learning algorithm for single objective real-parameter numerical optimization(CEC2016)[C]//2016 IEEE Congress on Evolutionary Computation(CEC).Vancouver:IEEE,2016:1165-1172.
[20]谢习华,徐雷,谭耀,等.基于PSO-GRNN的直升机旋翼不平衡故障诊断[J].噪声与振动控制,2015,35(2):175-179.(XIE Xihua,XU Lei,TAN Yao,et al.Fault diagnosis of helicopter rotor’s unbalance based on PSO-GRNN algorithms[J].Noise and Vibration Control,2015,35(2):175-179.(in Chinese))
[21]王拂晓,谭志祥,邓喀中.基于GA-GRNN的地表下沉系数预测方法研究[J].煤炭工程,2014,46(7):94-96.(WANG Fuxiao,TAN Zhixiang,DENG Kazhong.Study on the prediction method of surface subsidence coefficient using GA-GRNN[J].Coal Engineering,2014,46(7):94-96.(in Chinese))
[22]邱建东,蒋兆远.基于NLAPSO-RBF的铁路货运量预测研究[J].计算机工程与应用,2013,49(22):253-257.(QIU Jiandong,JIANG Zhaoyuan.Research of railway freight volume prediction based on NLA-PSO-RBF[J].Computer Engineering and Applications,2013,49(22):253-257.(in Chinese))
[23]刘伟,王建平,刘长虹,等.基于粒子群寻优的支持向量机番茄红素含量预测[J].农业机械学报,2012,43(4):143-147.(LIU Wei,WANG Jianping,LIUChanghong,et al.Lycopene content prediction based on support vector machine with particle swarm optimization[J].Transactions of the Chinese Society for Agricultural Machinery,2012,43(4):143-147.(in Chinese))
[24]廖杰,王文圣,李跃清.支持向量机及其在径流预测中的应用[J].四川大学学报(工程科学版),2006,38(6):24-29.(LIAO Jie,WANG Wensheng,LI Yueqing.Support vector machine method and its application to prediction of runoff[J].Journal of Sichuan University(Engineering Sciences Edition),2006,38(6):24-28.(in Chinese))
[25]徐纬芳,刘成忠,顾延涛.基于PCA和支持向量机的径流预测应用研究[J].水资源与水工程学报,2010,21(6):72-75.(XU Weifang,LIU Chengzhong,GUYantao.Application research onrunoff forecasting based on PCA and support vector machine[J].Journal of Water Resources and Water Engineering,2010,21(6):72-75.(in Chinese))
[26]李佳,王黎,马光文,等.LS-SVM在径流预测中的应用[J].中国农村水利水电,2008(5):8-11.(LI Jia,WANG Li,MA Guangwen,et al.Application of LS-SVMin runoff forecasting[J].China Rural Water and Hydropower,2008(5):8-11.(in Chinese))
[27]周佩玲,陶小丽,傅忠谦,等.基于遗传算法的RBF网络及应用[J].信号处理,2001,17(3):269-273.(ZHOUPeiling,TAO Xiaoli,FU Zhongqian,et al.RBF network based on genetic algorithm and its application[J]Journal of Signal Processing,2001,17(3):269-273.(in Chinese))
[28]杨易华,罗伟伟.基于KPCA-PSO-SVM的径流预测研究[J].人民长江,2017,48(3):44-47.(YANGYihua,LUO Weiwei.Research on runoff forecast based on KPCA-PSO-SVM[J].Yangtze River,2017,48(3):44-47.(in Chinese))
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |