基于GA-灰色神经网络的沥青路面使用性能预测
|
摘要
为准确预估我国沥青路面使用性能的变化趋势,在传统灰色预测模型GM(1,1)的基础之上,提出了无偏GM(1,1)模型和滑动GM(1,1)模型,并通过遗传算法(GA)优化后的BP神经网络对传统、无偏与滑动GM(1,1)模型进行了组合,得到了兼顾灰色理论、遗传算法和BP神经网络优点的GA-灰色神经网络组合预测模型,并以具体实例验证了该模型的有效性。结果表明:传统GM(1,1)模型的平均相对误差为4.67%,无偏GM(1,1)模型的平均相对误差为4.64%,滑动GM(1,1)模型的平均相对误差为4.63%,灰色神经网络组合模型的平均相对误差为2.41%,而GA-灰色神经网络组合模型平均相对误差仅为0.54%,证明所提出的组合模型预测精度较高,误差较小,可作为制定路面养护计划的依据。
In order to accurately predict the variation trend of asphalt pavement performance in our country,the unbiased GM( 1,1) model and sliding GM( 1,1) model were proposed on the basis of the traditional gray forecasting model GM( 1,1)model.The traditional model,unbiased model and sliding GM( 1,1) model were combined with BP neural network optimized by genetic algorithm( GA),and a combined forecasting model of GA-grey neural network was obtained,which took into account the advantages of grey theory,genetic algorithm and BP neural network. Finally,the effectiveness of the proposed combination model was verified with specific examples. The results show that: the average relative error of traditional GM( 1,1) model is 4. 67%; the average relative error of unbiased GM( 1,1) model is 4. 64%; the average relative error of sliding GM( 1,1) model is 4.63%; the average relative error of gray neural network combination model is2.41%,while the average relative error of GA-gray neural network combination model is only 0.54%. Therefore,it is proved that the proposed combination model has higher prediction accuracy and smaller error,which can be used as a basis for pavement maintenance planning.
In order to accurately predict the variation trend of asphalt pavement performance in our country,the unbiased GM( 1,1) model and sliding GM( 1,1) model were proposed on the basis of the traditional gray forecasting model GM( 1,1)model.The traditional model,unbiased model and sliding GM( 1,1) model were combined with BP neural network optimized by genetic algorithm( GA),and a combined forecasting model of GA-grey neural network was obtained,which took into account the advantages of grey theory,genetic algorithm and BP neural network. Finally,the effectiveness of the proposed combination model was verified with specific examples. The results show that: the average relative error of traditional GM( 1,1) model is 4. 67%; the average relative error of unbiased GM( 1,1) model is 4. 64%; the average relative error of sliding GM( 1,1) model is 4.63%; the average relative error of gray neural network combination model is2.41%,while the average relative error of GA-gray neural network combination model is only 0.54%. Therefore,it is proved that the proposed combination model has higher prediction accuracy and smaller error,which can be used as a basis for pavement maintenance planning.
引文
[1]王朝辉,王丽君,白军华,等.基于时段的沥青路面预防性养护时机与对策一体优化研究[J].中国公路学报,2010,23(5):27-34.WANG Zhaohui,WANG Lijun,BAI Junhua,et al. Research on integration optimization of asphalt pavement preventive maintenance timing and countermeasures during period[J]. China Journal of Highway and Transport,2010,23(5):27-34.
[2]王笑风.沥青路面最佳预防性养护时机决策模型[J].长安大学学报(自然科学版),2011,31(3):7-12.WANG Xiaofeng.Model to decide optimal timing of asphalt pavement preventive maintenance[J]. Journal of Chang'an University(Natural Science Edition),2011,31(3):7-12.
[3]姚祖康.路面管理系统[M].北京:人民交通出版社,1993.YAO Zukang. Pavement Management System[M]. Beijing:China Communications Press,1993.
[4]杜二鹏,马松林,景海民.基于灰色系统理论的沥青路面使用性能预测[J].同济大学学报(自然科学版),2010,38(8):1161-1164.DU Erpeng,MA Songlin,JING Haimin. Asphalt pavement performance prediction model based on gray system theory[J]. Journal of Tongji University(Natural Science),2010,38(8):1161-1164.
[5]刘秀菊,郑彦军.基于灰色理论的沥青混凝土路面使用性能多指标预测方法研究[J].公路,2012(4):233-237.LIU Xiujv, ZHENG Yanjun. Multi-index prediction method of asphalt pavement performance based on gray theory[J]. Highway,2012(4):233-237.
[6]王朝阳,姚馨源,张肇红.基于灰色理论的高速公路路面使用状况衰变预测[J].公路,2012(12):77-80.WANG Chaoyang,YAO Xinyuan,ZHANG Zhaohong. Depression prediction of expressway pavement usage based on gray theory[J].Highway,2012(12):77-80.
[7]吴栋,田小革,董凡荣.基于灰色理论的沥青路面使用性能预测模型[J].中外公路,2017,37(5):77-80.WU Dong, TIAN Xiaoge, DONG Fanrong. Prediction model of asphalt pavement performance based on gray theory[J]. Chinese&Foreign Highway,2017,37(5):77-80.
[8]吉培荣,邹红波,张玉文.无偏灰色预测模型在电力系统负荷预测中的应用[J].三峡大学学报(自然科学版),2005,27(4):318-320.JI Peirong,ZOU Hongbo,ZHANG Yuwen. Application of unbiased grey forecasting model to load forecasting of power system[J].Journal of China Three Gorges University(Natural Sciences),2005,27(4):318-320.
[9]杨杰,翁文国.基于改进无偏灰色模型的燃气供气量的预测[J].清华大学学报(自然科学版),2014,54(2):145-148.YANG Jie, WENG Wenguo. Improved unbiased grey model for prediction of gas supplies[J]. Journal of Tsinghua University(Science&Technology),2014,54(2):145-148.
[10]张洪伟,连鹏,杨东.基于灰色模型方法的路面使用性能预测[J].公路,2015(12):34-38.ZHANG Hongwei, LIAN Peng, YANG Dong. Prediction of pavement performance index based on grey model[J]. Highway,2015(12):34-38.
[11]王艳丽,王秉纲.应用人工神经网络预测路面使用性能[J].西安公路交通大学学报,2001,21(1):42-45.WANG Yanli,WANG Binggang. Prediction of pavement performance using artificial neural network[J].Journal of Xi'an Highway University,2001,21(1):42-45.
[12]周文献,李明利,孙立军.基于改进神经网络的水泥路面使用性能预测模型[J].同济大学学报(自然科学版),2006,34(9):1191-1195.ZHOU Wenxian,LI Mingli,SUN Lijun. Portland cement concrete pavement performance prediction model based on improved neural network[J]. Journal of Tongji University(Natural Science),2006,34(9):1191-1195.
[13]周文献,孙立军.基于遗传神经网络的水泥路面使用性能预测[J].计算机应用,2005,25(增刊):280-281.ZHOU Wenxian,SUN Lijun. Prediction of serviceability of cement pavement based on genetic neural network[J].Computer Applications,2005,25(Sup):280-281.
[14]谭伟,陆百川,黄美灵.神经网络结合遗传算法用于航迹预测[J].重庆交通大学学报(自然科学版),2010,29(1):147-150.TAN Wei,LU Baichuan,HUANG Meiling. Track prediction based on neural networks and genetic algorithm[J]. Journal of Chongqing Jiaotong University(Natural Science),2010,29(1):147-150.
[15]周鹏飞,温胜强,康海贵.基于马尔可夫链与神经网络组合的路面使用性能预测[J].重庆交通大学学报(自然科学版),2012,31(5):997-1001.ZHOU Pengfei,WEN Shengqiang,KANG Haigui. Pavement perfor-mance combining forecasting based on BP neural network and Markov model[J]. Journal of Chongqing Jiaotong University(Natural Science),2012,31(5):997-1001.
[16]王昌衡,柏理想,邓珊.基于熵权组合预测与粗糙模糊集的沥青路面使用性能分析[J].公路交通科技,2016,33(4):12-19.WANG Changheng,BAI Lixiang,DENG Shan. Analysis of asphalt pavement performance based on entropy weight combination forecast and rough fuzzy set[J]. Journal of Highway and Transportation Research and Development,2016,33(4):12-19.
[17]宋俊敏,李明,范虎彪,等.基于BP神经网络的路面使用性能评价方法研究[J].公路,2008(12):140-144.SONG Junmin,LI Ming,FAN Hubiao,et al. An evaluation method of pavement performance based on BP neural network[J].Highway,2008(12):140-144.
[18]郭玲玲.基于遗传神经网络的路面使用性能评价预测[J].公路工程,2017,42(4):223-227.GUO Lingling. Pavement performance evaluation and prediction based on genetic neural network[J]. Highway Engineering,2017,42(4):223-227.
[2]王笑风.沥青路面最佳预防性养护时机决策模型[J].长安大学学报(自然科学版),2011,31(3):7-12.WANG Xiaofeng.Model to decide optimal timing of asphalt pavement preventive maintenance[J]. Journal of Chang'an University(Natural Science Edition),2011,31(3):7-12.
[3]姚祖康.路面管理系统[M].北京:人民交通出版社,1993.YAO Zukang. Pavement Management System[M]. Beijing:China Communications Press,1993.
[4]杜二鹏,马松林,景海民.基于灰色系统理论的沥青路面使用性能预测[J].同济大学学报(自然科学版),2010,38(8):1161-1164.DU Erpeng,MA Songlin,JING Haimin. Asphalt pavement performance prediction model based on gray system theory[J]. Journal of Tongji University(Natural Science),2010,38(8):1161-1164.
[5]刘秀菊,郑彦军.基于灰色理论的沥青混凝土路面使用性能多指标预测方法研究[J].公路,2012(4):233-237.LIU Xiujv, ZHENG Yanjun. Multi-index prediction method of asphalt pavement performance based on gray theory[J]. Highway,2012(4):233-237.
[6]王朝阳,姚馨源,张肇红.基于灰色理论的高速公路路面使用状况衰变预测[J].公路,2012(12):77-80.WANG Chaoyang,YAO Xinyuan,ZHANG Zhaohong. Depression prediction of expressway pavement usage based on gray theory[J].Highway,2012(12):77-80.
[7]吴栋,田小革,董凡荣.基于灰色理论的沥青路面使用性能预测模型[J].中外公路,2017,37(5):77-80.WU Dong, TIAN Xiaoge, DONG Fanrong. Prediction model of asphalt pavement performance based on gray theory[J]. Chinese&Foreign Highway,2017,37(5):77-80.
[8]吉培荣,邹红波,张玉文.无偏灰色预测模型在电力系统负荷预测中的应用[J].三峡大学学报(自然科学版),2005,27(4):318-320.JI Peirong,ZOU Hongbo,ZHANG Yuwen. Application of unbiased grey forecasting model to load forecasting of power system[J].Journal of China Three Gorges University(Natural Sciences),2005,27(4):318-320.
[9]杨杰,翁文国.基于改进无偏灰色模型的燃气供气量的预测[J].清华大学学报(自然科学版),2014,54(2):145-148.YANG Jie, WENG Wenguo. Improved unbiased grey model for prediction of gas supplies[J]. Journal of Tsinghua University(Science&Technology),2014,54(2):145-148.
[10]张洪伟,连鹏,杨东.基于灰色模型方法的路面使用性能预测[J].公路,2015(12):34-38.ZHANG Hongwei, LIAN Peng, YANG Dong. Prediction of pavement performance index based on grey model[J]. Highway,2015(12):34-38.
[11]王艳丽,王秉纲.应用人工神经网络预测路面使用性能[J].西安公路交通大学学报,2001,21(1):42-45.WANG Yanli,WANG Binggang. Prediction of pavement performance using artificial neural network[J].Journal of Xi'an Highway University,2001,21(1):42-45.
[12]周文献,李明利,孙立军.基于改进神经网络的水泥路面使用性能预测模型[J].同济大学学报(自然科学版),2006,34(9):1191-1195.ZHOU Wenxian,LI Mingli,SUN Lijun. Portland cement concrete pavement performance prediction model based on improved neural network[J]. Journal of Tongji University(Natural Science),2006,34(9):1191-1195.
[13]周文献,孙立军.基于遗传神经网络的水泥路面使用性能预测[J].计算机应用,2005,25(增刊):280-281.ZHOU Wenxian,SUN Lijun. Prediction of serviceability of cement pavement based on genetic neural network[J].Computer Applications,2005,25(Sup):280-281.
[14]谭伟,陆百川,黄美灵.神经网络结合遗传算法用于航迹预测[J].重庆交通大学学报(自然科学版),2010,29(1):147-150.TAN Wei,LU Baichuan,HUANG Meiling. Track prediction based on neural networks and genetic algorithm[J]. Journal of Chongqing Jiaotong University(Natural Science),2010,29(1):147-150.
[15]周鹏飞,温胜强,康海贵.基于马尔可夫链与神经网络组合的路面使用性能预测[J].重庆交通大学学报(自然科学版),2012,31(5):997-1001.ZHOU Pengfei,WEN Shengqiang,KANG Haigui. Pavement perfor-mance combining forecasting based on BP neural network and Markov model[J]. Journal of Chongqing Jiaotong University(Natural Science),2012,31(5):997-1001.
[16]王昌衡,柏理想,邓珊.基于熵权组合预测与粗糙模糊集的沥青路面使用性能分析[J].公路交通科技,2016,33(4):12-19.WANG Changheng,BAI Lixiang,DENG Shan. Analysis of asphalt pavement performance based on entropy weight combination forecast and rough fuzzy set[J]. Journal of Highway and Transportation Research and Development,2016,33(4):12-19.
[17]宋俊敏,李明,范虎彪,等.基于BP神经网络的路面使用性能评价方法研究[J].公路,2008(12):140-144.SONG Junmin,LI Ming,FAN Hubiao,et al. An evaluation method of pavement performance based on BP neural network[J].Highway,2008(12):140-144.
[18]郭玲玲.基于遗传神经网络的路面使用性能评价预测[J].公路工程,2017,42(4):223-227.GUO Lingling. Pavement performance evaluation and prediction based on genetic neural network[J]. Highway Engineering,2017,42(4):223-227.