遗传BP神经网络在泥石流危险性评价中的应用
|
摘要
泥石流危险性的评价是地质灾害预测的重要研究课题之一,根据泥石流危险性评价因子,建立了遗传BP神经网络评价模型。模型利用BP神经网络的函数逼近能力,模拟泥石流某些主要评价指标与危险程度之间的非线性函数关系,实现对泥石流危险性的评价。为克服BP神经网络收敛慢、易陷入局部极小、泛化能力差等缺陷,引入遗传算法和对比分析方法优化BP评价网络的权值、阈值和网络结构。实验证明,采用所述方法优化后的BP神经网络的拟合精度、准确度、效率大幅提高,泛化能力也得到增强,该方法可作为解决泥石流危险性评价问题的一种新思路。
The risk assessment of debris flow is an important research field of geological disaster prediction.According to risk as-sessment indexes of debris flow,this paper constructs genetic BP Neural Network assessment model.The model utilizes function approximation capability of BP Neural Network to simulate nonlinear relation between some primary assessment indexes and risk of debris flow,and finally realizes risk assessment of debris flow.In order to overcome the shortcoming of BP Neural Network,such as slow convergence,easily getting into local dinky value and low generalization ability,the paper introduces genetic algo-rithm and comparative analysis method to optimize the weight,threshold and network structure of BP Assessment Network.Experiment shows that the precision,accuracy and efficiency of simulation have been greatly improved,and generalization ability has been enforced after optimizing by adopting the method.Therefore,this method should be a new way to solve risk assessment of debris flow.
The risk assessment of debris flow is an important research field of geological disaster prediction.According to risk as-sessment indexes of debris flow,this paper constructs genetic BP Neural Network assessment model.The model utilizes function approximation capability of BP Neural Network to simulate nonlinear relation between some primary assessment indexes and risk of debris flow,and finally realizes risk assessment of debris flow.In order to overcome the shortcoming of BP Neural Network,such as slow convergence,easily getting into local dinky value and low generalization ability,the paper introduces genetic algo-rithm and comparative analysis method to optimize the weight,threshold and network structure of BP Assessment Network.Experiment shows that the precision,accuracy and efficiency of simulation have been greatly improved,and generalization ability has been enforced after optimizing by adopting the method.Therefore,this method should be a new way to solve risk assessment of debris flow.
引文
[1]谭万沛,王成华.暴雨泥石流滑坡的区域预测与预报[M].成都:四川科学技术出版社,1994:73-80.
[2]Hürlimann M,Copons R,Altimir J.Detailed debris flow hazard as-sessment in Andorra:A multidisciplinary approach[J].Geomorphology,2006,78(3/4):359-372.
[3]Chen Chien-chih,Tseng Chih-yuan,Dong Jia-jyun.New entropy-based method for variables selection and its application to the de-bris-flow hazard assessment[J].Engineering Geology,2007,94(1/2):19-26.
[4]李阔,唐川.泥石流危险范围预测模型及在昆明东川城区的应用[J].地球科学与环境学,2006,28(4):69-72.
[5]周春花,唐川,铁永波.金沙江流域云南段泥石流危险度评价[J].中国水土保持科学,2006,17(4):79-83.
[6]铁永波,唐川.层次分析法在单沟泥石流危险度评价中的应用[J].中国地质灾害与防治学报,2006.
[7]Liang Yawei.Fuzzy knowledge based approach in threat assess-ment[J].Journal of Information and Computational Science,2007,4(2):587-596.
[8]王学武,石豫川.多级模糊综合评判方法在泥石流评价中的应用[J].灾害学,2004,19(2):2-6.
[9]潘晖.多级模糊模式识别模型在地质环境评价中的应用[J].西部探矿工程,2007(8):83-85.
[10]陈晓利,祁生文,叶洪.基于GIS的地震泥石流危险性的模糊综合评价研究[J].北京大学学报:自然科学版,2007(2):52-53.
[11]Song Shujun,Zhang Baolei,Feng Wenlan,et al.Using fuzzy rela-tions and GIS method to evaluate debris flow hazard[J].Wuhan University Journal of Natural Sciences,2006,11(4):875-881.
[12]高士平,杜丽,王瑞,等.基于3S技术的河北省泥石流灾害预测模型研究[J].地理与地理信息科学,2007,23(4):93-96.
[13]Chang Tung chueng,Chao Ru jen.Application of back-propagation networks in debris flow prediction[J].Engineering Geology,2006,85(3/4):270-280.
[14]Liu Y,Guo H C,Zou R,et al.Neural network modeling for re-gional hazard assessment of debris flow in Lake Qionghai Water-shed[J].Environmental Geology,2006,49(7):968-976.
[15]Chang Tung-chiung,Chien Yue-hone.The application of genetic algorithm in debris flows prediction[J].Environmental Geology,2007,53(2):339-347.
[16]曹剑峰.改进BP神经网络在地下水环境质量评价中的应用[J].水利水电科技进展,2006,26(3):21-23.
[17]刘希林,唐川.泥石流危险性评价[M].北京:科学出版社,2004.
[18]叶四桥.改进BP-NN在三峡库区滑坡稳定性分析中的应用[J].重庆建筑大学学报,2006(6):52-53.
[19]李端有.茅坪滑坡位移预测的BP网络方法应用研究[J].长江科学院院报,2005(6):65-69.
[20]Meng Xianyao,Han Xinjie,Xu Qingyang.BP network optimized with genetic algorithm and apply on the fault diagnose of com-plex equipment[C]//2007IEEE International Conference on Control and Automation(ICCA2007),2008:1630-1633.
[21]蒯圣龙,张红珍,李云辉.基于遗传神经网络的环境质量评价[J].沈阳大学学报,2006,18(2):43-45.
[22]李钰,孔凡国.基于模糊理论和遗传算法的神经网络权值优化[J].上海工程技术大学学报,2007,21(2):130-133.
[2]Hürlimann M,Copons R,Altimir J.Detailed debris flow hazard as-sessment in Andorra:A multidisciplinary approach[J].Geomorphology,2006,78(3/4):359-372.
[3]Chen Chien-chih,Tseng Chih-yuan,Dong Jia-jyun.New entropy-based method for variables selection and its application to the de-bris-flow hazard assessment[J].Engineering Geology,2007,94(1/2):19-26.
[4]李阔,唐川.泥石流危险范围预测模型及在昆明东川城区的应用[J].地球科学与环境学,2006,28(4):69-72.
[5]周春花,唐川,铁永波.金沙江流域云南段泥石流危险度评价[J].中国水土保持科学,2006,17(4):79-83.
[6]铁永波,唐川.层次分析法在单沟泥石流危险度评价中的应用[J].中国地质灾害与防治学报,2006.
[7]Liang Yawei.Fuzzy knowledge based approach in threat assess-ment[J].Journal of Information and Computational Science,2007,4(2):587-596.
[8]王学武,石豫川.多级模糊综合评判方法在泥石流评价中的应用[J].灾害学,2004,19(2):2-6.
[9]潘晖.多级模糊模式识别模型在地质环境评价中的应用[J].西部探矿工程,2007(8):83-85.
[10]陈晓利,祁生文,叶洪.基于GIS的地震泥石流危险性的模糊综合评价研究[J].北京大学学报:自然科学版,2007(2):52-53.
[11]Song Shujun,Zhang Baolei,Feng Wenlan,et al.Using fuzzy rela-tions and GIS method to evaluate debris flow hazard[J].Wuhan University Journal of Natural Sciences,2006,11(4):875-881.
[12]高士平,杜丽,王瑞,等.基于3S技术的河北省泥石流灾害预测模型研究[J].地理与地理信息科学,2007,23(4):93-96.
[13]Chang Tung chueng,Chao Ru jen.Application of back-propagation networks in debris flow prediction[J].Engineering Geology,2006,85(3/4):270-280.
[14]Liu Y,Guo H C,Zou R,et al.Neural network modeling for re-gional hazard assessment of debris flow in Lake Qionghai Water-shed[J].Environmental Geology,2006,49(7):968-976.
[15]Chang Tung-chiung,Chien Yue-hone.The application of genetic algorithm in debris flows prediction[J].Environmental Geology,2007,53(2):339-347.
[16]曹剑峰.改进BP神经网络在地下水环境质量评价中的应用[J].水利水电科技进展,2006,26(3):21-23.
[17]刘希林,唐川.泥石流危险性评价[M].北京:科学出版社,2004.
[18]叶四桥.改进BP-NN在三峡库区滑坡稳定性分析中的应用[J].重庆建筑大学学报,2006(6):52-53.
[19]李端有.茅坪滑坡位移预测的BP网络方法应用研究[J].长江科学院院报,2005(6):65-69.
[20]Meng Xianyao,Han Xinjie,Xu Qingyang.BP network optimized with genetic algorithm and apply on the fault diagnose of com-plex equipment[C]//2007IEEE International Conference on Control and Automation(ICCA2007),2008:1630-1633.
[21]蒯圣龙,张红珍,李云辉.基于遗传神经网络的环境质量评价[J].沈阳大学学报,2006,18(2):43-45.
[22]李钰,孔凡国.基于模糊理论和遗传算法的神经网络权值优化[J].上海工程技术大学学报,2007,21(2):130-133.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心