结构耐久性评估的软计算模型及应用
|
摘要
将层次分析等理论更快速方便地应用于结构评估工程实践,研究基于现有理论的自动化、智能评估方法.借助Matlab模糊数学、神经网络工具箱,采用线性映射的层次分析方法完成桥梁耐久性等级评估.FIS结构和BP模型评估结果的对比表明:受隶属函数限制,FIS结构评估结果较粗糙,但由于模糊关系的特性,处理复杂输入输出关系时效果较好;而当样本数据集在超空间中线性可分时,神经网络对已有数据的拟合精度更高,但只能处理与训练样本同构的评估数据.由此证明:利用Matlab软计算模型实现桥梁工作性能的自动化智能评估是可行的.
In order to conveniently apply the hierarchical analysis theory in structure evaluation,this study investigates the automatic and intelligent assessment methods based on existing theories.Using Matlab fuzzy mathematics and mathematical toolbox in neural network,the study conducts an evaluation on bridge's durability with the method of linear mapping and AHP-FCE.Comparative analysis on FIS structure and BP model shows that due to the restriction by membership function,the evaluation results of FIS structure are not accurate,however,because of the characteristics of fuzzy relation,the FIS structure can better adapt to a more complex input/output mapping.When the sample data set can be linearly categorized in super space,the fitting accuracy of existing data using BP neural network is better,however,it can only process the evaluation data which are homogeneous with training sample data.The study proves that it is feasible to use soft calculation model of Matlab to automatically and intelligently evaluate the bridge work performance.
In order to conveniently apply the hierarchical analysis theory in structure evaluation,this study investigates the automatic and intelligent assessment methods based on existing theories.Using Matlab fuzzy mathematics and mathematical toolbox in neural network,the study conducts an evaluation on bridge's durability with the method of linear mapping and AHP-FCE.Comparative analysis on FIS structure and BP model shows that due to the restriction by membership function,the evaluation results of FIS structure are not accurate,however,because of the characteristics of fuzzy relation,the FIS structure can better adapt to a more complex input/output mapping.When the sample data set can be linearly categorized in super space,the fitting accuracy of existing data using BP neural network is better,however,it can only process the evaluation data which are homogeneous with training sample data.The study proves that it is feasible to use soft calculation model of Matlab to automatically and intelligently evaluate the bridge work performance.
引文
[1]赵慧洁,葛文谦,李旭东.最小误差准则与脉冲耦合神经网络的裂缝检测[J].仪器仪表学报,2012,33(3):637-642.Zhao Huijie,Ge Wenqian,Li Xudong.Detection of crack defect based onminimum error and pulse coupled neural networks[J].Chinese Journalof Scientific Instrument,2012,33(3):637-642.
[2]赵钊,郭恩栋.基于人工神经网络的城市桥梁震害评估方法[J].世界地震工程,2011,27(4):7-12.Zhao Zhao,Guo Endong,etc.Seismic damage evaluation method ofurban bridge based on artificial neural network[J].World EarthquakeEngineering,2011,27(4):7-12.
[3]李书韬,程进.模糊层次分析方法在大跨度桥梁施工期风险评估中的应用[J].结构工程师,2011,27(5):159-162.Li Shutao,Cheng Jin.Ahp-fce method for construction period riskevaluation of long-span bridges[J].Structural Engineers,2011,27(5):159-162.
[4]胡小鹏.桥梁施工状况评估的小波神经网络模型[J].混凝土,2011,10(8):70-72.Hu Xiaopeng.Evaluation for bridge construction state based on the wavelet neural netw ork[J].Concrete,2011,10(8):70-72.
[5]向木生,陈健,刘瑞.基于BP神经网络的桥梁技术状态评估[J].交通科技,2011,10(5):41-44.Xiang Musheng,Chen Jian,Liu Rui.Assessment of the bridge technicalstate based on the BP neural network[J].Transportation Science&Technology,2011,10(5):41-44.
[6]徐家云,何晓鸣,张俊,等.模糊理论在桥梁评估中的应用[J].武汉:武汉理工大学学报,2003,25(7):38-41.Xu Jiayun,He Xiaoming,Zhang Jun,et al.The coefficient calculationon load transverse distribution of the two-way curved archbridge[J].Wuhan:Journal Of Wuhan University Of Technology,2003,25(7):38-41.
[7]楼顺天,胡昌华,张伟.基于Matlab的系统分析与设计[M].西安:西安电子科技大学出版社,2011.Lou Shuntian,Hu Canghua,Zhang Wei.System analysis and designbased on Matlab[M].Xi'an:Xi'an Electronic and Science Universitypress,2011.
[8]郭嗣琮.工程应用软计算[M].徐州:中国矿业大学出版社,2009.Guo Sizong.Engineering application of soft computing[M].Xuzhou:China University of Mining and Technology Press,2009.
[9]于红志,刘凤鑫,邹开其.改进的模糊BP神经网络及在犯罪预测中的应用[J].辽宁工程技术大学学报:自然科学版,2012,31(2):244-247.Yu Hongzhi,Liu Fengxin,Zou Kaiqi.Improved fuzzy BP neuralnetwork and its application in crime prediction[J].Journal of LiaoningTechnical University:Natural Science,2012,31(2):244-247.
[10]单锐,王淑花,李玲玲,等.基于ARIMA、BP神经网络与GM的组合模型[J].辽宁工程技术大学学报:自然科学版,2012,31(1):118-122.Shan Rui,Wang Shuhua,Li Lingling,et al.Combination model based onARIMA,BP neural network and GM[J].Journal of Liaoning TechnicalUniversity:Natural Science,2012,31(1):118-122.
[2]赵钊,郭恩栋.基于人工神经网络的城市桥梁震害评估方法[J].世界地震工程,2011,27(4):7-12.Zhao Zhao,Guo Endong,etc.Seismic damage evaluation method ofurban bridge based on artificial neural network[J].World EarthquakeEngineering,2011,27(4):7-12.
[3]李书韬,程进.模糊层次分析方法在大跨度桥梁施工期风险评估中的应用[J].结构工程师,2011,27(5):159-162.Li Shutao,Cheng Jin.Ahp-fce method for construction period riskevaluation of long-span bridges[J].Structural Engineers,2011,27(5):159-162.
[4]胡小鹏.桥梁施工状况评估的小波神经网络模型[J].混凝土,2011,10(8):70-72.Hu Xiaopeng.Evaluation for bridge construction state based on the wavelet neural netw ork[J].Concrete,2011,10(8):70-72.
[5]向木生,陈健,刘瑞.基于BP神经网络的桥梁技术状态评估[J].交通科技,2011,10(5):41-44.Xiang Musheng,Chen Jian,Liu Rui.Assessment of the bridge technicalstate based on the BP neural network[J].Transportation Science&Technology,2011,10(5):41-44.
[6]徐家云,何晓鸣,张俊,等.模糊理论在桥梁评估中的应用[J].武汉:武汉理工大学学报,2003,25(7):38-41.Xu Jiayun,He Xiaoming,Zhang Jun,et al.The coefficient calculationon load transverse distribution of the two-way curved archbridge[J].Wuhan:Journal Of Wuhan University Of Technology,2003,25(7):38-41.
[7]楼顺天,胡昌华,张伟.基于Matlab的系统分析与设计[M].西安:西安电子科技大学出版社,2011.Lou Shuntian,Hu Canghua,Zhang Wei.System analysis and designbased on Matlab[M].Xi'an:Xi'an Electronic and Science Universitypress,2011.
[8]郭嗣琮.工程应用软计算[M].徐州:中国矿业大学出版社,2009.Guo Sizong.Engineering application of soft computing[M].Xuzhou:China University of Mining and Technology Press,2009.
[9]于红志,刘凤鑫,邹开其.改进的模糊BP神经网络及在犯罪预测中的应用[J].辽宁工程技术大学学报:自然科学版,2012,31(2):244-247.Yu Hongzhi,Liu Fengxin,Zou Kaiqi.Improved fuzzy BP neuralnetwork and its application in crime prediction[J].Journal of LiaoningTechnical University:Natural Science,2012,31(2):244-247.
[10]单锐,王淑花,李玲玲,等.基于ARIMA、BP神经网络与GM的组合模型[J].辽宁工程技术大学学报:自然科学版,2012,31(1):118-122.Shan Rui,Wang Shuhua,Li Lingling,et al.Combination model based onARIMA,BP neural network and GM[J].Journal of Liaoning TechnicalUniversity:Natural Science,2012,31(1):118-122.
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