智能方法在桩基工程中的应用
|
摘要
在现代化的房屋建设中,桩基由于其自身的优点而得到广泛使用。这与现代工程技术以及我国经济建设的发展是密不可分的。但在施工工程中,桩身易出现一些缺损,如断裂,缩径,离析等,使桩基本身无法达到预期的承载力或使结构产生不均匀沉降而导致工程事故的发生。因此,如何合理确定桩基的健康性已成为一个很重要的课题。
利用神经网络对采集的数据进行分析、预测是解决这一问题的有效方法之一。本文正是在分析了神经网络处理数据特点的基础上,针对RBF网络的设计和训练存在的问题,将多种智能方法融合,设计了一种改进的DNA进化计算,并利用改进的DNA进化计算优化RBF神经网络以解决上述问题,从而改善网络结构,提高网络的逼近能力和泛化能力,有效地进行桩基健康检测。
本文研究的主要内容包括以下几个方面:
(1)研究了神经网络、粗糙集理论、遗传算法、DNA计算等多种智能方法。深入地分析了各种智能方法的优缺点。
(2)研究了基于粗糙集预处理神经网络训练样本集。利用粗糙集可以简化信息空间表达维数的特点,将粗糙集作为神经网络的前置系统,化简训练样本集的信息结构,简化神经网络结构的复杂性。
(3)RBF神经网络优化的实质是一个多目标优化问题。本文设计了一种多目标的DNA进化计算来解决RBF神经网络的优化问题,该算法利用排序的Pareto支配集确定进化计算中的个体适应度,使用基于碱基对的交叉、变异、倒位、复制等进化算子进行遗传操作,快速找到Pareto最优解集,并从中选出网络结果最优的RBF网络。本文同时对给出算法的收敛性进行了证明。
(4)将基于DNA进化计算的RBF神经网络应用于桩基的健康检测中,经过实测数据与经网络预测数据的分析比较,说明该网络具有良好的检测效果。
论文研究结果表明,粗糙集预处理网络的训练样本集,简化了神经网络的结构;通过引入基于Pareto最优解集的DNA进化计算,有效地解决多目标优化问题,实现了RBF神经网络的优化。从仿真试验和实际应用的结果分析,与传统的RBF网络相比,基于DNA进化计算的RBF网络逼近能力和泛化能力都有了显著提高,预测效果更精确。
In the modern building construction, the pile foundation obtains the widespread using as a result of its own merits. It is inseparable with modern project technology and the economic development of our country. But in the construction work, the body of pile is easy to appear some damages, such as breaking, reducing, segregation and so on. For that reasons, pile foundation itself can not be able to achieve the anticipated supporting capacity or the structure having the differential settlement to cause the project accident the occurrence. So, how to determine the healthy of pile foundation reasonably has become a very important topic.
Analysis and forecast of gathering data using the neural network is an effective method to this problem. This thesis was precisely in the basis of analyzing the characteristic of the neural network processing data , in view of existence question of RBF network designing and training ,fused many kinds of intelligent methods, designed one kind of improvement of DNA evolution computation, and optimized the RBF neural network using the improvement of DNA evolution computation to solve the above problems, to improve network architecture, to enhance the network's approach ability and exude ability, to carry on the health examination of pile foundation effectively.
The major contributions are as follows:
(1)The thesis has studied the neural network, the rough sets theory, the genetic algorithm, and the DNA computation and so on many kinds of intelligent methods, and has thoroughly analyzed each kind of intelligent method's good and bad points.
(2)The thesis has studied pretreatment neural network training sample sets based on the rough sets. For rough sets has the characteristic of simplifying the information space expression dimension, set rough sets achievement neural network pretage system to simplify the information structure of training sample sets, and simplify the complexity of neural network.
(3) The essence of optimizing the RBF neural network is a multi-objective question. This paper designed one kind of multi-objective DNA evolution computation to solve the RBF neural network's optimized problem. In this algorithm, determine individual sufficiency in the evolutional computation using sorting Pareto control sets, do hereditable operation using evolution operator such as overlapping, variation, inversion, duplication, find the Pareto optimal solution sets fast, and select the most superior RBF network. At the same time this article has given the algorithm the astringency proof.
(4) Apply RBF Neural network based on DNA evolution computation for the pile foundation health examination. Through analyzing and comparing the measured data and the data forecasted by neural network, showed this network will have the good examination effect.
The research's results showed that in theoretical analysis, rough sets pretreat neural network's training sample sets, simplify the complexity of neural network. Introducing Pareto optimal solution sets to the DNA evolution computation, solve the multi-objective optimization problem effectively, and realize the RBF neural network's optimization. From the simulation and actual experimental results, compare with the traditional RBF network, the approached ability and exudes ability of RBF neural network based on DNA evolution computation have enhanced remarkably, and the forecast effect has been more precise.
利用神经网络对采集的数据进行分析、预测是解决这一问题的有效方法之一。本文正是在分析了神经网络处理数据特点的基础上,针对RBF网络的设计和训练存在的问题,将多种智能方法融合,设计了一种改进的DNA进化计算,并利用改进的DNA进化计算优化RBF神经网络以解决上述问题,从而改善网络结构,提高网络的逼近能力和泛化能力,有效地进行桩基健康检测。
本文研究的主要内容包括以下几个方面:
(1)研究了神经网络、粗糙集理论、遗传算法、DNA计算等多种智能方法。深入地分析了各种智能方法的优缺点。
(2)研究了基于粗糙集预处理神经网络训练样本集。利用粗糙集可以简化信息空间表达维数的特点,将粗糙集作为神经网络的前置系统,化简训练样本集的信息结构,简化神经网络结构的复杂性。
(3)RBF神经网络优化的实质是一个多目标优化问题。本文设计了一种多目标的DNA进化计算来解决RBF神经网络的优化问题,该算法利用排序的Pareto支配集确定进化计算中的个体适应度,使用基于碱基对的交叉、变异、倒位、复制等进化算子进行遗传操作,快速找到Pareto最优解集,并从中选出网络结果最优的RBF网络。本文同时对给出算法的收敛性进行了证明。
(4)将基于DNA进化计算的RBF神经网络应用于桩基的健康检测中,经过实测数据与经网络预测数据的分析比较,说明该网络具有良好的检测效果。
论文研究结果表明,粗糙集预处理网络的训练样本集,简化了神经网络的结构;通过引入基于Pareto最优解集的DNA进化计算,有效地解决多目标优化问题,实现了RBF神经网络的优化。从仿真试验和实际应用的结果分析,与传统的RBF网络相比,基于DNA进化计算的RBF网络逼近能力和泛化能力都有了显著提高,预测效果更精确。
In the modern building construction, the pile foundation obtains the widespread using as a result of its own merits. It is inseparable with modern project technology and the economic development of our country. But in the construction work, the body of pile is easy to appear some damages, such as breaking, reducing, segregation and so on. For that reasons, pile foundation itself can not be able to achieve the anticipated supporting capacity or the structure having the differential settlement to cause the project accident the occurrence. So, how to determine the healthy of pile foundation reasonably has become a very important topic.
Analysis and forecast of gathering data using the neural network is an effective method to this problem. This thesis was precisely in the basis of analyzing the characteristic of the neural network processing data , in view of existence question of RBF network designing and training ,fused many kinds of intelligent methods, designed one kind of improvement of DNA evolution computation, and optimized the RBF neural network using the improvement of DNA evolution computation to solve the above problems, to improve network architecture, to enhance the network's approach ability and exude ability, to carry on the health examination of pile foundation effectively.
The major contributions are as follows:
(1)The thesis has studied the neural network, the rough sets theory, the genetic algorithm, and the DNA computation and so on many kinds of intelligent methods, and has thoroughly analyzed each kind of intelligent method's good and bad points.
(2)The thesis has studied pretreatment neural network training sample sets based on the rough sets. For rough sets has the characteristic of simplifying the information space expression dimension, set rough sets achievement neural network pretage system to simplify the information structure of training sample sets, and simplify the complexity of neural network.
(3) The essence of optimizing the RBF neural network is a multi-objective question. This paper designed one kind of multi-objective DNA evolution computation to solve the RBF neural network's optimized problem. In this algorithm, determine individual sufficiency in the evolutional computation using sorting Pareto control sets, do hereditable operation using evolution operator such as overlapping, variation, inversion, duplication, find the Pareto optimal solution sets fast, and select the most superior RBF network. At the same time this article has given the algorithm the astringency proof.
(4) Apply RBF Neural network based on DNA evolution computation for the pile foundation health examination. Through analyzing and comparing the measured data and the data forecasted by neural network, showed this network will have the good examination effect.
The research's results showed that in theoretical analysis, rough sets pretreat neural network's training sample sets, simplify the complexity of neural network. Introducing Pareto optimal solution sets to the DNA evolution computation, solve the multi-objective optimization problem effectively, and realize the RBF neural network's optimization. From the simulation and actual experimental results, compare with the traditional RBF network, the approached ability and exudes ability of RBF neural network based on DNA evolution computation have enhanced remarkably, and the forecast effect has been more precise.
引文
[1]Simon H.Networks-A Comprehensive Foundation.Beijing:Tsinghua University Press,2001:122-125
[2]许香莲.浅谈基桩低应变反射波法检测桩长.山西建筑,2008.34(3):143
[3]Brady.RM.Optimization strategices gleaned,biological evolution.Nature,1985.317:804-806
[4]罗红英,刘进忙.遗传算法在目标优化分配中的应用.电光与控制,2008.15(3):18-20
[5]Ming-Jong Yao,Weng-Ming Chu.A genetic algorithm for determining optimal replenishment cycles to minimize maximum warehouse space requirements.Elsevier Science Ltd,2008.36(4):619-631
[6]楼顺天,施阳.基于MATLAB的系统分析与设计.西安:西安电子科技大学出版社,2000:70-89
[7]冯劲,高广运.人工神经网络在基桩低应变完整性检测中的应用.岩士工程技术,2005.19(1):5-8
[8]李敏成,杨劲虎,郭宇.基于改进粒子群BP算法的神经网络及应用.大众科技,2008.101(1):34-36
[9]Zhang Kun,Wang Zhi-zhong.The application of BP neural network improved with LM algorithm in surface EMG signal classification..Zhong Guo Yi Liao Qi Xie Za Zhi,2005.29(6):399-401
[10]苏建元.计算智能主要算法的比较与融合.中国电子科学研究院学报,2007.2(1):52-56
[11]LüBQ,Junichi Murata,Kotaro Hirasawa.A new learning method using prior information of neural networks.Science In China Series F-Information Sciences,2004.47(6):793-814
[12]项宝卫,凌塑勇.计算智能算法的研究现状.台州学院学报,2006.28(3):22-25
[13]李强,王彦平.遗传算法中变异对优化进程的影响分析.高技术通讯,2000.(8):72-74
[14]XIE Xian-zhong;YI Wei-jian.Application of hybrid genetic algotithm to structural dynamic inversion.Engineering Mechanics.2005.03:30-34
[15]刘庆凤,李敏.基于遗传算法的TSP问题优化求解.计算机与现代化,2008.150(2):43-45
[16]段海滨,王道波.一种快速全局优化的改进蚁群算法及仿真.信息与控制,2004.33(2):241-244
[17]钟珞,李桂青.基于神经网络的结构损伤状态模拟.小型微型计算机系统,1999.20(2):20-25
[18]钟珞,潘昊,陈杰等.神经网络在土木工程中的应用与展望.国外建材科技,1996.17(2):15-17
[19]L.Zhong,The Application of Neural Network in Lifetime Prediction of Concrete,Wuhan University of Technology,2002.17(1):20-25
[20]钟珞,饶文碧,邹承明.人工神经网络及其融合应用技术.北京:科学出版社,2007:20-25
[21]Pawlak Z.Routh Sets.Computer and Information sciences,1982.11(5):341-356.
[22]丁永生.计算智能-理论、技术与应用.北京:科学出版社,2004:288-292
[23]曾黄磷.粗集理论及其应用-关于数据推理的方法.重庆:重庆大学出版社,1996:144-150
[24]黎明,张化光.基于粗糙集的神经网络建模方法的研究.自动化学报,2002.28(1):27-33
[25]Holland,J.H.,Adaptation in Natural and Artificial Systems,AnnArbor:The University of Michigan Press,1975:268-290
[26]oanna Lis.Genetic algorithm with the dynamic probability of mutation in the classification problem.Patern Recognition Leters,1995.16(4):1311-1320
[27]Uday Kumar Chakrabo.A branching process model for genetic algorithms,Information Process Letters,1995.56(10):281-290.
[28]Dana Vrajitoru.Crossover improvement for the genetic algorithm in information Retrieval.Information Process and Management,1998.34(4):405-415
[29]Adleman L M.Molecular Computation of Solutions to Combinatorial Problems.Science.1994.266:1021-1024.
[30]王丽丽,杨光军.DNA遗传算法研究.福建电脑,2007.(2):33-34
[31]Maley C C.DNA computation:Theory,practice and prospects.Evolutionary Computation,1998.6(3):201-229
[32]Rocha A F,Rebello M P and Miura K.Toward a theory of molecular computing.Information Sciences,1998.106(5):123-157
[33]蒋宗华等.DNA计算研究的新进展.上海大学学报(自然科学版),2004.10(3):306-311
[34]KariL.DNA computing:arrival of biological mathematics.The Mathematical Intelligeneer,1997.19(2):9-22
[35]张文修,仇国芳.基于粗糙集的不确定决策.北京:清华大学出版社,2005:28-38
[36]Head T.Formal language theory and DNA:analysis of the generative capacity of recombinant behaviors.Bull Math Biol,1987.49:737-759
[37]Deninnghoff KL,Gatterdam RW.On the undecidability of splicing systems,Int J Computer Math,1989.27:133-145
[38]Paun G.On the splicing operation.Discrete Appl Math,1996.70:57-70
[39]Paun G.On the power of the splicing operation.Int J Computer Math,1995.59:27-35
[40]Fu TJ,Seeman NC.DNA double-crossover molecules.Biochemistry,1993.32:3211-3220
[41]Deb K,Pratap A,Agrawal S,etal.A fast and elitist multi objective genetic algorithm.IEEE Transaction on Evolutionary Computation,2002.6(2):182-197
[42]Laumanns M,etal.Combining Convergence and Diversity in Evolutionary Multiobjective Optimization.Evolutionary Computation,2002.10(3):263-282
[43]FonseeaC.M.and P.J.Fleming.An overview of evolutionary algorithms in multi-objective optimization.Evolutionary Computation,1995.3(1):1-16.
[44]郑金华,蒋浩,邝达等.额用擂台赛法则构造多目标Pareto最优解集的方法.软件学报,2007.18(6):1288-1297
[45]李云.非线性动力学系统的现代数学方法及其应用.北京:人民邮电出版社,2001:56-59
[46]魏平,熊伟清,王小权.DNA计算求解连续空间优化问题.计算机应用研究,2006.(1):151-153
[47]周小勇,叶银忠.基于小波多分辨率分析的故障检测方法.控制工程,2005.12(1):157-159
[48]李炎.应用低应变反射波法动力检测桩的完整性.施工技术,2005增刊:117-118
[2]许香莲.浅谈基桩低应变反射波法检测桩长.山西建筑,2008.34(3):143
[3]Brady.RM.Optimization strategices gleaned,biological evolution.Nature,1985.317:804-806
[4]罗红英,刘进忙.遗传算法在目标优化分配中的应用.电光与控制,2008.15(3):18-20
[5]Ming-Jong Yao,Weng-Ming Chu.A genetic algorithm for determining optimal replenishment cycles to minimize maximum warehouse space requirements.Elsevier Science Ltd,2008.36(4):619-631
[6]楼顺天,施阳.基于MATLAB的系统分析与设计.西安:西安电子科技大学出版社,2000:70-89
[7]冯劲,高广运.人工神经网络在基桩低应变完整性检测中的应用.岩士工程技术,2005.19(1):5-8
[8]李敏成,杨劲虎,郭宇.基于改进粒子群BP算法的神经网络及应用.大众科技,2008.101(1):34-36
[9]Zhang Kun,Wang Zhi-zhong.The application of BP neural network improved with LM algorithm in surface EMG signal classification..Zhong Guo Yi Liao Qi Xie Za Zhi,2005.29(6):399-401
[10]苏建元.计算智能主要算法的比较与融合.中国电子科学研究院学报,2007.2(1):52-56
[11]LüBQ,Junichi Murata,Kotaro Hirasawa.A new learning method using prior information of neural networks.Science In China Series F-Information Sciences,2004.47(6):793-814
[12]项宝卫,凌塑勇.计算智能算法的研究现状.台州学院学报,2006.28(3):22-25
[13]李强,王彦平.遗传算法中变异对优化进程的影响分析.高技术通讯,2000.(8):72-74
[14]XIE Xian-zhong;YI Wei-jian.Application of hybrid genetic algotithm to structural dynamic inversion.Engineering Mechanics.2005.03:30-34
[15]刘庆凤,李敏.基于遗传算法的TSP问题优化求解.计算机与现代化,2008.150(2):43-45
[16]段海滨,王道波.一种快速全局优化的改进蚁群算法及仿真.信息与控制,2004.33(2):241-244
[17]钟珞,李桂青.基于神经网络的结构损伤状态模拟.小型微型计算机系统,1999.20(2):20-25
[18]钟珞,潘昊,陈杰等.神经网络在土木工程中的应用与展望.国外建材科技,1996.17(2):15-17
[19]L.Zhong,The Application of Neural Network in Lifetime Prediction of Concrete,Wuhan University of Technology,2002.17(1):20-25
[20]钟珞,饶文碧,邹承明.人工神经网络及其融合应用技术.北京:科学出版社,2007:20-25
[21]Pawlak Z.Routh Sets.Computer and Information sciences,1982.11(5):341-356.
[22]丁永生.计算智能-理论、技术与应用.北京:科学出版社,2004:288-292
[23]曾黄磷.粗集理论及其应用-关于数据推理的方法.重庆:重庆大学出版社,1996:144-150
[24]黎明,张化光.基于粗糙集的神经网络建模方法的研究.自动化学报,2002.28(1):27-33
[25]Holland,J.H.,Adaptation in Natural and Artificial Systems,AnnArbor:The University of Michigan Press,1975:268-290
[26]oanna Lis.Genetic algorithm with the dynamic probability of mutation in the classification problem.Patern Recognition Leters,1995.16(4):1311-1320
[27]Uday Kumar Chakrabo.A branching process model for genetic algorithms,Information Process Letters,1995.56(10):281-290.
[28]Dana Vrajitoru.Crossover improvement for the genetic algorithm in information Retrieval.Information Process and Management,1998.34(4):405-415
[29]Adleman L M.Molecular Computation of Solutions to Combinatorial Problems.Science.1994.266:1021-1024.
[30]王丽丽,杨光军.DNA遗传算法研究.福建电脑,2007.(2):33-34
[31]Maley C C.DNA computation:Theory,practice and prospects.Evolutionary Computation,1998.6(3):201-229
[32]Rocha A F,Rebello M P and Miura K.Toward a theory of molecular computing.Information Sciences,1998.106(5):123-157
[33]蒋宗华等.DNA计算研究的新进展.上海大学学报(自然科学版),2004.10(3):306-311
[34]KariL.DNA computing:arrival of biological mathematics.The Mathematical Intelligeneer,1997.19(2):9-22
[35]张文修,仇国芳.基于粗糙集的不确定决策.北京:清华大学出版社,2005:28-38
[36]Head T.Formal language theory and DNA:analysis of the generative capacity of recombinant behaviors.Bull Math Biol,1987.49:737-759
[37]Deninnghoff KL,Gatterdam RW.On the undecidability of splicing systems,Int J Computer Math,1989.27:133-145
[38]Paun G.On the splicing operation.Discrete Appl Math,1996.70:57-70
[39]Paun G.On the power of the splicing operation.Int J Computer Math,1995.59:27-35
[40]Fu TJ,Seeman NC.DNA double-crossover molecules.Biochemistry,1993.32:3211-3220
[41]Deb K,Pratap A,Agrawal S,etal.A fast and elitist multi objective genetic algorithm.IEEE Transaction on Evolutionary Computation,2002.6(2):182-197
[42]Laumanns M,etal.Combining Convergence and Diversity in Evolutionary Multiobjective Optimization.Evolutionary Computation,2002.10(3):263-282
[43]FonseeaC.M.and P.J.Fleming.An overview of evolutionary algorithms in multi-objective optimization.Evolutionary Computation,1995.3(1):1-16.
[44]郑金华,蒋浩,邝达等.额用擂台赛法则构造多目标Pareto最优解集的方法.软件学报,2007.18(6):1288-1297
[45]李云.非线性动力学系统的现代数学方法及其应用.北京:人民邮电出版社,2001:56-59
[46]魏平,熊伟清,王小权.DNA计算求解连续空间优化问题.计算机应用研究,2006.(1):151-153
[47]周小勇,叶银忠.基于小波多分辨率分析的故障检测方法.控制工程,2005.12(1):157-159
[48]李炎.应用低应变反射波法动力检测桩的完整性.施工技术,2005增刊:117-118