PCA-RBF神经网络模型在桥梁变形预测中的应用分析
|
摘要
在由多种因素导致的桥梁变形进行变形预测时,针对大多神经网络预测方法具有局部最优等局限性,以及高维度的影响因子之间具有很强的相关性和信息重叠性等问题,该文提出基于主成分分析(PCA)的径向基函数(RBF)神经网络来进行桥梁变形预测,并和直接采用RBF神经网络的预测结果进行了对比。实例分析证明:两种方法的训练误差都在10~(-15)mm级,均能很好地训练样本,其中基于主成分分析的径向基函数神经网络误差更小,提高了预测精度,这对变形监测中分析主要的影响因子从而建立预测模型具有参考意义。
When predicting bridge deformation caused by many factors,aiming at the limitations of most neural network prediction methods such as local optimum,and the strong correlation and information overlap between high-dimensional influencing factors,this paper proposes a radial basis function(RBF) neural network based on principal component analysis(PCA) to predict bridge deformation,and compares the prediction results with RBF neural network directly. The example shows that the training errors of the two methods are all at 10~(-15) mm level,and both of them all can train samples well. Among them,the error of RBF neural network based on principal component analysis is smaller,the predicted accuracy is improved. It has reference significance for analysing main influencing factors in deformation monitoring and establishing prediction model.
When predicting bridge deformation caused by many factors,aiming at the limitations of most neural network prediction methods such as local optimum,and the strong correlation and information overlap between high-dimensional influencing factors,this paper proposes a radial basis function(RBF) neural network based on principal component analysis(PCA) to predict bridge deformation,and compares the prediction results with RBF neural network directly. The example shows that the training errors of the two methods are all at 10~(-15) mm level,and both of them all can train samples well. Among them,the error of RBF neural network based on principal component analysis is smaller,the predicted accuracy is improved. It has reference significance for analysing main influencing factors in deformation monitoring and establishing prediction model.
引文
[1] 栾元重,栾亨宣,马德鹏,等.桥梁变形数据小波去噪与混沌预测.大地测量与动力学,2013,33(5):133～135,139
[2] 栾元重,栾亨宣,李伟,等.桥梁变形监测数据小波去噪与Kalman滤波研究.大地测量与地球动力学,2015,35(6):1041～1045
[3] 蒋斌松,贺立军,贺永念.深部岩体变形的混沌预测方法.岩土力学与工程学报,2005,24(16):2934～2940
[4] 肖桂元,刘立龙.动态模糊神经网络在变形预测中的应用.桂林理工大学学报,2011,31(03):395～398
[5] 沈月千,黄腾,陈喜凤,等.逐步回归分析在桥梁挠度变形预测中的应用.工程勘察,2012,40(07):79～83
[6] 李勇,栾元重,张善廷,等.基于自适应Kalman滤波的高铁桥梁变形预测应用研究.测绘与空间地理信息,2016,39(08):200～203
[7] 桑慧茹,王丽学,陈韶明,等.基于主成分分析的RBF神经网络在需水预测中的应用.水电能源科学,2017,35(07):58～61
[8] 吴杰,余腾,郭冰,等.小波神经网络在桥梁变形中的应用.测绘科学,2017,42(11):74～79
[9] 岳东杰,李立瑞,郭培闪.主成分分析在GPS高程拟合中的应用.河海大学学报(自然科学版),2011,39(03):323～326
[10] 薛小杰,黄强,惠泱河,等.基于径向基函数神经网络与改进遗传算法的黄河流域需水预测.水土保持学报,2002,16(3):83～85,97
[11] 朱明星,张德龙.RBF网络基函数中心选取算法的研究.安徽大学学报:自然科学版,2000,24(1):73～78
[2] 栾元重,栾亨宣,李伟,等.桥梁变形监测数据小波去噪与Kalman滤波研究.大地测量与地球动力学,2015,35(6):1041～1045
[3] 蒋斌松,贺立军,贺永念.深部岩体变形的混沌预测方法.岩土力学与工程学报,2005,24(16):2934～2940
[4] 肖桂元,刘立龙.动态模糊神经网络在变形预测中的应用.桂林理工大学学报,2011,31(03):395～398
[5] 沈月千,黄腾,陈喜凤,等.逐步回归分析在桥梁挠度变形预测中的应用.工程勘察,2012,40(07):79～83
[6] 李勇,栾元重,张善廷,等.基于自适应Kalman滤波的高铁桥梁变形预测应用研究.测绘与空间地理信息,2016,39(08):200～203
[7] 桑慧茹,王丽学,陈韶明,等.基于主成分分析的RBF神经网络在需水预测中的应用.水电能源科学,2017,35(07):58～61
[8] 吴杰,余腾,郭冰,等.小波神经网络在桥梁变形中的应用.测绘科学,2017,42(11):74～79
[9] 岳东杰,李立瑞,郭培闪.主成分分析在GPS高程拟合中的应用.河海大学学报(自然科学版),2011,39(03):323～326
[10] 薛小杰,黄强,惠泱河,等.基于径向基函数神经网络与改进遗传算法的黄河流域需水预测.水土保持学报,2002,16(3):83～85,97
[11] 朱明星,张德龙.RBF网络基函数中心选取算法的研究.安徽大学学报:自然科学版,2000,24(1):73～78