基于BP神经网络的大坝新多测点位移模型
|
摘要
大坝位移监测资料分析大多以单一测点得到的数据建立模型,这种单测点模型无法反映大坝作为一个整体各点位移之间的相互联系,也就不能真实地反映坝体的整体安全性态。为此,将多个同源测点联合考虑,通过测点之间的相关性对目标测点建模,再通过该模型推求未布置测点位置的大坝位移值,为推求大坝整体单向位移创造条件。经实例验证,这种新模型在对目标测点的位移预测和补全缺失数据两方面相对常规的单测点模型效果更佳,而且在对未知点的位移值进行预测方面也具有良好效果。
Aiming at the problem of that most of the analyses on dam deformation monitoring data based on establishing model with the data obtained from single measuring point, which cannot fully reflect the correlation among the displacements of all the points of the dam body, and then cannot really reflect the integral safety behavior of dam body as it is an integrity, several homologous measuring points are jointly considered and the target measuring points are modeled through the correlation among all the measuring points, and then the displacement values of those locations without measuring points are derived through this model, so as to create the condition for deriving the integral unidirectional displacement of the dam. Through the verification of the actual case concerned, the effect of this kind of new model is better in the aspects of predicting displacement and completing missing data if compared with those from the conventional single measuring point model, while it has better effect in the aspect of predicting the displacement value of the location without measuring point as well.
Aiming at the problem of that most of the analyses on dam deformation monitoring data based on establishing model with the data obtained from single measuring point, which cannot fully reflect the correlation among the displacements of all the points of the dam body, and then cannot really reflect the integral safety behavior of dam body as it is an integrity, several homologous measuring points are jointly considered and the target measuring points are modeled through the correlation among all the measuring points, and then the displacement values of those locations without measuring points are derived through this model, so as to create the condition for deriving the integral unidirectional displacement of the dam. Through the verification of the actual case concerned, the effect of this kind of new model is better in the aspects of predicting displacement and completing missing data if compared with those from the conventional single measuring point model, while it has better effect in the aspect of predicting the displacement value of the location without measuring point as well.
引文
[1] 吴中如.水工建筑物安全监控理论及其应用[M].北京,高等教育出版社,2003.
[2] 冯宇强,陈五一,陶丛丛,等.基于遗传算法的岭回归模型在大坝安全监测中的应用[J].水电能源科学,2010,28(10):51- 52.
[3] 李红祥, 岳东杰, 李立瑞. 基于主成分回归的大坝位移模型[J]. 水电与抽水蓄能, 2008, 32(5):61- 64.
[4] 赵斌,吴中如,张爱玲.BP模型在大坝安全监测预报中的应用[J].大坝观测与土工测试,1999(6):1- 4.
[5] 陈维江,马震岳,董毓新.大坝安全监测遗传回归模型研究及应用[J].水电能源科学,2002,20(2):39- 42.
[6] 张帆. 基于神经网络的大坝安全监控模型研究[D].南京:东南大学,2016.
[7] 齐银峰.BP神经网络在大坝变形分析中的应用及改进[D].昆明:昆明理工大学,2017.
[8] 杨超.改进的粒子群优化BP神经网络在大坝变形预测中的应用[D].抚州:东华理工大学,2016.
[9] 吴中如,陈波.大坝变形监控模型发展回眸[J].现代测绘,2016,39(5):1- 3.
[10] 赵卿. 大坝变形分析多测点统计模型的应用研究[D].武汉:武汉大学,2010.
[11] 顾冲时,吴中如.混凝土坝空间位移场的确定性模型反演分析法[J].河海大学学报,1994(2):82- 87.
[12] 安慧琳,李艳玲,曾贝佳,钟为.重力坝挠度多测点空间模型研究[J].水电能源科学,2016,34(11):77- 81.
[13] 黄铭,葛修润,刘俊.大坝安全监测的多测点位移向量模型[J].上海交通大学学报,2001(4):514- 517.
[14] 李端有,周元春,甘孝清.混凝土拱坝多测点确定性位移监控模型研究[J].水利学报,2011,42(8):981- 985,994.
[15] HE JP,TU YY,SHI YQ,et al. Model of diagnosing abnormal behavior of dam based on multi-monitoring points and bayes fusion theory[J]. Journal of Yangtze River Scientific Research Institute, 2012, 29(10):63- 67.
[16] 李端有,周元春.BP网络在大坝变形空间多测点监测模型中的应用[J].长江科学院院报,2005(6):7- 8.
[17] 柴丽莎,戚丹,吴浩.多测点多方向BP网络模型在大坝变形监测中的应用[J].水电能源科学,2014,32(3):94- 97.
[18] 黄大伟,刘斌,戴吾蛟.基于神经网络模型的五强溪大坝多测点位移模型[J].工程勘察,2017,45(5):62- 64.
[19] 刘斌,戴吾蛟,曾凡河,杨国祥.利用独立分量回归建立大坝多测点位移模型[J].大地测量与地球动力学,2016,36(2):124- 128.
[20] 王嵘冰,徐红艳,李波,冯勇.BP神经网络隐含层节点数确定方法研究[J].计算机技术与发展,2018,28(4):31- 35.
[2] 冯宇强,陈五一,陶丛丛,等.基于遗传算法的岭回归模型在大坝安全监测中的应用[J].水电能源科学,2010,28(10):51- 52.
[3] 李红祥, 岳东杰, 李立瑞. 基于主成分回归的大坝位移模型[J]. 水电与抽水蓄能, 2008, 32(5):61- 64.
[4] 赵斌,吴中如,张爱玲.BP模型在大坝安全监测预报中的应用[J].大坝观测与土工测试,1999(6):1- 4.
[5] 陈维江,马震岳,董毓新.大坝安全监测遗传回归模型研究及应用[J].水电能源科学,2002,20(2):39- 42.
[6] 张帆. 基于神经网络的大坝安全监控模型研究[D].南京:东南大学,2016.
[7] 齐银峰.BP神经网络在大坝变形分析中的应用及改进[D].昆明:昆明理工大学,2017.
[8] 杨超.改进的粒子群优化BP神经网络在大坝变形预测中的应用[D].抚州:东华理工大学,2016.
[9] 吴中如,陈波.大坝变形监控模型发展回眸[J].现代测绘,2016,39(5):1- 3.
[10] 赵卿. 大坝变形分析多测点统计模型的应用研究[D].武汉:武汉大学,2010.
[11] 顾冲时,吴中如.混凝土坝空间位移场的确定性模型反演分析法[J].河海大学学报,1994(2):82- 87.
[12] 安慧琳,李艳玲,曾贝佳,钟为.重力坝挠度多测点空间模型研究[J].水电能源科学,2016,34(11):77- 81.
[13] 黄铭,葛修润,刘俊.大坝安全监测的多测点位移向量模型[J].上海交通大学学报,2001(4):514- 517.
[14] 李端有,周元春,甘孝清.混凝土拱坝多测点确定性位移监控模型研究[J].水利学报,2011,42(8):981- 985,994.
[15] HE JP,TU YY,SHI YQ,et al. Model of diagnosing abnormal behavior of dam based on multi-monitoring points and bayes fusion theory[J]. Journal of Yangtze River Scientific Research Institute, 2012, 29(10):63- 67.
[16] 李端有,周元春.BP网络在大坝变形空间多测点监测模型中的应用[J].长江科学院院报,2005(6):7- 8.
[17] 柴丽莎,戚丹,吴浩.多测点多方向BP网络模型在大坝变形监测中的应用[J].水电能源科学,2014,32(3):94- 97.
[18] 黄大伟,刘斌,戴吾蛟.基于神经网络模型的五强溪大坝多测点位移模型[J].工程勘察,2017,45(5):62- 64.
[19] 刘斌,戴吾蛟,曾凡河,杨国祥.利用独立分量回归建立大坝多测点位移模型[J].大地测量与地球动力学,2016,36(2):124- 128.
[20] 王嵘冰,徐红艳,李波,冯勇.BP神经网络隐含层节点数确定方法研究[J].计算机技术与发展,2018,28(4):31- 35.