基于组合预测思想,结合BP神经网络和马尔科夫链2种预测方法,构建了一种新维BP神经网络-马尔科夫链大坝沉降预测模型。通过对训练样本的学习,利用新维改进的BP神经网络算法实现了对沉降位移时间序列的滚动预测。在此基础上,借助马尔科夫链模型对其随机扰动误差进行修正,有效地提高了预测结果的精度。将构建的组合模型应用于长洲大坝船闸控制楼沉降位移时序预测中,研究结果表明该模型预测精度较高、可靠性好,提高了模型的中长期预测能力,为大坝沉降预测提供了一种有效的新方法。
Abstract
A dam settlement prediction model integrating BP neural network model and Markov chain prediction was built in this paper. Through emulating the training samples, rolling prediction for the settlement displacement time series was performed by the metabolism-improved BP neural network algorithm. Furthermore, Markov chain was used to correct its random disturbance and the prediction results were improved. This model was applied to the settlement displacement timing prediction of Changzhou dam lock control building. The result shows that the model has high prediction accuracy and good reliability. It improves the long-term prediction ability, and provides an effective method for dam settlement prediction.
关键词
沉降预测 /
BP神经网络 /
马尔科夫链 /
大坝监测 /
长洲水利枢纽
Key words
settlement prediction /
BP neural network /
Markov chain /
dam monitoring /
Changzhou water power junction
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 吴中如.大坝的安全监控理论和试验技术[M].北京:中国水利水电出版社,2009.(WU Zhong-ru. Dam Safety Monitoring Theory and Test Technology [M]. Beijing: China Water Power Press,2009. (in Chinese))
[2] 潘洁晨.基于Matlab的土石坝变形分析BP神经网络模型的建立——以哈尔滨西泉眼水库大坝为例[J].水资源与水工程学报,2012,23(3):166-169.(PAN Jie-chen. Establishment of BP Neural Network Model Based on Matlab to Deformation of Earth Rockfill Dam: Case Study of Xiquanyan Reservoir Dam in Harbin [J]. Journal of Water Resources ＆ Water Engineering,2012,23(3):166-169. (in Chinese))
[3] 徐 伟,何金平.基于多尺度小波分析的大坝变形自回归预测模型[J].武汉大学学报(工学版),2012,45(3):285-289.(XU Wei,HE Jin-ping. Forecast Model of Dam Deformation Based on Multi-scale Wavelet Analysis and Autoregressive Method[J]. Engineering Journal of Wuhan University,2012,45(3):285-289.(in Chinese))
[4] 吕蓓蓓,杨远斐.偏最小二乘法与神经网络耦合的大坝监测模型[J].人民黄河,2013,35(3):84-89.(LV Bei-bei,YANG Yuan-fei. Dam Monitoring Model Based on Coupling of Partial Least Square Regression and Artificial Neural Network[J]. Yellow River,2013,35(3):84-89. (in Chinese))
[5] 蔡小辉,张 瀚,崔冬冬.EMD-GM(1,1)模型及在大坝变形预测中的应用[J].人民长江,2011,42(10):91-94.(CAI Xiao-hui, ZHANG Han,CUI Dong-dong. Research on EMD-GM(1,1) Model and Its Application in Dam Displacement Forecast[J]. Yangtze river,2011,42(10):91-94. (in Chinese))
[6] 龙 浩,高 睿,孔德新,等.基于BP神经网络-马尔科夫链模型的隧道围岩位移预测[J].raybet体育在线
院报,2013,30(3):40-43.(LONG Hao,GAO Rui,KONG De-xin,et al. Forecast of Tunnel’s Surrounding Rock Displacement by BP Neural and Markov Chain[J]. Journal of Yangtze River Scientific Research Institute,2013,30(3):40-43. (in Chinese))
[7] 张登文,蒋红妍,张子圆.基于BP神经网络的建筑工程造价快速预测[J].水利与建筑工程学报,2010,8(3):61-62.(ZHANG Deng-wen,JIANG Hong-yan,ZHANG Zi-yuan. Fast Estimation for Architectural Project Cost Based on BP Neural Network[J]. Journal of Water Resources and Architectural Engineering,2010,8(3):61-62. (in Chinese))
[8] 周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].北京:清华大学出版社,2005.(ZHOU Kai-li,KANG Yao-hong. Neural Network Model and Its MATLAB Simulation Program Design[M]. Beijing: Tsinghua University,2005. (in Chinese))
[9] 朱凤林,韩 卫.Matlab仿真平台下大坝位移BP神经网络模型研究[J].raybet体育在线
院报,2013,30(1):99-101.( ZHU Feng-lin,HAN Wei. BP Neural Network Model to Monitor Dam Deformation in Matlab Simulation Platform[J]. Journal of Yangtze River Scientific Research Institute,2013,30(1):99-101. (in Chinese))
[10]尤 杰,车 轶,仲伟秋.基于BP神经网络的既有建筑混凝土强度预测[J].建筑科学与工程学报,2011,28(1):70-75.(YOU Jie,CHE Yi,ZHONG Wei-qiu. Prediction of Concrete Strength of Existing Buildings Based on BP Neural Networks[J]. Journal of Architecture and Civil Engineering,2011,28(1):70-75. (in Chinese))
[11]何自立,杨建国,靳国云,等.基于新维无偏灰色马尔可夫模型的大坝沉降预测研究[J].西北农林科技大学学报(自然科学版),2013,41(5):213-218. (HE Zi-li,YANG Jian-guo,JIN Guo-yun,et al. Dam Settlement Prediction Based on Metabolism Unbiased Grey-Markov Model[J]. Journal of Northwest A & F University (Natural Science Edition),2013,41(5):213-218. (in Chinese))
[12]张守平,樊科伟.基于自适应MGM(1,n)-马尔科夫链模型的大坝变形预测[J].南水北调与水利科技,2014,12(1):145-148. (ZHANG Shou-ping,FAN Ke-wei. Prediction of Dam Deformation Based on Self-adaptive MGM-Markov Model[J]. South to North Water Transfers and Water Science & Technology,2014,12(1):145-148. (in Chinese))
[13]向华琦.基于时间序列分析法的大坝变形监测数据分析研究[D].陕西杨凌:西北农林科技大学,2012. (XIANG Hua-qi. Analysis on Dam Deformation Monitoring Data Using Time Series Analysis Method[D]. Yangling,Shaanxi: Northwest A & F University,2012. (in Chinese))
[14]毛亚纯,王恩德,修春华. 剔除变形监测粗差数据的新方法——数据跳跃法[J]. 东北大学学报(自然科学版),2011,32(7):1020-1023. (MAO Ya-chun,WANG En-de,XIU Chun-hua. Data Jump Method: a New Approach to Eliminating the Deformation Monitoring Data with Gross Errors[J]. Journal of Northeastern University (Natural Science),2011,32(7):1020-1023. (in Chinese))
[15]朱新国,张展羽,祝 卓.基于改进型BP神经网络马尔科夫模型的区域需水量预测[J].水资源保护,2010,26(2):28-31. (ZHU Xin-guo,ZHANG Zhan-yu,ZHU Zhuo. Prediction of Water Demand Based on Improved BP Neural Network and Markov Model[J]. Water Resources Protection,2010,26(2):28-31. (in Chinese))
PDF(1127 KB)
