岩土力学 ›› 2019, Vol. 40 ›› Issue (7): 2866-2872.doi: 10.16285/j.rsm.2018.0593

• 数值分析 • 上一篇    下一篇

海量监测数据下分布式BP神经网络区域 滑坡空间预测方法

赵久彬1,刘元雪1,刘娜2,胡明1   

  1. 1. 陆军勤务学院 岩土力学与地质环境保护重庆市重点实验室,重庆 401311;2. 重庆市地质矿产测试中心,重庆 400042
  • 收稿日期:2018-04-10 出版日期:2019-07-11 发布日期:2019-07-28
  • 通讯作者: 刘元雪,1969年生,男,博士,教授,博士生导师,主要从事岩土体本构关系与地下工程稳定性的教学与科研工作。E-mail: lyuanxue@vip.sina.com E-mail:459694118@qq.com
  • 作者简介:赵久彬,男,1987年生,博士研究生,主要从事滑坡监测预警大数据系统研究。
  • 基金资助:
    国家自然科学基金项目(No. 41877219);重庆市基础科学与前沿技术研究专项重点项目(No. cstc2015jcyjBX0073);重庆市国土资源和房屋管理局科技计划项目(No. KJ-2018016);陆军勤务学院研究生创新项目(No. LY180510)。

Spatial prediction method of regional landslide based on distributed bp neural network algorithm under massive monitoring data

ZHAO Jiu-bin1, LIU Yuan-xue1, LIU Na2, HU Ming1   

  1. 1. Chongqing Key Laboratory of Geomechanics and Geoenvironment Protection, Army Logistics University of PLA, Chongqing 401311, China; 2. Chongqing Testing Center of Geology and Mineral Resources, Chongqing 400042, China
  • Received:2018-04-10 Online:2019-07-11 Published:2019-07-28
  • Supported by:
    This work was supported by the National Natural Science Foundation of China (41877219), Chongqing Research Program of Basic Research and Frontier Technology (cstc2015jcyjBX0073), the Science and Technology Project of Land Resources and Real Estate Management Bureau of Chongqing Government (KJ-2018016) and the Graduate Creative Program of Army Logistics University of PLA (LY180510).

摘要: 提出BP神经网络的分布式区域滑坡预测方法,算法设计在大数据分布式处理平台Spark下实现,通过构造包含均方误差和L2正则化的代价函数,提高运算实时性和算法泛化能力。统计影响滑坡评价因子的量化指标和定义监测剖面危险级别评价值,并进行评价因子特征选取,用于三峡库区忠县区域9个滑坡11年月监测海量数据挖掘,对研究区所有滑坡监测剖面每月进行危险级别评价,实现以月为周期的区域滑坡危险程度空间预测。试验表明,采用所述方法得到的拟合精度、准确度、效率均比梯度提升决策树、随机森林算法好,预测的滑坡危险级别准确,该方法可作为区域滑坡空间预测的一种新思路。

关键词: BP神经网络, 分布式Spark平台, 区域滑坡空间预测, 监测剖面

Abstract: Landslides have characteristics such as regionality, multipleness, and seriousness. The traditional area landslide spatial prediction method, under massive data condition, has poor real-time performance and strong subjectivity, and the evaluation performance is poor under multiple factors. A distributed regional landslide prediction method based on BP neural network is proposed in this paper. The algorithm is designed as a parallel computing environment of big data processing platform Spark, and the cost function of BP network is designed as two items of mean square error and L2 regularization, which improves generalization ability. Through statistics of the quantitative indicators of landslide factors and the definition of hazard index of monitoring profile, the influencing factors are selected. This approach is applied to massive data mining of 9 landslides in 11 years in Zhongxian area of Three Gorges Reservoir area, which achieves the combination of qualitative analysis and quantitative analysis. All the landslide monitoring sections in the study area were monthly evaluated to determine the risk level, and the spatial prediction of the monthly landslide risk degree was achieved. Experiments show that the fitting accuracy and efficiency obtained by the method are better than gradient-based decision trees and random forest algorithms, and the prediction area landslide risk assessment accuracy is good. This method can be used as a new approach for regional landslide spatial prediction.

Key words: BP neural network, Spark platform, regional landslide spatial prediction, monitoring profile

中图分类号: 

  • P 642.22
[1] 胡 军,董建华 ,王凯凯 ,黄贵臣,. 边坡稳定性的CPSO-BP模型研究[J]. , 2016, 37(S1): 577-582.
[2] 王开禾,罗先启,沈 辉,张海涛. 围岩力学参数反演的GSA-BP神经网络模型及应用[J]. , 2016, 37(S1): 631-638.
[3] 左育龙 ,朱合华 ,李晓军 . 岩土工程可靠度分析的神经网络四阶矩法[J]. , 2013, 34(2): 513-518.
[4] 周 喻 ,吴顺川 ,焦建津 ,张晓平 . 基于BP神经网络的岩土体细观力学参数研究[J]. , 2011, 32(12): 3821-3826.
[5] 涂 帆,崔广强,林从谋,肖朝昀. 垃圾填埋场稳定影响因素敏感性神经网络分析[J]. , 2010, 31(4): 1168-1172.
[6] 许尚杰,党发宁,高闯洲,党维维. 吸力内摩擦角的确定方法研究[J]. , 2009, 30(S2): 22-27.
[7] 温 森,赵延喜,杨圣奇. 基于Monte Carlo-BP神经网络TBM掘进速度预测[J]. , 2009, 30(10): 3127-3132.
[8] 闫 滨 ,高真伟,. 基于PSONN的大坝监控实时预报模型[J]. , 2006, 27(S2): 548-552.
[9] 金长宇 ,马震岳 ,张运良 ,沙瑞华 ,陈庆发,. 神经网络在岩体力学参数和地应力场反演中的应用[J]. , 2006, 27(8): 1263-1266.
[10] 刘福深,刘耀儒,杨 强. 基于差异进化算法的前馈神经网络在大坝变形监测中的应用[J]. , 2006, 27(4): 597-600.
[11] 张福波,陈有亮,潘镇涛. 基于BP神经网络与模糊控制的深基坑开挖侧向变形分析[J]. , 2005, 26(7): 1148-1152.
[12] 彭 涛 ,杨岸英 ,梁 杏 ,袁 琴,. BP神经网络-灰色系统联合模型预测软基沉降量[J]. , 2005, 26(11): 1810-1814.
[13] 刘勇健. 基于遗传-神经网络的单桩竖向极限承载力预测方法研究[J]. , 2004, 25(1): 59-63.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!