基于天牛须优化算法的相关向量机边坡稳定性分析

doi:10.3969/j.issn.1674-0696.2024.11.02

摘要/Abstract

摘要： 为了快速、准确地预测边坡稳定性，及时控制边坡危害，提出了一种基于天牛须(beetle antennae search, BAS)优化算法的相关向量机(relevance vector machine, RVM)边坡稳定性分析模型。基于RVM模型，建立了边坡影响因素与稳定性的非线性映射关系；采用BAS算法对RVM模型参数进行优化，提出了基于BAS算法的RVM边坡稳定性分析优化模型；并将该模型应用于京新高速公路的边坡稳定性分析。分析结果表明：与实际值相比，基于BAS-RVM模型的最大绝对值相对误差为3.90%；在相同学习样本下，与RVM模型、支持向量机(support vector machine, SVM)模型和径向基函数(radical basis function, RBF)模型的预测值相比，BAS-RVM模型预测结果的可信度和拟合度更好、精度更高，其平均绝对值误差(mean absolute error, EMA)、均方根误差(root mean square error, ERMS)、相对均方误差(relative root mean square error, ERRMS)远低于其他3种模型。

关键词: 岩土工程；天牛须优化算法（BAS）；相关向量机（RVM）；预测模型；边坡

Abstract: In order to predict slope stability quickly and accurately as well as control slope damage in time, a slope stability analysis model of relevance vector machine (RVM) based on beetle antennae search (BAS) optimization algorithm was proposed. Based on RVM model, the nonlinear mapping relationship between slope influence factors and stability was established. The parameters of RVM model were optimized by BAS algorithm, and an optimization model of RVM slope stability analysis based on BAS algorithm was proposed. The proposed model was applied to the slope stability analysis of Beijing-Urumqi expressway. The analysis results show that compared with the actual value, the maximum absolute relative error based on the BAS-RVM model is 3.90%. Under the same learning sample, compared with the RVM model, support vector machine (SVM) model and radical basis function (RBF) model, the BAS-RVM model has better reliability and fit, and higher accuracy in predicting results, whose mean absolute error (EMA), root mean square error (ERMS) and relative root mean square error (ERRMS) are much lower than those of other three kinds of models.

Key words: geotechnical engineering; beetle antennae search (BAS) optimization algorithm; relevance vector machine (RVM) ; prediction model; slope

中图分类号:

U417.1

张研1,2，唐北昌1，孟庆鹏1,2. 基于天牛须优化算法的相关向量机边坡稳定性分析[J]. 重庆交通大学学报（自然科学版）, 2024, 43(11): 11-17.

ZHANG Yan1,2, TANG Beichang1, MENG Qingpeng1,2. Slope Stability Analysis on Relevance Vector Machine Based on Beetle Antennae Search Optimization Algorithm[J]. Journal of Chongqing Jiaotong University(Natural Science), 2024, 43(11): 11-17.

参考文献

［1］史笑凡, 杨春风, 王可意. 基于支持向量机和改进BP神经网络的路基边坡稳定性研究［J］. 公路交通科技, 2019, 36(1): 31-37.
SHI Xiaofan, YANG Chunfeng, WANG Keyi. Study on stability of roadbed slope based on SVM and improved BP neural network ［J］. Journal of Highway and Transportation Research and Development, 2019, 36(1): 31-37.
［2］杨枭, 李朋, 肖盛燮. 可靠性分析在边坡灰色聚类问题中的应用［J］. 重庆交通大学学报(自然科学版), 2011, 30(4): 778-781.
YANG Xiao, LI Peng, XIAO Shengxie.Application of reliability analysis in grey cluster slope ［J］. Journal of Chongqing Jiaotong University (Natural Science), 2011, 30(4): 778-781.
［3］原先凡, 胡帅, 杨威, 等. 基于时空演化规律的某水库边坡稳定性及其变形特征分析［J］. 重庆交通大学学报(自然科学版), 2017, 36(3): 71-78.
YUAN Xianfan, HU Shuai, YANG Wei, et al. Stability and deformation characteristics of a certain reservoir slope based on space-time evolution laws ［J］. Journal of Chongqing Jiaotong University (Natural Science), 2017, 36(3): 71-78.
［4］武小菲, 杨涛, 武琨璐, 等. 复杂空间形态边坡的稳定性分析［J］. 西南交通大学学报, 2018, 53(4): 756-761.
WU Xiaofei, YANG Tao, WU Kunlu, et al. Stability analysis of slope with complex spatial shape ［J］. Journal of Southwest Jiaotong University, 2018, 53(4): 756-761.
［5］宁昕扬, 曾俊, 吕国梁. 考虑裂隙统计分布的膨胀土边坡稳定分析和加固设计［J］. 水利水电技术(中英文), 2022, 53(增刊1): 436-441.
NING Xinyang, ZENG Jun, LYU Guoliang. Stability analysis and reinforcement design of expansive soil slope considering statistical distribution ofcracks［ J］. Water Resources and Hydropower Engineering, 2022, 53(Sup1): 436-441.
［6］李丽敏, 魏雄伟, 温宗周, 等. 基于改进AHP-FCE的滑坡地质灾害危险性评价［J］. 国外电子测量技术, 2021, 40(10): 53-59.
LI Limin, WEI Xiongwei, WEN Zongzhou, et al. Risk assessment of landslide geological hazard based on improved AHP-FCE ［J］. Foreign Electronic Measurement Technology, 2021, 40(10): 53-59.
［7］任洋, 李天斌, 杨玲, 等. 基于离心模型试验与数值计算的超高陡加筋土填方边坡稳定性分析［J］. 岩土工程学报, 2022, 44(5): 836-844.
REN Yang, LI Tianbin, YANG Ling, et al. Stability analysis of ultra-high-steep reinforced soil-filled slopes based on centrifugal model tests and numerical calculation ［J］. Chinese Journal of Geotechnical Engineering, 2022, 44(5): 836-844.
［8］张莹莹, 杨忠年, 时伟, 等. 冻融循环作用下膨胀土边坡稳定性模型试验研究［J］. 西安建筑科技大学学报(自然科学版), 2020, 52(2): 257-266.
ZHANG Yingying, YANG Zhongnian, SHI Wei, et al. Model test study on the stability of expansive soil slope under freeze-thaw cycle ［J］. Journal of Xian University of Architecture & Technology (Natural Science Edition), 2020, 52(2): 257-266.
［9］洪勇, 邵珠山, 石广斌, 等. 基于三维极限分析法的GIM和SRM边坡安全系数计算结果对比［J］. 河海大学学报(自然科学版), 2022, 50(4): 112-120.
HONG Yong, SHAO Zhushan, SHI Guangbin, et al. Comparison of GIM and SRM calculated slope safety factor based on three-dimensional limit analysis method ［J］. Journal of Hohai University (Natural Sciences), 2022, 50(4): 112-120.
［10］赵波, 许宝田, 阎长虹, 等. 人工堆山边坡稳定性数值分析［J］. 工程地质学报, 2011, 19(6): 859-864.
ZHAO Bo, XU Baotian, YAN Changhong, et al. Numerical analysis of slope stability for artificial landscape hill ［J］. Journal of Engineering Geology, 2011, 19(6): 859-864.
［11］马文涛. 基于PSO和LSSVM的边坡稳定性评价方法［J］. 岩土力学, 2009, 30(3): 845-848.
MA Wentao. Evaluation of rock slope stability based on PSO and LSSVM ［J］. Rock and Soil Mechanics, 2009, 30(3): 845-848.
［12］温廷新, 张波. 露天煤矿边坡稳定性的随机森林预测模型［J］. 科技导报, 2014, 32(增刊1): 105-109.
WEN Tingxin, ZHANG Bo. Stochastic forest prediction model for slope stability of open-pit coal mine ［J］. Science & Technology Review, 2014, 32(Sup1): 105-109.
［13］ BUI D T, TSANGARATOS P, NGUYEN V T, et al. Comparing the prediction performance of adeep learning neural network model with conventional machine learning models in landslide susceptibility assessment ［J］. CATENA, 2020, 188: 104426.
［14］ LIU Yutao, CHI Xiaobo, LIU Jianbing, et al.Improved PSO-RBF neural network based prediction of slope stability factors ［C］∥The 31st China Process Control Conference. Xuzhou, China: CPCC, 2020: 29914.
［15］张研, 吴哲康, 王鹏鹏, 等. 基于PCA-RVM的露天矿边坡稳定性预测模型［J］. 矿业研究与开发, 2021, 41(3): 13-18.
ZHANG Yan, WU Zhekang, WANG Pengpeng, et al. Prediction model of slope stability of open pit mine based on PCA-RVM ［J］. Mining Research and Development, 2021, 41(3): 13-18.
［16］赵春晖, 张燚. 相关向量机分类方法的研究进展与分析［J］. 智能系统学报, 2012, 7(4): 294-301.
ZHAO Chunhui, ZHANG Yi. Research progress and analysis on methods for classification of RVM ［J］. CAAI Transactions on Intelligent Systems, 2012, 7(4): 294-301.
［17］楼俊钢, 江建慧, 沈张果, 等. 软件可靠性预测的相关向量机模型［J］. 计算机研究与发展, 2013, 50(7): 1542-1550.
LOU Jungang, JIANG Jianhui, SHEN Zhangguo, et al. Software reliability prediction modeling with relevance vector machine ［J］. Journal of Computer Research and Development, 2013, 50(7): 1542-1550.
［18］ TIPPING M E. Sparse Bayesian learning and the relevance vector machine ［J］. Journal of Machine Learning Research, 2001, 1: 211-244.
［19］ ZHANG Bin, DUANYiqin, ZHANG Yi, et al. Particle swarm optimization algorithm based on beetle antennae search algorithm to solve path planning problem ［C］∥2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC). Chongqing, China. IEEE, 2020: 1586-1589.
［20］王庆喜, 郭晓波. 基于莱维飞行的粒子群优化算法［J］. 计算机应用研究, 2016, 33(9): 2588-2591.
WANG Qingxi, GUO Xiaobo. Particle swarm optimization algorithm based on Levy flight ［J］. Application Research of Computers, 2016, 33(9): 2588-2591.
［21］ YANG Xinshe, DEB S. Engineering optimization by cuckoo search ［J］. International Journal of Mathematical Modelling and Numerical Optimization, 2010, 1(4): 330.
［22］谢朔. 基于天牛须优化的船舶运动建模与避碰方法研究［D］. 武汉: 武汉理工大学, 2020.
XIE Shuo.Beetle Antenna Search Based Ship Motion Modeling and Collision Avoidance Methods ［D］. Wuhan: Wuhan University of Technology, 2020.
［23］孙吉书, 夏健超, 王建平, 等. 相关向量机模型在边坡稳定性预测中的应用［J］. 科学技术与工程, 2021, 21(28): 12234-12242.
SUN Jishu, XIA Jianchao, WANG Jianping, et al. Application of relevance vector machine model in slope stability prediction ［J］. Science Technology and Engineering, 2021, 21(28): 12234-12242.

[1]	牟凤云1，杨猛1，余情2，刘振涛3. 基于RF-RUSLE模型的水土流失性公路自然灾害风险评估——以重庆市巴南区为例[J]. 重庆交通大学学报（自然科学版）, 2020, 39(11): 114-121.
[2]	曾红艳1，2，刘伟1，2，周成1，2，韩利彪1，2，谭昌明3. 抗滑短桩支护土坡的试验研究[J]. 重庆交通大学学报（自然科学版）, 2020, 39(09): 119-126.
[3]	王宗建1,2，马书文1,2，卢谅2，张耿川3，沈权4. 墙面结构对加筋土挡墙变形性能的影响[J]. 重庆交通大学学报（自然科学版）, 2019, 38(03): 51-59.
[4]	张四平1，2，黄亚飞1，吴曙光1，2，常通1，罗超1. 地震作用下考虑土拱效应的桩间挡板土压力计算[J]. 重庆交通大学学报（自然科学版）, 2018, 37(04): 45-52.
[5]	李霞,田远,崔洪军, 赵志强,张志磊. 高速公路波形梁护栏安全性能提升方案设计[J]. 重庆交通大学学报（自然科学版）, 2016, 35(5): 32-37.
[6]	邰永刚，赵源. 长大下坡路段隧道入口钢护栏结构形式研究[J]. 重庆交通大学学报（自然科学版）, 2015, 34(5): 65-68.
[7]	崔洪军，崔姗，邢小高，梁国凤. 护栏高度变化对防撞能力影响研究[J]. 重庆交通大学学报（自然科学版）, 2015, 34(1): 84-86.
[8]	魏军扬，王保田，张海霞，蓝日彦. 格栅反包生态袋挡土面层界面特性试验研究[J]. 重庆交通大学学报（自然科学版）, 2014, 33(2): 68-71.
[9]	陈亮，谌晓静. 倒Y型挡土墙力学特性研究[J]. 重庆交通大学学报（自然科学版）, 2013, 32(3): 419-423.
[10]	林国辉，邰永刚，包凌文，白书锋. 防撞护栏破坏点控制方法研究[J]. 重庆交通大学学报（自然科学版）, 2012, 31(5): 1002-1006.
[11]	唐秋元，施毅，周峰，袁恒. 混合支挡结构在工程中的应用[J]. 重庆交通大学学报（自然科学版）, 2011, 30(S1): 541-544.
[12]	唐秋元，施毅，周峰，袁恒. 混合支挡结构在工程中的应用[J]. 重庆交通大学学报（自然科学版）, 2011, 30(S1): 541-544.
[13]	王景梅，姚令侃，杨明. 汶川震区路肩墙抗震能力检算与震害机理分析[J]. 重庆交通大学学报（自然科学版）, 2010, 29(6): 919-924.
[14]	王宏，钟宁，王志超. 重庆奉云高速公路挖断村滑坡的成因分析与治理措施[J]. 重庆交通大学学报（自然科学版）, 2010, 29(1): 85-89.
[15]	饶枭宇,李剑,杨静. 锚固注浆体性能试验研究[J]. 重庆交通大学学报（自然科学版）, 2009, 28(3): 497-500.