中国安全科学学报 ›› 2023, Vol. 33 ›› Issue (9): 41-48.doi: 10.16265/j.cnki.issn1003-3033.2023.09.1143

• 安全工程技术 • 上一篇    下一篇

基于WOA-SVM的引水隧洞岩爆烈度评估模型

靳春玲(), 姬照泰, 贡力, 安祥, 周一   

  1. 兰州交通大学 土木工程学院,甘肃 兰州 730070
  • 收稿日期:2023-03-08 修回日期:2023-06-16 出版日期:2023-09-28
  • 作者简介:

    靳春玲 (1976—),女,黑龙江齐齐哈尔人,硕士,教授,主要从事引水隧洞重大地质灾害方面的研究。E-mail:

    贡 力 教授

  • 基金资助:
    国家自然科学基金资助(51969011); 国家自然科学基金资助(72261024); 甘肃省科技计划项目(20JR10RA274); 甘肃省教育厅优秀研究生“创新之星”项目(2023CXZX-599)

Evaluation model of rockburst intensity of diversion tunnel based on WOA-SVM

JIN Chunling(), JI Zhaotai, GONG Li, AN Xiang, ZHOU Yi   

  1. College of Civil Engineering, Lanzhou Jiaotong University, Lanzhou Gansu 730070, China
  • Received:2023-03-08 Revised:2023-06-16 Published:2023-09-28

摘要:

为减少引水隧洞施工过程中岩爆事故的发生,在施工前做好岩爆烈度评估,选取4项评价指标作为岩爆的评价指标,分别为:岩石单轴饱和抗压强度Rc、岩石单轴抗拉强度Rt、围岩最大切向应力σθ和岩石弹性能量指数Wet;基于前人研究成果,选取120组岩爆实例作为机器学习样本数据,构建基于鲸鱼优化算法(WOA)优化支持向量机(SVM)的评估模型;并以滇中引水工程香炉山深埋长引水隧洞为例进行岩爆烈度评估的验证。结果表明:机器学习可以较好避开人为因素,完全由数据驱动,WOA-SVM评估精度达到97.22%;经过对比,所构建的模型比PSO-SVM、GA-SVM和WOA-BP神经网络模型在评估精度、泛化程度上均更优;同时,WOA-SVM模型在处理岩爆问题上可以更好地捕捉岩爆等级与指标之间的联系。

关键词: 鲸鱼优化算法(WOA), 支持向量机(SVM), 引水隧洞, 岩爆烈度, 机器学习

Abstract:

This study aims to reduce the occurrence of rockburst accidents in the construction of diversion tunnels. Before construction, rockburst intensity assessment and prevention measures were put forward. Four evaluation indexes were selected as rock burst evaluation indexes in the study, namely, rock uniaxial saturated compressive strength Rc, rock uniaxial tensile strength Rt, maximum tangential stress σθ of surrounding rock and rock elastic energy index Wet. According to the research results, 120 groups of rockburst instances were selected as the machine learning sample data, and the WOA-SVM assessment model was proposed. Taking a section of a deep-buried and long diversion tunnel in Xianglushan of the Central Yunnan Water Diversion Project as an example, the intensity assessment results of rockburst intensity were verified. The results show that machine learning can better avoid human factors, and it is completely data-driven with an assessment accuracy of 97.22% for WOA-SVM. By comparison, its assessment accuracy and generalization are better than those of PSO-SVM, GA-SVM and WOA-BP neural network models. The results show that the WOA-SVM model can better capture the link between rockburst levels and indicators for rockburst problems.

Key words: whale optimization algorithm (WOA), support vector machine (SVM), water intake tunnel, rockburst intensity, machine learning