期刊文献+

山岭公路隧道施工安全风险评估方法及其应用研究 被引量:3

STUDY ON SAFETY RISK ASSESSMENT METHOD OF MOUNTAIN RIDGE HIGHWAY TUNNEL CONSTRUCTION AND ITS APPLICATION
下载PDF
导出
摘要 由于山岭公路隧道施工安全风险大小与各安全风险影响因子之间存在非线性映射关系,引入混合核函数和粒子群算法,建立基于粒子群算法优化混合核极限学习机的山岭公路隧道施工安全风险评估方法。该方法依据山岭公路隧道地质与施工特征,建立隐含层节点特征映射混合核函数,采用粒子群算法对训练样本进行模型训练,同时对映射函数中混合核函数参数进行最小均方差寻优,获得山岭公路隧道施工安全风险评估的混合核极限学习鳩型并进行算例验证,结果表明所建模型可靠。 As a result of the nonlinear mapping between construction safety risk of mountain ridge highway tunnel and influencing factors of safety risk,the hybrid kernel function and particle swarm optimization algorithm are applied to establish safety risk evaluation method of mountain ridge highway tunnel construction based on the hybrid kernel limit learning machine optimized by particle swarm optimization algorithm.According to the geological and construction characteristics of mountain ridge highway tunnel,this method establishes the hybrid kernel function of hidden layer node feature mapping,uses particle swarm optimization algorithm to train the training samples,and optimizes the parameters of the hybrid kernel function in the mapping function to the minimum mean square deviation,finally obtains the hybrid kernel limit learning machine model of mountain ridge highway tunnel construction safety risk assessment,and carries out the example verification.The results show that the model is reliable.
作者 宋明 舒恒 彭文波 周峰 崔庆龙 谢全敏 SONG Ming;SHU Heng;PENG Wen-bo;ZHOU Feng;CUI Qing-long;XIE Quan-min(CCCC Second Highway Consultants Co.,Ltd.,430056,Wuhan,China;School of Civil Engineering and Architecture,Wuhan University of Technology,430070,Wuhan,China)
出处 《建筑技术》 2021年第7期884-887,共4页 Architecture Technology
基金 新疆维吾尔自治区重大科技专项(2020A03003-4) 国家自然科学基金项目(51779197)。
关键词 山岭公路隧道 施工安全 风险评估 混合核函数 粒子群算法 mountain ridge highway tunnel construction safety risk assessment hybrid kernel function particle swarm optimization
  • 相关文献

参考文献3

二级参考文献28

  • 1VAPNIK V. The nature of statistical learning theory[ M]. New York: Springer-Verlag, 1995.
  • 2邓乃阳,田英杰.数据挖掘中的新方法:支持向量机[M].北京:科学出版社,2004.
  • 3LIN H T, LIN C J. A study on sigmoid kernels for SVM and the training of non-PSD kernels by SMO-type methods[ EB/OL]. [2009 -8 -17]. http:// www. csie. ntu. edu. tw /- cjlin/papers /tanh. pdf.
  • 4BACH F R, LANCKRIET G R G, JORDAN M I. Multiple kernel learning, conic duality, and the SMO algorithm[ C]// Proceedings of the 21st International Conference on Machine-Learning. Banff. New York: ACM, 2004, 69:41 -48.
  • 5KEERTHI S S, SHEVADE S K, BHATTACHARYYA C, et al. Improvements to Platt's SMO algorithm for SVM classifier design [ J]. Neural Computation, 2001, 13(3) : 637 - 649.
  • 6SMITS G F, JORDAAN E M. Improved SVM regression using mixtures of kernels [ C]// Proceedings of the 2002 International Joint Conference on Neural Networks. Washington, DC: IEEE, 2002, 3: 2785 - 2790.
  • 7ZHOU S S, LIU H W, YE F. Variant of gaussian kernel and parameter setting method for nonlinear SVM[ J]. Neurocomputing, 2009, 72( 13 - 15) : 2931 - 2937.
  • 8STEINWART I. On the optimal parameter choice for support vector machines[ J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(10) : 1274 - 1284.
  • 9CAMPS V G, MARTIN-GUERRERO J D, ROJO-ALVAREZ J L, et al. Fuzzy sigmoid kernel for support vector classifiers[ J]. Neurocomputing, 2004, 62(7) : 501 - 506.
  • 10RAKOTOMAMONJY A, BACH F, CANU S, et al. More efficiency in multiple kernel learning[ C]//Proceedings of the 24th International Conference on Machine Learning. New York: ACM, 2007, 227: 775 - 782.

共引文献159

同被引文献23

引证文献3

二级引证文献5

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部