锚杆锚固强度是评价锚杆锚固质量的主要因素之一,而混凝土中锚杆锚固强度受多因素影响,各因素间也具有复杂的关联。应用支持向量机回归原理,以混凝土龄期、锚杆直径和锚固长度3个因素作为输入列向量构建样本集,选用径向基核函数建立混凝土中锚杆锚固强度的支持向量机回归预测模型。利用30组锚固强度实验数据中2/3的数据作为训练样本,剩余1/3的数据作为预测样本,对锚固强度进行回归预测,将预测结果与试验结果和BP网络计算结果进行对比分析。研究结果表明:此模型预测精度高,具有良好的泛化能力,预测结果具有可信性,将SVM方法运用于混凝土中锚杆锚固强度的预测是合理有效的,为锚固强度的预测提供了一条新的途径。
As one of the main factors of evaluating the anchoring quality, bolt anchoring strength in the concrete is affected by many factors which have complex interrelationships with each other. Concrete age, bolt diameter and anchorage length are used as the input column vector to build sample set, and radial basis kernel function is adopted for an prediction model of bolt anchoring strength in concrete based on support vector machine for regression. There are 30 groups of experimental data of anchoring strength. Two-thirds of those groups are selected as training samples, and the others are selected as predicted samples to forecast anchorage strength. Then the predicted results are compared with the test result and BP network result. Comparison suggest that this model has high prediction accuracy and good generalization ability, and the prediction results are credible. It is reasonable and effective to apply SVM to predict the anchorage strength in concrete.
[1]汤 雷,陆士良,高加胜. 锚杆拉拔试验的意义. 矿山压力与顶板管理,1996, (2):68-70. (TANG Lei, LU Shi-liang, GAO Jia-sheng. Significance of Bolt Pullout Test. Ground Pressure and Strata Control, 1996, (2):68-70. (in Chinese))
[2] 杨双锁,张百胜.锚杆对岩土体作用的力学本质.岩土力学,2003,24(增):279-282. (YANG Shuang-suo, ZHANG Bai-sheng. The Influence of Bolt Action Force to the Mechanical Property of Rocks. Rock and Soil Mechanics, 2003,24(Sup.):279-282. (in Chinese))
[3] 康红普,姜铁明,高富强. 预应力在锚杆支护参数的设计.煤炭学报, 2008,33(7) : 721-726. (KANG Hong-pu, JIANG Tie-ming, GAO Fu-qiang. Design for Pretensioned Rock Bolting Parameters. Journal of China Coal Society, 2008, 33(7) : 721-726.(in Chinese))
[4] 舒谷生,彭文祥,何忠明. 全长粘结式锚杆拉拔试验的数值实现. 科技导报,2009,27(12):47-50. (SHU Gu-sheng, PENG Wen-xiang, HE Zhong-ming. Numerical Simulation of the Pullout Test of Wholly Grouted Cable. Science and Technology Review, 2009, 27(12): 47-50. (in Chinese))
[5] 谷拴成,崔希鹏. 混凝土中锚杆锚固荷载传递特性研究.混凝土,2010,(10):27-30. (GU Shuan-cheng, CUI Xi-peng. Characteristic Research on the Anchorage Load Transfer of Bolt in Concrete. Concrete, 2010, (10):27-30. (in Chinese))
[6] 徐 波,吴智敏. 混凝土中锚杆荷载传递机理的理论分析. 哈尔滨工业大学学报,2006,38(3):417-419. (XU Bo, WU Zhi-min. Analysis of Load-transfer Mechanism of Anchors in Concrete. Journal of Harbin Institute of Technology. 2006,38(3):417-419. (in Chinese))
[7] VAPNIK V N. The Nature of Statistical Learning Theory, (Second Edition). New York: Spring-Verlag, 1999.
[8] 陈 斌,郭雪莽,刘国华. 基于粗糙集(RS )和支持向量机( SVM)的混凝土性能预测实证研究. 水力发电学报,2011,30(6):251-257. (CHEN Bin, GUO Xue-mang, LIU Guo-hua. Prediction of Concrete Properties Based on Rough Sets and Support Vector Machine Method. Journal of Hydroelectric Engineering, 2011,30(6): 251- 257. (in Chinese))
[9] 武换娥,丁圣果,巩玉志,等. 支持向量回归机在混凝土强度预测中的应用研究. 工业建筑,2007,37(增1):991-995. (WU Huan-e, DING Sheng-guo, GONG Yu-zhi, et al. Research on Support Vector Machine’s Prediction of Concrete Strength. Industrial Construction, 2007,37(Sup.1):991-995. (in Chinese))
[10]崔海霞. 高强混凝土强度预测的支持向量机模型及应用. 混凝土,2010,(5):49-51. (CUI Hai-xia. Strength Prediction of High Strength Concrete Using SVM and Its Application. Concrete, 2010,(5): 49-51. (in Chinese))
[11]朱怡翔,石广仁. 火山岩岩性的支持向量机识别. 石油学报,2013,34(2):312-322. (ZHU Yi-xiang, SHI Guang-ren. Identification of Lithological Characteristics of Volcanic Rocks by Support Vector Machine. Acta Petrolei Sinica, 2013,34(2):312-322. (in Chinese))
[12]冯夏庭,赵洪波. 岩爆预测的支持向量机. 东北大学学报(自然科学版),2002,23(1):57-59. (FENG Xia-ting, ZHAO Hong-bo. Prediction of Rockburst Using Support Vector Machine. Journal of Northeastern University (Natural Science), 2002, 23(1): 57-59. (in Chinese))
[13]赵洪波 ,冯夏庭. 非线性位移时间序列预测的进化-支持向量机方法及应用. 岩土工程学报,2003,25(4):468-471. (ZHAO Hong-bo, FENG Xia-ting. Study and Application of Genetic Support Vector Machine for Nonlinear Displacement Time Series Forecasting. Chinese Journal of Geotechnical Engineering, 2003, 25(4):468-471. (in Chinese))
[14]VAPNIK V, LERNER A. Pattern Recognition Using Generalized Portrait Method. Automation and Remote Control, 1963, (24): 774-780.
[15]VAPNIK V. Estimation of Dependence Based on Empirical Data. New York: Springer-Verlag, 1982.
[16]CORTES C, VAPNIK V. Support Vector Networks. Machine Learning, 1995, (20): 1-25.
[17]陈永义,余小鼎,高学浩. 处理非线性分类和回归问题的一种新方法(Ⅰ)——支持向量机方法简介. 应用气象学报,2004,15(3):345-354. (CHEN Yong-yi, YU Xiao-ding, GAO Xue-hao. A New Method for Non-linear Classify and Non-linear Regression Ⅰ: Introduction to Support Vector Machine. Quarterly Journal of Applied Meteorology, 2004, 15(3): 345-354. (in Chinese))
[18]燕孝飞,葛洪伟,颜七笙. RBF核SVM及其应用研究. 计算机工程与设计,2006,27(11):1996-2011. (YAN Xiao-fei, GE Hong-wei, YAN Qi-sheng. SVM with RBF Kernel and Its Application Research. Computer Engineering and Design, 2006, 27(11): 1996-2011. (in Chinese))
[19]邓乃扬,田英杰. 数据挖掘中的新方法-支持向量机.北京:科学出版社, 2005. (DENG Nai-yang, TIAN Ying-jie. New Method of Data Mining: Support Vector Machine. Beijing: Science Press, 2005. (in Chinese))
