基于ACOR-LSSVM算法的爆破振动速度预测Blasting Vibration Velocity Prediction based on ACOR-LSSVM Algorithm
郑皓文,赵根,胡英国,柴朝政
摘要(Abstract)：
由于工程地质条件复杂,传统的方法很难准确预测爆破振动速度。引入连续域蚁群算法(ACOR),对最小二乘支持向量机(LS-SVM)进行参数优化,构建连续域蚁群最小二乘法爆破振动速度预测模型(ACOR-LSSVM)来提高预测精度。结合白鹤滩水电站左岸坝肩槽开挖过程中的40组爆破监测数据,分别采用ACOR-LSSVM、LS-SVM模型与萨氏公式进行爆破振动速度预测,三者的平均绝对相对误差分别为3.16%、10.07%、22.96%。相比之下,ACOR-LSSVM模型预测精度更高,泛化能力更强,在爆破振动速度预测中具有一定的理论意义和工程应用价值。
关键词(KeyWords)： 连续域蚁群算法;最小二乘支持向量机;坝肩槽开挖;爆破振动速度
基金项目(Foundation): 国家自然科学青年基金项目(51609017)
作者(Author): 郑皓文,赵根,胡英国,柴朝政
参考文献(References)：
- [1]史秀志,郭霆,尚雪义,等.基于PCA-BP神经网络的岩石爆破平均粒径预测[J].爆破,2016,33(2):55-61.SHI Xiu-zhi,GUO Ting,SHANG Xue-yi,et al.Prediction of mean particle size of rock blast on combination of PCA and BP neural networks[J].Blasting,2016,33(2):55-61.(in Chinese)
- [2]蒲传金,郭王林,秦晓星,等.基于BP神经网络的桩基爆破振动速度预测[J].爆破,2018,35(2):177-181.PU Chuan-jin,GUO Wang-lin,QIN Xiao-xing,et al.Prediction of blasting vibration velocity of pile foundation based on BP neural network[J].Blasting,2018,35(2):177-181.(in Chinese)
- [3]黄伟杰,吴叶,陈志坚,等.基于ACO-SVM的桥梁基础群桩轴力预测[J].长江科学院报,2016,33(1):121-125.HUANG Wei-jie,WU Ye,CHEN Zhi-jian,et al.Prediction on axial force of pile group in bridge foundation based on ACO-SVM[J].Journal of Yangtze River Scientific Research Institute,2016,33(1):121-125.(in Chinese)
- [4]邵良杉,白媛,邱云飞,等.露天采矿爆破振动对民房破坏的LS-SVM预测模型[J].煤炭学报,2012,37(10):1637-1642.SHAO Liang-shan,BAI Yuan,QIU Yun-fei,et al.LS-SVM analysis model and its application for prediction residential house's damage against blasting vibration from open pit mining[J].Journal of China Coal Society,2012,37(10):1637-1642.(in Chinese)
- [5]马晨阳,张汉斌,袁青,等.基于人工智能方法的地下洞室群爆破振动速度预测[J].爆破,2017,34(4):12-16.MA Chen-yang,ZHANG Han-bin,YUAN Qing,et al.Research of underground caverns blasting vibration velocity prediction based on artificial intelligence method[J].Blasting,2017,34(4):12-16.(in Chinese)
- [6]孙苗,吴立,袁青.基于PSO-LSSVM算法的地下储气库洞室群爆破振动预测[J].爆破,2017,34(3):145-150.SUN Miao,WU Li,YUAN Qing.Blasting vibration prediction of underground gas storage caverns based on PSOLSSVM algorithm J].Blasting,2017,34(3):145-150.(in Chinese)
- [7]汪旭光.爆破设计与施工[M].北京:冶金工业出版社,2013.
- [8]陈烨.用于连续函数优化的蚁群算法[J].四川大学学报(工程科学版),2004,36(6):117-121.CHEN Ye.Ant colony system for continuous function optimization[J].Journal of Sichuan University(Engineering Science Edition),2004,36(6):117-121.(in Chinese)
- [9]段海滨.蚁群算法原理及其应用[M].北京:科学出版社,2005.
- [10]卢二伟,史秀志,陈佳耀.基于LS-SVR小样本容量的爆破振动峰值速度预测研究[J].世界科技研究与发展,2016,38(6):1258-1261.LU Er-wei,SHI Xiu-zhi,CHEN Jia-yao.Prediction research for blasting-vibration-peak-speed based on LSSVR in small sample space[J].World Sci-Tech R&D,2016,38(6):1258-1261.(in Chinese)
- [11]阎辉,张学工,李衍达.支持向量机与最小二乘法的关系研究[J].清华大学学报(自然科学版),2001,41(9):77-80.YAN Hui,ZHANG Xue-gong,LI Yan-da.Relation between a support vector machine and the least square method[J].Journal of Tsinghua University(Science and Technology),2001,41(9):77-80.(in Chinese)