史秀志,董凯程,邱贤阳,陈小康
SHI Xiu-zhi,DONG Kai-cheng,QIU Xian-yang,CHEN Xiao-kang(School of Resources and Safety Engineering

• 1:中南大学资源与安全工程学院

摘要(Abstract)：

运用支持向量机回归(SVMR)预测理论,对爆破振动质点振动速度进行预测,并与实测数据进行对比分析。通过与RBF神经网络、传统预测方法进行对比分析,运用支持向量机回归理论预测方法能较好地预测爆破振动速度,对研究爆破振动特征及灾害控制具有一定意义。
This article predicted the PPV of blasting vibration and contrasted the results with the measured data based on support vector machine regression(SVMR) prediction theory.With the comparative analysis between the RBF neural network and traditional prediction method,the fact that the method based on support vector machine regression theory could make a better prediction of the PPV of blasting vibration and reduce prediction inaccuracy was revealed,showing the significance of the study of blasting vibration characteristics and the control of disasters caused by blasting.

关键词(KeyWords)： 支持向量机回归;质点振速峰值;预测
Supportive Vector Machine Regression(SVMR);Peak Particle Velocity(PPV);Prediction

Abstract:

Keywords:

基金项目(Foundation):

作者(Author): 史秀志,董凯程,邱贤阳,陈小康
SHI Xiu-zhi,DONG Kai-cheng,QIU Xian-yang,CHEN Xiao-kang(School of Resources and Safety Engineering

参考文献(References)：

• [1]唐海,石永强,李海波,等.基于神经网络的爆破振动速度峰值预报[J].岩石力学与工程学报,2007,26(1):3534-3538.
• [2]史秀志,王怀勇,田建军,等.基于灰关联法的爆破振动对民房破坏致因因素的敏感性分析[J].爆破,2008,25(3):9-12.
• [3]史秀志.爆破振动信号时频分析与爆破振动预测研究[D].长沙:中南大学,2007.
• [4]史耀媛.基于支持向量机的股市分析与预测方法研究[D].西安:西北工业大学,2006.
• [5]杨俊燕,张优云,赵荣珍.支持向量机在机械设备振动信号趋势预测中的应用[J].西安交通大学学报,2005,39(9):950-952.
• [6]郝惠敏,汤晓君,白鹏,等.基于核主成分分析和支持向量回归机的红外光谱多组分混合气体定量分析[J].光谱学与光谱分析,2008,28(6):1286-1288.
• [7]林继鹏,刘君华.基于小波的支持向量机算法研究[J].西安交通大学学报,2005,39(9):816-819.
• [8]Chih-wei Hsu,Chih-jen Lin.Acomparison of methodsfor multiclass support vector machines[J].IEEE Trans.on Neural Networks,2002,13(2):415-425.
• [9]荆双喜,华伟.基于小波-支持向量机的矿用通风机故障诊断[J].煤炭学报,2007,32(1):99-102.
• [10]Yao-Wen Hsueh,Chan-Yun Yang.Prediction of toolbreakage in face milling using support vector machine[J].Int J Adv Manuf Technol(2008)37:872-880.
• [11]吴青,刘三阳,杜喆.回归型模糊最小二乘支持向量机[J].西安电子科技大学学报(自然科学版),2007,34(5):774-777.