费鸿禄,左壮壮,蒋安俊,包世杰
FEI Hong-lu,ZUO Zhuang-zhuang,JIANG An-jun,BAO Shi-jie

• 1:辽宁工程技术大学爆破技术研究院

摘要(Abstract)：

为了保证爆破作业时周围建筑物的稳定，需要提高对峰值爆破振动速度预测的准确性。运用Kennard-Stone算法优化训练样本，采用网络搜索算法获得支持向量回归机的最优惩罚系数和核函数参数，构建KS-GS-SVR的峰值爆破振速预测模型。结合湖北铜录山现场露天台阶爆破的振速实测数据，选取影响爆破振动速度的8个主要因素作为模型的输入变量，运用KS-GS-SVR模型进行峰值振速预测，并将KS-GS-SVR模型预测结果分别与GS-SVR、KS-GA-BP、KS-萨氏公式模型预测结果对比分析。结果表明，相比于GS-SVR的预测结果，KS-GS-SVR模型预测结果的平均相对误差降低了4.31%,说明Kennard-Stone算法通过优化训练样本提高了预测精度。KS-GS-SVR模型预测结果的平均相对误差为12.17%,明显低于其他模型，说明KS-GS-SVR模型学习和泛化能力更强，预测精度更高。所构建的预测模型可供类似工程爆破振速峰值预测借鉴。
In order to ensure the stability of surrounding buildings during blasting operations, it is necessary to improve the accuracy of the prediction of peak blasting vibration velocity. The Kennard-Stone algorithm is used to optimize the training samples, and the network search algorithm is used to obtain the optimal penalty coefficient and kernel function parameters of the support vector regression machine, and the KS-GS-SVR peak blasting vibration velocity prediction model is constructed. Based on the measured data of vibration velocity of open-air bench blasting at Tonglushan site in Hubei, eight main factors affecting blasting vibration velocity are selected as the input variables of the model, and the KS-GS-SVR model is used to predict the peak vibration velocity, and KS-GS-SVR model prediction results of are compared with those of GS-SVR, KS-GA-BP, and KS-Sachs formula model respectively. The results show that compared with the prediction results of GS-SVR, the average relative error of the prediction results of the KS-GS-SVR model is reduced by 4.31%, indicating that the Kennard-Stone algorithm improves the prediction accuracy by optimizing the training samples. The average relative error of the prediction results of the KS-GS-SVR model is 12.17%, which is significantly lower than other models, indicating that the KS-GS-SVR model has stronger learning and generalization capabilities and higher prediction accuracy. The constructed prediction model can be used as a reference for the prediction of peak blasting vibration velocity in similar projects.

关键词(KeyWords)： 峰值爆破振速;网格搜索;支持向量机;预测
peak blasting vibration velocity;grid search;support vector machine;prediction

Abstract:

Keywords:

基金项目(Foundation):

作者(Author): 费鸿禄,左壮壮,蒋安俊,包世杰
FEI Hong-lu,ZUO Zhuang-zhuang,JIANG An-jun,BAO Shi-jie

DOI: 10.19931/j.EB.20210389

参考文献(References)：

• [1] 苟倩倩，赵明生，池恩安，等.基于PCA-BP神经网络在爆破振动评价要素中的预测及应用[J].矿业研究与开发，2018,38(12):97-102.GOU Q Q,ZHAO M S,CHI E A,et al.Prediction and application of blasting vibration evaluation elements based on PCA-BP neural network[J].Mining Research and Development,2018,38(12):97-102.
• [2] 郭钦鹏，杨仕教，朱忠华，等.运用GA-BP神经网络对爆破振动速度预测[J].爆破，2020,37(3):148-152.GUO Q P,YANG S J,ZHU Z H,et al.Using GA-BP neural network to predict blasting vibration velocity[J].Blasting,2020,37(3):148-152.
• [3] 陈秋松，张钦礼，陈新，等.基于GRA-GEP的爆破峰值速度预测[J].中南大学学报(自然科学版),2016,47(7):2 441-2 447.CHEN Q S,ZHANG Q L,CHEN X,et al.Prediction of peak blasting velocity based on GRA-GEP[J].Journal of Central South University (Natural science edition),2016,47(7):2 441-2 447.
• [4] 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):1 258-1 261.LU E W,SHI X Z,CHEN J Y.Research on the prediction of peak velocity of blasting vibration based on small sample volume of LS-SVR[J].World Science and Technology Research and Development,2016,38(6):1 258-1 261.
• [5] 史秀志.爆破振动信号时频分析与爆破振动特征参量和危害预测研究[D].长沙：中南大学，2007.SHI X Z.Time-frequency analysis of blasting vibration signal and research on characteristic parameters of blasting vibration and hazard prediction[D].Changsha:Central South University,2007.
• [6] 张明理，杨晓亮，滕云，等.基于主成分分析与前向反馈传播神经网络的风电场输出功率预测[J].电网技术，2011,35(3):183-187.ZHANG M L,YANG X L,TENG Y,et al.Wind farm output power prediction based on principal component analysis and forward feedback propagation neural network[J].Power System Technology,2011,35(3):183-187.
• [7] 窦希杰，王世博，谢洋，等.基于IMF能量矩和SVM的煤矸识别[J].振动与冲击，2020,39(24):39-45.DOU X J,WANG S B,XIE Y,et al.Coal gangue recognition based on IMF energy moment and SVM[J].Journal of Vibration and Shock,2020,39(24):39-45.
• [8] 郁磊，史峰，王辉，等.MATLAB智能算法30个案例分析[M].北京：北京航空航天大学出版社，2015.YU L,SHI F,WANG H,et al.Analysis of 30 cases of MATLAB intelligent algorithm[M].Beijing:Beijing University of Aeronautics and Astronautics Press,2015.
• [9] 高宝成，陶博文.基于SVR算法的混凝土强度预测[J].城市住宅，2019,26(4):143-146.GAO B C,TAO B W.Concrete strength prediction based on SVR algorithm[J].Urban Housing,2019,26(4):143-146.
• [10] 张腰，杨庆东.基于GS-SVM的数控机床热误差预测研究[J].机械工程师，2019(11):36-38.ZHANG Y,YANG Q D.Research on thermal error prediction of CNC machine tools based on GS-SVM[J].Mechanical Engineer,2019(11):36-38.
• [11] 李烨，贾进章.基于改进GS-SVM的煤矿冲击地压预测研究[J].世界科技研究与发展，2016,38(4):758-762.LI Y,JIA J Z.Research on coal burst forecast based on improved GS-SVM[J].World Science and Technology Research and Development,2016,38(4):758-762.