岳衡,韩翔宇,张继春,潘强,李鹏川,阳陶
YUE Heng,HAN Xiang-yu,ZHANG Ji-chun,PAN Qiang,LI Peng-chuan,YANG Tao

• 1:西南交通大学土木工程学院

摘要(Abstract)：

目前桩孔开挖主要依靠工程类比进行,不同设计者设计的爆破参数往往因掌握的爆破理论和经验的不同而有所差异,爆破质量参差不齐。为此,提出基于遗传算法GA改进BP神经网络(GA-BP)建立爆破参数优化设计模型,该法不仅可以利用已有爆破经验数据和工程地质条件,同时,使用遗传算法优化BP神经网络阈值和权值可以弥补BP神经网络不稳定的缺陷,以达到获得更优爆破参数的目的。实践表明,基于遗传算法改进BP神经网络相比一般BP神经网络预测相对误差较小,同时GA-BP神经网络得到的优化爆破参数进行现场试验,取得了良好的爆破效果。因此,GA-BP神经网络模型应用于抗滑桩孔开挖爆破参数设计是可行的,可用于指导爆破施工。
Currently,the pile holes are excavated mainly relying on the engineering analogy,but the blasting parameters designed by different theories and experience and the effect of blasting are different.Therefore,BP neural network improved by genetic algorithm was provided and the model of optimization of blasting parameters was set up.The sample data obtained from good blasting effect and geology of practical engineering could be used,and GA could make up the defect of BP neural network which was not stable through optimizing the threshold and weight of BP neural network,and the purpose of obtaining the better blasting parameters was achieved.The practice showed that relative errors of prediction of GA-BP neural network were fewer than the general BP neural network,and it achieved a good result after field test using the optimized blasting parameters.GA-BP neural network model was well applied in the blasting parameters design of excavation of slide-resistant pile hole,it was feasible and could be used to guide the construction of blasting.

关键词(KeyWords)： 爆破参数优化;BP神经网络;遗传算法;现场试验;桩孔开挖;爆破开挖
Blasting parameters optimization;BP neural network;GA;Field test;Pile hole excavation;Blasting excavation

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(41272321)

作者(Author): 岳衡,韩翔宇,张继春,潘强,李鹏川,阳陶
YUE Heng,HAN Xiang-yu,ZHANG Ji-chun,PAN Qiang,LI Peng-chuan,YANG Tao

参考文献(References)：

• [1]程远学,程康,周子然,等.人工挖孔桩爆破开挖技术探讨[J].土工基础,2007,21(4):5-6.CHENG Yuan-xue,CHENG Kang,ZHOU Zi-ran,et al.Discussion of explosive excavation technique of handdug pile[J].Soil Eng.and Foundation,2007,21(4):5-6.
• [2]张成良,杨阳,梁开水,等.岩壁梁爆破参数优化的神经网络模型[J].工程爆破,2006,12(1):22-26.ZHANG Cheng-liang,YANG Yang,LIANG Kai-shui,et al.Neural network model of blasting parameters optimization of crane beam at rock wall[J].Engineering blasting,2006,12(1):22-26.
• [3]张继春,蔡德所,胡铁松.基于神经网络理论的岩体爆破效应预测[J].东北大学学报,1995,16(增刊):101-106.ZHANG Ji-chun,CAI De-suo,HU Tie-song.Rock blasting effect forecast based on neural network theory[J].Journal of Northeast University,1995,16(Sup.):101-106.
• [4]张磊.入岩控制爆破技术在铁路桥梁挖孔桩中的应用[J].山西建筑,2011,37(27):193-194.ZHANG Lei.The application of controlled blasting into the rock technology in railway bridge digging piles[J].Shanxi Architecture,2011,37(27):193-194.
• [5]林文强,苏阳,欧阳衡.人工挖孔桩工程孔内基岩爆破设计和施工简介[J].水运工程,2001(2):56-58.LIN Wen-qiang,SU Yang,OUYANG Heng.Design and construction of in-hole base rock explosive for artificial excavation-hole pile engineering[J].Port&Waterway Engineering,2001(2):56-58.
• [6]刘召芹.光面爆破技术在人工挖孔桩中的应用[J].西部探矿工程,2001,69(2):89-90.LIU Zhao-qin.Smooth blasting technology applied in the manual excavating pile[J].West-china Explosive Engineering,2001,69(2):89-90.
• [7]柴毅,尹宏鹏,李大杰,等.基于改进遗传算法的BP神经网络自适应优化设计[J].重庆大学学报(自然科学版),2007,30(4):91-96.CHAI Yi,YIN Hong-peng,LI Da-jie,et al.Self-adaptation optimize BP neural design based on the genetic algorithms[J].Journal of Chongqing University(Natural Science Edition),2007,30(4):91-96.
• [8]姚金阶,朱以文.岩体爆破参数设计的神经网络模型[J].爆破,2005,22(2):34-37.YAO Jin-jie,ZHU Yi-wen.The neural network model of rock blasting parameters design[J].Blasting,2005,22(2):34-37.
• [9]刘庆,张光权,吴春平,等.基于BP神经网络模型的爆破飞石最大飞散距离预测研究[J].爆破,2013,30(1):115-118.LIU Qing,ZHANG Guang-quan,WU Chun-ping,et al.Research on maximum distance prediction of blast fly rock based on BP neutral work[J].Blasting,2013,30(1):115-118.
• [10]郑长青,陈庆寿,徐海波,等.基于神经网络的台阶爆破参数优化设计[J].爆破,2008,25(3):22-25.ZHENG Chang-qing,CHEN Qing-shou,XU Hai-bo,et al.Bench blasting design and optimization based on neural network[J].Blasting,2008,25(3):22-25.
• [11]杨建刚.人工神经网络实用教程[M].杭州:浙江大学出版社,2002.YANG Jian-gang.Practical artificial neural network tutorial[M].Hangzhou:Zhejiang University Press,2002.
• [12]陈德志,朱瑞赓,徐顺香.基于BP神经网络的路堑爆破对邻近民房安全预测的研究[J].岩石力学与工程学报,2002,21(S2):2554-2557.CHEN De-zhi,ZHU Rui-geng,XU Shun-xiang.BPneural network study on safety prediction for civil houses adjacent to cutting blasting[J].Chinese Journal of Rock Mechanics and Engineering,2002,21(S2):2554-2557.
• [13]范睿,李国斌,景韶光.基于实数编码遗传算法的混合神经网络算法[J].计算机仿真,2006,23(1):161-162.FAN Rui,LI Guo-bin,JING Shao-guang.A method of mixed neural network based on real-coded genetic algorithm[J].Computer simulation,2006,23(1):161-162.
• [14]罗学东,范新宇,代贞伟,等.BP神经网络模型在露天矿爆破振动参数预测中的应用及修正[J].中南大学学报(自然科学版),2013,44(1):5020-5024.LUO Xue-dong,FAN Xin-yu,DAI Zhen-wei,et al.BP neural network application and model modification in prediction of open-pit mine blasting vibration parameters[J].Journal of Central South University,2013,44(1):5020-5024.
• [15]爆破安全规程GB 6722-2014[S].北京:中国标准出版社,2014.Safety regulations for blasting GB 6722-2014[S].Beijing:China Standards Press,2014.