基于BP神经网络的围岩介质爆炸峰值压力预测

郭璇1,2,马思远1,郭一帆1,张晓新3

振动与冲击 ›› 2019, Vol. 38 ›› Issue (3) : 199-206.

PDF(1172 KB)
PDF(1172 KB)
振动与冲击 ›› 2019, Vol. 38 ›› Issue (3) : 199-206.
论文

基于BP神经网络的围岩介质爆炸峰值压力预测

  • 郭璇1,2,马思远1,郭一帆1,张晓新3
作者信息 +

Blast peak pressure prediction for surrounding rock medium based on BP neural network method

  • GUO Xuan1,2,MA Siyuan1, GUO Yifan1, ZHANG Xiaoxin3
Author information +
文章历史 +

摘要

基于BP(Back Propagation)神经网络法,收集对比130个公开的地下封闭爆炸数据,区分粘土、砂性土和岩石三组围岩介质,简化地下任意点爆炸围岩介质峰值力的多因素影响,分析爆炸比例距离、纵波波速、密度和饱和度等特征参数产生的权重影响,考察爆冲的输出峰值压力特征,提出土中任一点围岩介质峰值压力的简易预测方法,并通过与经验方法对比,验证简易方法的实效性。利用Matlab®建立不同隐含层单元数的BP(Back-Propagation)神经网络,当隐含层分别选择6、7、6个神经元时整体网络性能最佳,该条件下对比测试样本的BP神经网络、经验公式和多元回归分析方法(MVRA)的预测效果,BP神经网络方法得到最小平均绝对误差。在各围岩介质数据的误差对比分析中,BP神经网络法得到砂性土的预测误差相对最小,相比经验公式和多元回归分析优势明显。在同一围岩介质参数的敏感度分析中,纵波波速对峰值压力产生最显著影响。将工程实例参数带入对比BP神经网络和MVRA,考虑不同介质反射系数得到峰值压力预测值和拱顶爆炸荷载峰值实测值的相对误差可小于20%。该估算方法可为类似地下结构防护设计值提供一种简化参考。

Abstract

Here, based on the BP neural network method, 130 open data sets of underground closed blasts were collected and compared to distinguish three groups of surrounding rock medium including clay, sandy soil and rock, and influences of multi-factor on surrounding rock medium peak pressure of arbitrary point explosion in soil were simplified.The weight influences produced by characteristic parameters of blast scaled distance, longitudinal wave velocity, density and saturation level were analyzed to investigate blast impact’s output peak pressure characteristics and propose the simple prediction method for surrounding rock medium blast peak pressure of arbitrary point in soil.Through comparing with the empirical method, the effectiveness of the simple method was verified.BP neural networks with different hidden layer elements were built using the software MATLAB.It was shown that when the hidden layer has 6, 7, 6 neurons, respectively, the overall network performance is the best; under this condition, comparing BP neural network, empirical formula and multi-variable regression analysis (MVRA) prediction results for measured samples, the BP neural network method obtains the minimum average absolute error; in the error contrastive analysis for surrounding rock medium data, the BP neural network method’s prediction error for sandy soil medium is relatively minimum to have obvious advantages compared with empirical formula and MVRA; in the sensitivity analysis for the same surrounding rock medium parameter, longitudinal wave velocity affects peak pressure most obviously; the actual engineering example’s parameters are brought into the BP neural network method and MVRA for comparison, the relative error between the peak pressure predicted values considering different mediums’ reflect coefficients and the actual measured blast load peak value at the dome can be less than 20%.The proposed estimation method provided a simplified reference for the protection design of similar underground structures.

关键词

BP神经网络 / 围岩介质 / 峰值压力 / 预测值 / 爆炸荷载

Key words

BP (back propagation)neural networks / Surrounding rock Mass / peak pressure / prediction value / blast loads

引用本文

导出引用
郭璇1,2,马思远1,郭一帆1,张晓新3. 基于BP神经网络的围岩介质爆炸峰值压力预测[J]. 振动与冲击, 2019, 38(3): 199-206
GUO Xuan1,2,MA Siyuan1, GUO Yifan1, ZHANG Xiaoxin3. Blast peak pressure prediction for surrounding rock medium based on BP neural network method[J]. Journal of Vibration and Shock, 2019, 38(3): 199-206

参考文献

[1] U.S. Department of the Army. Fundamentals of Protective Design for Conventional Weapons, Department of the Army[S].TM5-855-1,1996.
[2] 洪武, 徐迎, 金丰年, 范华林. 地下拱形结构爆炸响应计算二维和三维模型比较[J], 振动与冲击, 2014, 33(9): 142-147. (Hong Wu, Xu Ying, Jin Fengnian, Fan Hualin. Comparison between 2 D and 3 D models for computing blast responses of buried arching structures[J], Journal of Vibration and Shock, 2014, 33(9): 142-147.(in Chinese))
[3] 张小勇, 龚顺风. 隧道内爆炸作用下衬砌结构损伤机理及抗爆性能研究[J], 振动与冲击, 2013, 32(22): 193-199. (Zhang Xiaoyong, Gong Shunfeng. Damage mechanism and anti-explosion behavior of tunnel lining structures under internal blast loading[J], Journal of Vibration and Shock, 2013, 32(22): 193-199. (in Chinese))
[4] 赵跃堂, 易义君, 储程. 一种提高管片隧道衬砌结构抗内爆炸性能的工程措施研究[J], 振动与冲击, 2017, 36(8): 41-47. (Zhao Yuetang, Yi Yijun, Chu Cheng. A method to improve internal explosion resistance performance of segmental lining structures[J], Journal of Vibration and Shock, 2017, 36(8):41-47.  (in Chinese))
[5] 刘扬, 宋春明, 卢浩. 爆炸荷载下盾构管片的动力响应分析[J], 振动与冲击, 2014, 33(5): 120-124. (Liu Yang, Song Chunming, Lu Hao. A simplified calculation method for dynamic response of a shield tunnel segment subjected to explosion loads[J], Journal of Vibration and Shock, 2014, 33(5): 120-124. (in Chinese))
[6] Ляхов Г.М,Покровский Г.И.Взрывные волны в грунтах[M]. Госгортехиздат,1962.
[7] 周丰峻,黄能法,王双进. 饱和土中应力波传播计算[J].流体力学实验与测量,1998,3(12):48–52.(Zhou Fengjun,Huang Nengfa,Wang Shuangjin. Propagation calculation of stress waves in saturated soils[J].Chinese Journal of Experiments and Measurements in Fluid Mechanics,1998,3(12):48-52.(in Chinese))
[8] Henrych, J,GR Abrahamson.The dynamics of explosion and its use[M].New York:1979.
[9] 叶亚齐,任辉启,李永池,吴祥云,姚哲芳.砂质黏土中不同深度爆炸围岩介质地冲击参数预计方法研究[J].,岩石力学与工程学报,2011,30 (9):1918-1923.(YE Yaqi,REN Huiqi,LI Yongchi,WU Xiangyun,YAO Zhefang.Study of prediction of ground shock parameters in free field at different depths of burst in sandy clay [J].Chinese Journal of Rock Mechanics and Engineering,2011,30 (9):1918-1923.(in Chinese a))
[10] 王占江,李孝兰,戈琳,王培宇.花岗岩中化爆的围岩介质应力波传播规律分析[J].,岩石力学与工程学报,2003,22(11):1827-1831. (Wang Zhanjang,li Xiaolan,Ge Lin,Wang Peiyu.Free-field stress wave propagation induced by underground chemical explosion in granite [J].Chinese Journal of Rock Mechanics and Engineering,2003,22(11):1827-1831.(in Chinese))
[11] Al-Qasimi E, Charlie W, Woeller D.Canadian Liquefaction Experiment (CANLEX): Blast-Induced Ground Motion and Pore Pressure Experiments[J].Astm Geotechnical Testing Journal,2005,28(1):9-21.
[12] William R.Perret,Robert C.Bass.Free-Field Ground Motion Induced by Underground Explosions[R].Sandia National Laboratories,1975.
[13] EC Leong,S Anand,HK Cheong,CH Lim.Re-examination of peak stress and scaled distance due to ground shock[J].International Journal of Impact Engineering,2007,34(9):1487-1499.
[14] 市野宏嘉,大野友則,別府万寿博,蓮江和夫.爆薬の地中爆発において地盤の粒度組成および飽和度が爆土圧特性に及ぼす影響[J].土木学会論文集C,2008,2(64):353-368.
Effects of soil properties on ground shock pressure due to explosion in the subsurface soil,Hiroyoshi Ichino,Tomonori Ohno,Masuhiro Beppu, Kazuo Hasue, Journal of  the Japan Society of Civil Engineers C,2008,2(64):353-368.
[15] Gefken Paul R,Florence Alexander L,Sanai Mohsen, Spherical waves in saturated sand[R].Naval Surface Warfare Center,1996.
[16] 谢锋云,江炜文,陈红年等.基于广义BP神经网络的切削颤振识别研究,振动与冲击,2018,37(5):65-70
XIE Fengyun,JIANG Weiwen,CHEN Hongnian et al.Cutting chatter recognition based on generalized BP neural network,Journal of Vibration and Shock,2018,37(5):65-70
[17] 李磊,秦卫阳,张劲夫.采用BP神经网络进行混沌运动控制,振动与冲击,2006,25(5):89-91
Li Lei, QinWeiyang, Zhang Jinfu, Controlling chaosmotion to approach arbitrary objective orbit by bp neural network, Journal of Vibration and Shock,2006,25(5):89-91
[18] MT Hagan,MB Menhaj.Training Feed forward Networks with the Marquardt Algorithm[J].IEEE Transactions on Neural Networks,1994,5(6):989-993.
[19] H Chen,J Zhou,H Fan,F Jin,Y Xu. Dynamic responses of buried arch structure subjected to subsurface localized impulsive loading Experimental study[J].International Journal of Impact Engineering,2014,65(65):89–101.
[20] Y Yang,Q Zhang. A hierarchical analysis for rock engineering using artificial neural networks[J].Rock Mechanics and Rock Engineering,1997,30(4):207-222.

PDF(1172 KB)

Accesses

Citation

Detail

段落导航
相关文章

/