基于改进PSO&ndash;BP神经网络的爆破振动速度峰值预测

PDF(3289 KB)

振动与冲击 ›› 2022, Vol. 41 ›› Issue (16) : 194-203.

论文

基于改进PSO–BP神经网络的爆破振动速度峰值预测

范勇1，裴勇1，杨广栋1，冷振东1，2，卢文波3

作者信息 +

Prediction of blasting vibration velocity peak based on an improved PSO-BP neural network

FAN Yong1,PEI Yong1,YANG Guangdong1,LENG Zhendong1,2,LU Wenbo3

Author information +

文章历史 +

摘要

为了提高爆破振动速度峰值预测的准确度，将BP(back propagation)神经网络解决复杂非线性函数逼近能力和粒子群优化 (particle swarm optimization ,PSO) 算法全局寻优能力相结合，建立了改进的PSO–BP神经网络预测模型，利用改进的PSO算法来优化BP神经网络的初始权值和阈值。以白鹤滩水电站左岸坝肩槽爆破开挖监测数据为依据，选取爆心距、最大单响药量、高程差和纵波波速作为输入参数，通过余弦振幅法分析输入参数与爆破振动速度峰值的关系强度得出代表场地条件的纵波波速也是对爆破振动速度传播的重要影响因素。对比BP神经网络和萨道夫斯基公式的检验结果，结果表明：改进的PSO–BP神经网络预测模型的预测值与实测值吻合更好，预测的结果更为可靠，具有较好泛化能力。研究方法为类似工程中爆破振动速度峰值的预测提供了借鉴。
关键词：爆破振动；爆破振动速度峰值；BP神经网络；粒子群优化(PSO)算法；纵波波速

Abstract

In order to improve the accuracy of blasting vibration velocity peak prediction, the ability of back propagation (BP) neural network to solve complex nonlinear function approximation and the global optimization ability of particle swarm optimization (PSO) are combined, establishment the improved PSO–BP neural network prediction model, using the improved PSO to optimize the initial weight and threshold of BP neural network. Based on blasting excavation monitoring data of dam abutment on left bank of Baihetan hydropower station, selecting blast center distance, maximum charge per delay, height difference and longitudinal wave velocity as input parameters, the strengths of the relations between the input parameters and the peak value of blasting vibration velocity is analyzed by the cosine amplitude method, it can be concluded that the longitudinal wave velocity representing the site conditions is also an important factor affecting the propagation of blasting vibration velocity. And compared with the test results of BP neural network and Sadovsky formula, the results showed: the prediction value of the improved PSO–BP neural network prediction model is better consistent with the measured value, the results are more reliable, and the model has good generalization ability. The research method provides a model reference for the prediction of blasting vibration velocity peak in similar projects.
Key words: blasting vibration; peak blasting vibration velocity; BP neural network; particle swarm optimization (PSO) algorithm; longitudinal wave velocity

导出引用

范勇1，裴勇1，杨广栋1，冷振东1，2，卢文波3. 基于改进PSO–BP神经网络的爆破振动速度峰值预测[J]. 振动与冲击, 2022, 41(16): 194-203

FAN Yong1,PEI Yong1,YANG Guangdong1,LENG Zhendong1,2,LU Wenbo3. Prediction of blasting vibration velocity peak based on an improved PSO-BP neural network[J]. Journal of Vibration and Shock, 2022, 41(16): 194-203

参考文献

[1] XU S D, LI Y H, LIU J P, et al. Optimization of blasting parameters for an underground mine through prediction of blasting vibration[J]. Journal of Vibration and Control, 2019, 25(9): 1585-1595.
[2] HU X，QU S. A new approach for predicting bench blasting-induced ground vibrations: A case study[J]. The Journal of the Southern African Institute of Mining and Metallurgy, 2018, 118(5): 531-538.
[3] 唐海, 李海波, 蒋鹏灿, 等. 地形地貌对爆破振动波传播的影响实验研究[J]. 岩土力学与工程学报, 2007, 26(9): 1817-1823.
TANG Hai, LI Haibo, JIANG Pengcan. et al. Experimental study on the effect of topography on propagation of blasting wave [J]. Chinese Journal of Rock Mechanics and Engineering, 2007, 26(9): 1817-1823.
[4] REZAEINESHAT A, MASOUD M, MEHRDANESH A, et al. Optimization of blasting design in open pit limestone mines with the aim of reducing ground vibration using robust techniques [J]. Geomechanics and Geophysics for Geo-Energy and Geo-Resources, 2020, 6(2): 1-14.
[5] 刘亚群, 李海波, 裴启涛, 等. 基于灰色关联分析的遗传神经网络在水下爆破中质点峰值振动速度预测研究[J].岩土力学, 2013, 34(增刊1): 259-264.
LIU Yaqun, LI Haibo, PEI Qitao, et al. Prediction of peak particle velocity induced by underwater blasting based on the combination of grey relational analysis and genetic neural network[J]. Rock and Soil Mechanics, 2013,34(Suppl.1):259-264.
[6] 骆晓峰, 邱伟, 黄文龙, 等. 基于量纲理论的复杂地形下爆破振动传播衰减公式修正[C]// 中国水力发电工程学会电网调峰与抽水蓄能专业委员会2020年学术交流年会.北京: 中国电力出版社, 2020.
[7] XU S D, CHEN T X, LIU J Q, et al. Blasting vibration control using an improved artificial neural network in the ashele copper mine [J]. Shock and Vibration, 2021(2):1-11.
[8] 史秀志, 陈新, 史采星, 等. 基于GEP的爆破峰值速度预测模型[J]. 振动与冲击, 2015, 34(10): 95-99.
SHI Xiuzhi, CHEN Xin, SHI Caixing, et al. Prediction model for blasting-vibration-peak-speed based on GEP[J]. Journal of Vibration and Shock, 2015, 34(10): 95-99.
[9] 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 Liangshan, BAI Yuan, QIU Yunfei, 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.
[10] 赵红梦, 姜志侠. PCA-BP算法在地面爆破振动中的应用[J]. 工程爆破, 2020, 26(5): 30-35.
ZHAO Hongmeng, JIANG Zhixia. Application of PCA-BP algorithm in ground blasting vibration[J]. Engineering Blasting, 2020, 26(5): 30-35.
[11] 申旭鹏, 璩世杰, 王福缘, 等. 基于BP神经网络的爆破振速峰值预测[J]. 爆破, 2013, 30(1): 122-125.
SHEN Xupeng, QU Shijie, WANG Fuyuan, et al. Prediction of blasting peak particle velocity by BP neural network model[J]. Blasting, 2013, 30(1): 122-125.
[12] 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]. 岩土力学与工程学报, 2007, 26(1): 3533-3539.
TANG Hai, SHI Yongqiang, LI Haibo, et al. Prediction of peak velocity of blasting vibration based on neural network[J]. Chinese Journal of Rock Mechanics and Engineering, 2007, 26(1): 3533-3539.
[13] 施建俊, 李庆亚, 张琪, 等. 基于Matlab和BP神经网络的爆破振动预测系统[J]. 爆炸与冲击, 2017, 37(6): 1087-1092.
SHI Janjun, LI Qingya, ZHANG Qi, et al. Blasting vibration prediction system based on Matlab and BP neural network[J]. Explosion and Shock Waves, 2017, 37(6): 1087-1092.
[14] 郭饮鹏, 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 Yinpeng, YANG Shijiao, ZHU Zhonghua, et al. Prediction of blasting vibration velocity using GA-BP neural network[J]. Blasting, 2020, 37(3): 148-152.
[15] 闫鹏程, 尚松行, 张超银, 等. 改进BP神经网络算法对煤矿水源的分类研究[J].光谱学与光谱分析, 2021, 41(7): 2288-2293.
YAN Pengcheng, SHANG Songxing, ZHANG Chaoyin, et al. Study on classification of coal mine water source by improved BP neural network algorithm[J]. Spectroscopy and Spectral Analysis, 2021, 41(7): 2288-2293.
[16] 徐以山, 曾碧, 尹秀文, 等. 基于改进粒子群算法的BP神经网络及其应用[J]. 计算机工程与应用, 2009, 45(35): 233-235.
XU Yishan, ZENG Bi, YIN Xiuwen, et al. BP Neural Network and its applications based on improved PSO[J]. Computer Engineering and Applications, 2009, 45(35): 233-235.
[17] ??NGUYEN H，BUI X N，TRAN Q H, et al. Prediction of ground vibration intensity in mine blasting using the novel hybrid MARS-PSO-MLP model[J]. Engineering with Computers, 2021.
[18] 惠阳, 王永岗, 彭辉, 等. 基于优化PSO-BP算法的耦合时空特征下地铁客流预测[J]. 交通运输工程学报, 2021, 21(4): 210-222.
HUI Yang, WANG Yonggang, PENG Hui, et al. Subway passenger flow prediction based on optimized PSO-BP algorithm with coupled spatio-temporal characteristics[J]. Journal of Traffic and Transportation Engineering, 2021, 21(4): 210-222.
[19] YANG Y, ZANG O. A hierarchical analysis for rock engineering using artificial neural networks[J]. Rock Mechanics and Rock Engineering, 1997, 30(4): 207–222.
[20] 王峰, 周宜红, 赵春菊, 等. 基于改进粒子群算法的混凝土坝热学参数反演研究[J]. 振动与冲击, 2019, 38(12): 168-174.
WANG Feng, ZHOU Yihong, ZHAO Chunju, et al. Inverse analysis concrete dam thermal parameters based on an improved particle swarm optimization method[J]. Journal of Vibration and Shock, 2019, 38(12): 168-174.
[21] 陈贵敏, 贾建援, 韩琪. 粒子群优化算法的惯性权值递减策略研究[J]. 西安交通大学学报, 2006, 40(1): 53-56.
CHEN Guimin, JIA Jianyuan, HAN Qi. Study on strategy of decreasing inertia weight in particle swarm optimization algorithm[J]. Journal of Xi'an Jiaotong University, 2006, 40(1): 53-56.
[22] 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.
[23] HAJIHASSANI M , JAHED ARMAGHANI D, MONJEZI M, et al. Blast-induced air and ground vibration prediction: a particle swarm optimization-based artificial neural network approach[J]. Environmental Earth Sciences, 2015, 74(4): 2799-2817.