基于粗糙集模糊神经网络的爆破振动危害预测
|
摘要
为了探索一种能克服单因素预测的局限性、提高爆破振动危害预测精度的方法,基于粗糙集模糊神经网络理论,建立了综合考虑爆破振动幅值、主频率、主频率持续时间及结构动力特性等10个因素的民房破坏程度预测模型;用铜绿山矿爆破振动和民房破坏情况观测数据,对该模型进行了训练和测试,测试结果与现场观测结果具有良好的一致性。研究表明:粗糙集理论可将现场数据进行属性约简,简化输入变量,缩小神经网络的搜索空间,改善爆破振动的预测性能;基于粗糙集模糊神经网络理论的爆破振动危害预测模型,能更好地考虑各种因素对危害程度的综合影响,避免了单因素预测的局限性。
According to the nonlinear links between blasting-vibration-induced damage degree and its influencing factors,a rough set-based fuzzy-neural network model is proposed to seek a method that can overcome the limitations in the single-factor case and improve the damage prediction precision.In the proposed prediction model,there are 10 factors to be taken into account,which include particle vibration velocity(PPV),dominant frequency,dominant frequency duration and dynamic characteristics of structures.The prediction model is trained and tested by a series of data from the observations of blasting vibration and damage degree of houses in Tonglüshan Copper Mine.The training results are in agreement with the field observations.The rough set-based fuzzy-neural network can reduce data indexes and simplify input variables,and minify the decision table size and accelerate the approach to the minimal rules.The proposed method considering the manifold factors can improve the prediction precision of damage degree induced by blasting vibration.
According to the nonlinear links between blasting-vibration-induced damage degree and its influencing factors,a rough set-based fuzzy-neural network model is proposed to seek a method that can overcome the limitations in the single-factor case and improve the damage prediction precision.In the proposed prediction model,there are 10 factors to be taken into account,which include particle vibration velocity(PPV),dominant frequency,dominant frequency duration and dynamic characteristics of structures.The prediction model is trained and tested by a series of data from the observations of blasting vibration and damage degree of houses in Tonglüshan Copper Mine.The training results are in agreement with the field observations.The rough set-based fuzzy-neural network can reduce data indexes and simplify input variables,and minify the decision table size and accelerate the approach to the minimal rules.The proposed method considering the manifold factors can improve the prediction precision of damage degree induced by blasting vibration.
引文
[1]李夕兵,张义平,刘志祥,等.爆破震动信号的小波分析与HHT变换[J].爆炸与冲击,2005,25(6):528-534.LI Xi-bing,ZHANG Yi-ping,LI U Zhi-xiang,et al.Wavelet analysis and Hilbert-Huang transformof blasting vi-bration signal[J].Explosion and Shock Waves,2005,25(6):528-534.
[2]闫鸿浩,李晓杰,曲艳东,等.爆破振动速度测试精细分析[J].岩土力学,2007,28(10):2091-2094.YAN Hong-hao,LI Xiao-jie,QU Yan-dong,et al.Fine analysis of blasting vibration velocity testing[J].Rock andSoil Mechanics,2007,28(10):2091-2094.
[3]凌同华,李夕兵,王桂尧.爆破震动灾害主动控制方法研究[J].岩土力学,2007,28(7):1439-1452.LING Tong-hua,LI Xi-bing,WANG Gui-yao.Astudy on initiative control of blast vibration damages[J].Rockand Soil Mechanics,2007,28(7):1439-1452.
[4]Lilly D.Neural network si mulation:Charting the future of blast process control[J].Pit&Quarry,1995,13(2):34-37.
[5]徐全军,刘强,聂渝军.爆破地震峰值预报神经网络研究[J].爆炸与冲击,1999,19(2):133-138.XU Quan-jun,LI U Qiang,NIE Yu-jun,et al.Study of neural network prediction on peak particle amplitude ofblasting ground vibration[J].Explosion and Shock Waves,1999,19(2):133-138.
[6]XU Quan-jun.Ground vibration model testing of bench blasting and BP neural network analysis[C]∥The 7thInter-national Symposiumon Rock Fragmentation by Blasting.Beijing,China,2002:591-594.
[7]ZHONG Dong-wan.Study on the forecast of blasting vibration peak value based on the fuzzy neural network[C]∥The 7th International Symposiumon Rock Fragmentation by Blasting.Beijing,China,2002:263-266.
[8]史忠植.知识发现[M].北京:清华大学出版社,2002:58-67.
[9]刘同明.数据挖掘技术及其应用[M].北京:国防工业出版社,2001:124-131.
[10]张燕秦,徐向东.用于热力系统建模的基于粗糙集的模糊神经网络[J].清华大学学报(自然科学版),2004,44(8):1083-1086.ZHANG Yan-qin,XU Xiang-dong.Rough set-based fuzzy-neural network model design for thermodynamic sys-tems[J].Journal of Tsinghua University(Science and Technology),2004,44(8):1083-1086.
[11]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].湖南长沙:中南大学,2007.
[2]闫鸿浩,李晓杰,曲艳东,等.爆破振动速度测试精细分析[J].岩土力学,2007,28(10):2091-2094.YAN Hong-hao,LI Xiao-jie,QU Yan-dong,et al.Fine analysis of blasting vibration velocity testing[J].Rock andSoil Mechanics,2007,28(10):2091-2094.
[3]凌同华,李夕兵,王桂尧.爆破震动灾害主动控制方法研究[J].岩土力学,2007,28(7):1439-1452.LING Tong-hua,LI Xi-bing,WANG Gui-yao.Astudy on initiative control of blast vibration damages[J].Rockand Soil Mechanics,2007,28(7):1439-1452.
[4]Lilly D.Neural network si mulation:Charting the future of blast process control[J].Pit&Quarry,1995,13(2):34-37.
[5]徐全军,刘强,聂渝军.爆破地震峰值预报神经网络研究[J].爆炸与冲击,1999,19(2):133-138.XU Quan-jun,LI U Qiang,NIE Yu-jun,et al.Study of neural network prediction on peak particle amplitude ofblasting ground vibration[J].Explosion and Shock Waves,1999,19(2):133-138.
[6]XU Quan-jun.Ground vibration model testing of bench blasting and BP neural network analysis[C]∥The 7thInter-national Symposiumon Rock Fragmentation by Blasting.Beijing,China,2002:591-594.
[7]ZHONG Dong-wan.Study on the forecast of blasting vibration peak value based on the fuzzy neural network[C]∥The 7th International Symposiumon Rock Fragmentation by Blasting.Beijing,China,2002:263-266.
[8]史忠植.知识发现[M].北京:清华大学出版社,2002:58-67.
[9]刘同明.数据挖掘技术及其应用[M].北京:国防工业出版社,2001:124-131.
[10]张燕秦,徐向东.用于热力系统建模的基于粗糙集的模糊神经网络[J].清华大学学报(自然科学版),2004,44(8):1083-1086.ZHANG Yan-qin,XU Xiang-dong.Rough set-based fuzzy-neural network model design for thermodynamic sys-tems[J].Journal of Tsinghua University(Science and Technology),2004,44(8):1083-1086.
[11]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].湖南长沙:中南大学,2007.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心