中深孔爆破振动参数的BP神经网络预报
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
以某工程不同爆点不同监测点的爆破振动监测数据为背景 ,在分析爆破振动主要影响因素的基础上 ,建立了能同时对爆破振动速度峰值、振动主频率和振动的持续时间进行预报的BP神经网络模型。该模型的预报结果 (爆破振动的幅值、振动主频率和振动持续时间 )与实际监测结果基本吻合 ,从而得到了该场地不同地质、地形情况下爆破振动预报的BP神经网络模型。
On the basis of main factors analysis that affect blasting vibration in an engineering project, a BP neural network model was established to predict the peak value, main frequency and duration time of blasting vibration in several different sites. Vibration monitor records at the work sites were used as training set. The trained neural network can predict blast vibration parameters in accordance with monitor data.
引文
[1] ShimshoniY .ClassificationofSeismicSignalsbyIntegrationEnsemblesofNeuralNetwork[R].IEEETransactionsonSignalProcessing,1998,46(5):10941101.
    [2] BowmanBC .Real timeClassificationofSignalsfromThree componentSeismicSensorsusingNeuralNets[R ].DE92014886,1992.
    [3] 徐全军,张庆明,恽寿榕.爆破地震峰值的神经网络预报模型[J].北京理工大学学报,1998,18(4):472475.XUQuan jun,ZHANGQing ming,YUNShou rong.NeuralNetworkModelforForecastingPeakAccelerationofBlast ingVibration[J].JournalofBeijingInstituteofTechnology,1998,18(4):472475.
    [4] 程相君,王春宁,陈生潭.神经网络原理及其应用[M ].北京:国防工业出版社,1995.CHENGXiang jun,WANGChun ning,CHENSheng tan.ThePrincipleandApplicationofNeuralNetwork[M ].Bei jing:NationalDefensePublicationCompany,1995.

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