CAJ | 학술논문

针对BP神经网络对工程爆破振动的预测存在精度不够高的缺点，建立遗传算法优化神经网络的模型，并介绍了它的原理。最后通过爆破振动预测实例的介绍，应用MATLAB编程，将总装药量Q、测点与爆源的高差h、孔间微差时间t、最大药包距离L这4个参数作为模型参数，对爆破振动幅值v、振动主频f和振动持续时间T进行预测，得出基于遗传算法的神经网络预测的结果比BP神经网络更为精确，克服了BP神经网络的缺点。
침대BP신경망락대공정폭파진동적예측존재정도불구고적결점，건립유전산법우화신경망락적모형，병개소료타적원리。최후통과폭파진동예측실례적개소，응용MATLAB편정，장총장약량Q、측점여폭원적고차h、공간미차시간t、최대약포거리L저4개삼수작위모형삼수，대폭파진동폭치v、진동주빈f화진동지속시간T진행예측，득출기우유전산법적신경망락예측적결과비BP신경망락경위정학，극복료BP신경망락적결점。
In view of the shortcoming of bad precision of forecasting the blasting vibrationi by BP neural net-work,the genetic algorithm optimization neural network the model is established and principles is introduced. Through introduction of the example of blasting vibration forecast,the total charge amount,and height,delay time between holes,the maximum distance to blast source these four parameters are used as the model parameters to forecast blas-ting vibration amplitude,vibration frequency and vibration duration by applying the MATLAB programming,more pre-cise based on the genetic algorithm neural network forecast result compared with BP neutral network is obtained, which overcome the BP neural network shortcoming.