摘要
人工神经网络在现代科学技术领域展现出了巨大的应用潜力。但是,传统的BP神经网络存在运算速度慢、易陷入局部极小值的问题。为了解决这个问题,笔者尝试通过改变误差梯度方向及使用线性搜索来改进BP算法。为了验证改进效果,使用某钻井的声波测井数据,对比了传统BP算法和改进后的算法在确定岩层孔隙度方面的效果。
Artificial neural network has shown great potential in modern science and technology.But,the traditional BP Neural Network has the problem of slow operation speed and easy to fall into local minima.To solve this problem,the author tries to improve the BP algorithm by changing the direction of error gradient and using linear search.In order to verify the improvement effect,the effect of the traditional BP algorithm and the improved algorithm on determining the porosity of rock strata is compared by using the sonic logging data of a drilling rig.
作者
刘淳
周菁菁
Liu Chun;Zhou Jingjing(Lanzhou Resources and Environment Voc-Tech College,Lanzhou Gansu 730000,China)
出处
《信息与电脑》
2018年第11期60-61,64,共3页
Information & Computer
关键词
人工神经网络
BP算法
变梯度法
artificial neural network
BP algorithm
variable gradient method
