摘要
应用几种改进ＢＰ算法，提高了ＢＰ神经网络的收敛速度与稳定性，详细描述了神经网络预测产量及工效的求解机理与具体实施步骤．重点研究了网络学习前后的数据处理工作、网络结构的确定方法以及网络合理的学习步数．
Four reformatory learning algorithms are applied to enhance learning speed and stability of neural network. It is also indicated that general principles for forecasting productivity and efficiency with artificial neural network and the detailed operational steps. It is laid that stress on how to process dates before and after learning procedure ,the structure of network,and the proper times of reiteration during learning procedure.
出处
《煤炭学报》
EI
CAS
CSCD
北大核心
1999年第2期132-136,共5页
Journal of China Coal Society
关键词
BP神经网络
综采
产量
生产指标预测
采煤
reformatory backpropagation neural network,fullymechanized coal winning technology,productivity and efficiency
