摘要
常规神经网络在当训练样本时分母项易趋于0,导致运算进入死循环,降低了结果的可信度。改进的模糊神经网络模型克服了上述现象,具有绝对收敛性,且隐含层的神经元个数容易调整。将该改进模型用于储层产能预测,正确率达95%以上。
The denominator of generally neural network output often tends to be zero,leading to infinite loop when training sample data. The reliability of results is debased. Improved fuzzy neural network model gets over such shortcoming. It has absolute convergence. In this model, we can easily adjust the number of nerve cells of hidden layer. This model is used to forecast reservoir productivity. Application results show that the accuracy is over 95 percent.
出处
《吉林大学学报（地球科学版）》
EI
CAS
CSCD
北大核心
2003年第1期48-50,55,共4页
Journal of Jilin University：Earth Science Edition
