基于前馈神经网络井控多属性融合的断裂识别方法

赵军, 冉琦, 朱博华, 李洋, 梁舒瑗, 常健强

A method for identifying faults based on well-controlled multi-attribute fusion using a feedforward neural network

ZHAO Jun, RAN Qi, ZHU Bo-Hua, LI Yang, LIANG Shu-Yuan, CHANG Jian-Qiang

表3 DFNN不同隐含层深度测试效果统计

Table 3 DFNN test statistics of different hidden layer depths

DFNN深度 均方误差MSE 相关系数 2层 0.0294 0.8415 3层 0.0037 0.9891 4层 0.012 0.9471 5层 0.0315 0.8758 6层 0.0789 0.7886