模糊J-K触发器神经网络降低传感器交叉敏感方法

Decreasing sensor cross sensitivity based on fuzzy J-K Flip-flop neural network

用模糊J-K触发器作为神经元的作用函数,构建了模糊J-K触发器神经网络系统,并将其应用于消除压阻式压力传感器干扰电流对目标参量的影响。实验结果表明,该方法结合了模糊技术和J-K触发器的优势,具有结构简单、训练速度快的优点。同采用常规S型函数作为神经元作用函数的神经网络相比,模糊J-K触发器神经网络训练次数少,均方根误差从4.641 8×10?4降低到了6.284 4×10?5,降低了一个数量级。

Fuzzy J-K flip-flop is used as an action function of neural cell in neural network.A fuzzy J-K flip-flop neural network system is constructed at first,and applied to decrease the influence of interference current to the objective parameter of the piezo-resistive pressure sensor.The method combines the advantages of fuzzy theory and J-K flip-flop,with the advantages of quickness and ease.Comparing with the common S function in neural network,the new one de-creases the training times,and Root Mean Square Error（RMSE） is lower in an order of magnitude from 4.6418e-004 to 6.2844e-005.