传感器阵列信号处理的人工神经网络方法

Artificial Neural Network Approach on Processing Signal From Ion-selective Electrode Array

本文提出传感器阵列信号处理的人工神经网络方法,并以K^+/Ca^(2+)/NO_3^-/Cl^-阵列系统为对象,尝试了该方法的效果。结果表明,其拟合最大相对误差不超过7.4％,预测最大相对误差不超过6.9％。可见,其性能良好,可望成为各种传感器阵列信号处理的有用工具。

The artificial neural network method for processing signal from ion-selective electrodes array was presented. The performance of the neural network approach was tested in the simultaneous determination of K+-Ca2+-NO3-Cl- system. Its fitting related error maximum does not exceed 7. 4% and predicting related error maximum does not exceed 6. 9%. The results show that the method is good, and therefore it might be referred as useful tool of processing signals from various kinds of ion-selective electrode array.