Performance Prediction and Sensitivity Analysis of SAW Gas Sensors

Abstract

An improved adaptive neuro-fuzzy inference system (IANFIS) is proposed to build a model to predict the resonant frequency shift performance of surface acoustic wave (SAW) gas sensors. In the proposed IANFIS, by directly minimizing the root-mean-squared-error performance criterion, the Taguchi-genetic learning algorithm is used in the ANFIS to find both the optimal premise and consequent parameters and to simultaneously determine the most suitable membership functions. The five design parameters of SAW gas sensors are considered to be the input variables of the IANFIS model. The input variables include the number of electrode finger pairs, the electrode overlap, the separation distance of two interdigital transducers on the substrate, the dimensions of the stable temperature-cut (ST-cut) quartz substrate, and the electrode thickness. The output variable of the IANFIS model is composed of the resonant frequency shift performance. The results predicted by the proposed IANFIS are compared with those obtained by the back-propagation neural network. The comparison has shown that the performance prediction of resonant frequency shift using the proposed IANFIS is effective. In addition, the sensitivity analyses of the five design parameters have also shown that both the electrode overlap and the dimensions of the ST-cut quartz substrate have the most influence on the resonant frequency shift performance.