A study of the application of the CMAC artificial neural network to the problem of gas sensor array calibration

This paper explores the application of the Cerebeller Model Arithmetic Computer (CMAC) artificial neural network to the analysis of multicomponent gas mixtures using an array of eight nonselective, nonlinear and noisy Taguchi gas sensors. Various network parameters that affect the performance of the CMAC are discussed. Results of the analysis of three gas component mixtures are presented.