A new approach is presented for analyzing gas mixtures by transforming the
problem into a pattern classification one to reduce the effect of the poor
repeatability of sensor response on the prediction of gas concentration. Th
e aim of numerical simulation is to determine how successfully the approach
using the combination of artificial neural networks with multi-sensor arra
ys can analyze multi-component gas mixtures. The results indicate that the
new approach is realistic for gas mixture analysis, and numerical simulatio
n is a powerful tool to determine the architecture of a network. (C) 2001 E
lsevier Science B.V. All rights reserved.