In this work, vacuum deposited thin films of PbPc, NiPc, VOPc, TiOPc and Co
Pc were employed as gas sensor to detect NO2 and NO. Data collected from se
nsor responses were used to train a back-propagation network (BPN) for iden
tifying the gas species and quantifying its concentration; The results show
that among the metallophthalocyanines tested, PbPc and NiPc have better se
nsing characteristics towards NO2 and NO. In BPN training, maximum error oc
curs for data collected by the TiOPc sensor, and minimum error occurs for a
rray of PbPc and NiPc sensors. In the concentration prediction of NO or NO2
, the maximum predicted error is 6.94%. When Two-Stage BPN or Single-Stage
BPN was use to identify and quantify a single gas (NO2 or NO), the accuracy
of recognition approaches 100% and the maximum error for concentration pre
diction is 7.4%. (C) 1999 Elsevier Science S.A. All rights reserved.