Xw. He et al., IDENTIFICATION OF COMBUSTIBLE MATERIAL WITH PIEZOELECTRIC CRYSTAL SENSOR ARRAY USING PATTERN-RECOGNITION TECHNIQUES, Talanta, 44(11), 1997, pp. 2033-2039
A promising way of increasing the selectivity and sensitivity of gas s
ensors is to treat the signals from a number of different gas sensors
with pattern recognition (PR) method. A gas sensor array with seven pi
ezoelectric crystals each coated with a different partially selective
coating material was constructed to identify four kinds of combustible
materials which generate smoke containing different components. The s
ignals from the sensors were analyzed with both conventional multivari
ate analysis, stepwise discriminant analysis (SDA), and artificial neu
ral networks (ANN) models. The results show that the predictions were
even better with ANN models. In our experiment, we have reported a new
method for training data selection, 'training set stepwise expending
method' to solve the problem that the network can not converge at the
beginning of the training. We also discussed how the parameters of neu
ral networks, learning rate eta, momentum term alpha and few bad train
ing data affect the performance of neural networks. (C) 1997 Elsevier
Science B.V.