IDENTIFICATION OF COMBUSTIBLE MATERIAL WITH PIEZOELECTRIC CRYSTAL SENSOR ARRAY USING PATTERN-RECOGNITION TECHNIQUES

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.