A systematic investigation on the use of time dependant sensor signals in pattern recognition techniques

Due to the lack in selectivity and separability of most common chemical sensors, the use of sensor arrays in combination with Artficial Neural Network (ANN) signal processing is state of the development. The time dependent behaviour of gas sensors is one of the principal problems in signal processing methods for sensor arrays, these time dependencies of semiconductor sensors can be classified into three main time domains: Firstly the rise time of the sensor after a sudden concentration change, secondly the short time drift after switching on and finally the long time deteriorating of the semiconductor material. An important improvement in the treatment of these time dependent processes is the compensation of sensors rise time and short time drift effects. The short time drift of semiconductor sensors can be modelled and equalized by a preprocessing step. The rise time effects can be reduced by measuring the sensor signals with a high measurement rate and training ANN's with these measu rements. Preprocessing the sensor signal and applying the rise time behaviour leads to an improvement of ANN generalization ability, and attains a minimum of prediction error after a minimum of time after gas exchange.