IMPROVEMENT OF SURFACE-ACOUSTIC-WAVE GAS SENSOR RESPONSE-TIME USING NEURAL-NETWORK PATTERN-RECOGNITION

Surface acoustic wave (SAW) gas-sensor signal processing may allow first, detection of gases, secondly, their identification and thirdly, if possible, their quantification. For a few years now, pattern-recognition techniques using artificial neural networks have been applied to sensor arrays with promising results. Nevertheless, data sets needed for these techniques are always built with well-established and stable sensor responses. Sometimes, the SAW gas-sensor response times are quite long due to kinetic factors concerning the gas adsorption. Moreover, in some applications, such as military or safety, the gases involved are extremely dangerous or toxic. The detection speed is hence an essential parameter. Thus, we are developing a neural-network-based signal-processing system that aims to allow dynamic gas detection: the sensor steady-state response does not need to be reached to ascertain the presence of gas. This signal-processing system includes three steps. First, the gas-sensor output is pre-processed in order to extract some characteristic parameters. These then constitute the input pattern of a three-layer neural network trained with the back-propagation learning rule. Finally, its output is post-processed to decide whether or not to turn an alarm on. Up to now, we have only used the results given by one sensor consisting of a dual SAW delay-line oscillator for NOx sensing. We propose a pre- and a post-algorithm. Results are presented and discussed. In particular, we emphasize that some attention has to be given to the constitution of the data set and to the definition of the neural-network performance.