VOC recognition with sensor array and neuro-fuzzy network

A sensor array with ten sensors integrated on a substrate was developed to recognize various kinds and quantities of volatile organic compounds (VOCs), such as benzene, toluene, ethyl alcohol, methyl alcohol, and acetone. The sensor array consists of gas-sensing materials using SnO2 as the base material, plus a heating element based on a meandered platinum layer, all deposited on the substrate. The sensors on the sensor array are designed to produce a uniform thermal distribution and show a high and broad sensitivity and reproductivity to low concentrations through the usage of nano-sized sensing materials with high surface areas and different additives. By utilizing the sensing signals of the array with a neuro-fuzzy network, a recognition system can then be implemented for the classification and quantification of VOCs. We implemented a gas species recognizer using a multi-layer neural network with error back propagation learning algorithm and a gas concentration recognizer using a neuro-fuzzy network. The neuro-fuzzy network for gas concentration recognizer shows good generalization results for the test data as well as the learning data.