Application of sensor array and neural networks for quantification of organic solvent vapours in air

Organic solvents represent significant class of air pollutants. Mixtures of butanol and aromatic compounds are classified among the most commonly used there. The concept of two sensor systems capable of measurements and analy sis of butanol/xylene and butanol/toluene mixtures is presented. Sensor arr ay consists of four commercial, tin oxide based, semiconductor type gas sen sors (TGS 800 series). For the sensors characterisation manually operated g as installation is constructed. Feedforward neural networks are developed f or appropriate analysis of sensors responses. Both systems provide measurem ents of several single compounds concentrations with inaccuracy not exceedi ng 15% of range. Humidity influence on system responses is rejected. Possib ility of portable realisation make the systems potential replacement of tra ditional gas analysing devices, especially in off-laboratory applications. (C) 1999 Elsevier Science S.A. All rights reserved.