A MULTISENSOR SYSTEM FOR BEER FLAVOR MONITORING USING AN ARRAY OF CONDUCTING POLYMERS AND PREDICTIVE CLASSIFIERS

This paper describes the results of a three year project, jointly funded by the UK government and industry, to develop a multisensor system capable of discriminating between the aromas of different beers. The system consists of an array of up to 24 conducting polymer sensors (thin films electrodeposited onto a microelectrode structure). The conducting polymers provide the active layer in these conductometric odour sensors and respond differentially to the headspaces of beers and lagers. The interface circuitry and signal conditioning have been designed and realized in custom PCBs housed in a Eurorack-based multisensor system. A comprehensive suite of software modules has been developed to automate the sampling system and process the sensor array data. The output from the polymer array is pre-processed using a variety of algorithms (e.g., fractional change in conductance, normalized relative response) and then classified using a statistical (chemometric fingerprinting technique) or neural predictive classifier (multi-layer perceptron using back-propagation learning). The odour-sensing system can distinguish subtle taints, e.g., 0.5 ppm of diacetyl in an ethanol solution with only nine different varieties of conducting polymers.