Odour monitoring by the combination of sensores and neural networks

Abstract The treatment of waste is always combined with odour emission which can be annoying to people living near waste treatment plants. To identify and evaluate these odour emissions, different methods are used. The most frequently applied “measuring instrument” is the human nose. However, various factors, e.g. form on the day, make assessment difficult. Therefore, it is necessary to develop a measuring method which is objective and efficient. One example is a combination of sensors and neural networks. With this device, called an “Electronic Nose”, it is not only possible to identify odour, but all kinds of substances, depending on the selectivities of the sensors, can be detected and monitored. With reference to the characteristic patterns of defined emission situations, process control is possible in order to classify the emitting parts of a plant.