The recognition of Chinese spirits using electronic nose with dynamic method

摘要

This paper describes a method to recognize Chinese spirits using a gas sensor array being dynamically heated. An FFT and an RBF neural network are employed for dynamic signal extraction and pattern recognition, respectively. Four kinds of SnO{sub}2 gas sensors were chosen to build a sensor array for our experiments. Three Chinese spirits, which had similar odors were chosen to be recognized. The response signals were collected while the sensor array was periodically heated. After the FFT was applied on low frequency segment in a specific period, we used RBF neural network to analyze the results for pattern recognition. The recognition rate was 98%.