Pattern recognition of gases of petroleum based on RBF model

Abstract

In the case of aerial accident spreading out dangerous gases into the atmosphere, an instrument called electronic nose can warn about the beginning of petroleum derived leaks. In this paper we present the architecture of the neural network for pattern recognition of gases of petroleum based on an RBF model. With this model we analyzed the pattern recognition of five gases: ethane, methane, propane, butane and carbon monoxide, separated in three classes of problems.