Semi-supervised methane gas concentration detection model based on TDLAS technology

Abstract:

Because methane is flammable and explosive, the detection process is time-consuming and dangerous, and it is difficult to obtain labeled data. In order to reduce the dependence on marker data when detecting methane concentration using tunable diode laser absorption spectroscopy (TDLAS) technology, this paper designs a methane gas acquisition platform based on TDLAS and proposes a methane gas concentration detection model based on semi-supervised learning. Firstly, the methane gas is feature extracted, and then semi-supervised learning is introduced to select the optimal feature combination; subsequently, the traditional whale optimization algorithm is improved to optimize the parameters of the random forest to detect the methane gas concentration. The results show that the model is not only able to select the optimal feature combi-nation under limited labeled data, but also has an accuracy of 94.25%, which is better than the traditional model, and is robust in terms of parameter optimization.

Key words:Tunable diode laser absorption spectroscopy; semi-supervised learning; feature selection; random forest