Prediction of coal mine gas concentration based on partial least squares regression

Gas concentration is an important index to measure the harm degree of gas in coal mine. A new method of gas concentration prediction by partial least squares regression (PLSR) is presented. In this paper, variable characteristics related to gas concentration in mine were searched. a prediction method based on PLSR is proposed to predict the Gas concentration. Firstly, the influence factors related to gas concentration are analyzed and extracted as input variables, and the gas concentration as output variables. Then, PLSR algorithm is used to solve the prediction model. Moreover, the model is used to predict the gas concentration in coal mine. The results show that the prediction model based on PLSR method has the characteristics of fast training speed and more accurate prediction. It provides a more reliable theoretical basis for the prediction and treatment of actual coal mine gas concentration.