Abstract：Aiming at the problem of high dimensional nonlinear data processing in the prediction of mine gas emission, the optimal fuzzy partition matrix of prediction factors is obtained by fuzzy clustering, fuzzy recognition and optimization theory. combined with the gas emission level, The characteristic value of the level variable of the sample data is calculated, On this basis, a prediction model of gas emission from single input and single output is established by using MATLAB curve fitting toolbox. The empirical analysis shows that the prediction model obtained by this modeling method has higher prediction accuracy, and the prediction effect is better than the existing prediction models.
2018, Vol. 28 