The predictive study on coal mine gas emission quantity

摘要

The coal mining gas emission accident is one of great disasters, staffs are injured, and the coal industry has been caused great loss of property. Due to the special environment of coal mining conditions, gas emission is restricted by many factors; the object cannot be described by a simple mathematical model. In this paper, firstly, the data is preprocessed through ant colony clustering; secondly, through the fuzzy C-means clustering, the sample data's centers and administrative degree are obtained; then fuzzy theory and neural network are unified, fuzzy neural network model is constructed, and trained network is used to forecast the gas emission.