Application of ant colony clustering algorithm in coal mine gas accident analysis under the background of big data research

In order to better solve the problem of gas outburst prediction, based on the in-depth study of ant colony algorithm, the ant colony clustering algorithm is improved, and the population classification and ant sensory perception characteristics are applied to make the ant colony the most likely to find. The optimal solution effectively avoids the possibility of local optimization, improves the global optimization performance and convergence speed of the algorithm, and reduces the influence of human subjective factors. Based on the prominent basic speech and actual working conditions, the paper selects five indexes of gas velocity, initial gas velocity, gas content, gas pressure and coal firmness coefficient as clustering attributes, and uses ant colony clustering algorithm to judge outstanding the state of occurrence. The paper uses MATLAB programming language to write a coal and gas outburst prediction program based on improved ant colony clustering algorithm, and predicts a coal mine. The final result is the same as the actual observation.