Study on the Improved PSO Algorithm Used in Coal Mine Safety Resource Allocation

Due to the coal mine safety resource allocation is a multivariate, multiple constrained, nonlinear combination optimization problem, so the particle swarm optimization (PSO) is easy to fall into local optimal value, low precision and slow convergence speed and so on. A particle swarm optimization based on Levy (LF-PSO) is proposed. This algorithm is applied to the study of coal mine safety resource allocation, combining with the time series dynamic, complex multiple attributes and so on. first of all, to build the index of safety resources from man - machine - environment - administration - emergency; secondly, in a safe investment as the constraint conditions, the use of the nonlinear function relationship between the BP neural network is used to fit the resource security and safety level, and then to build a coal mine safety resource allocation model; finally, based on the LF-PSO algorithm for model optimization. The results show that the LF-PSO algorithm has fewer parameters and is easy to jump out of local optima. Compared with the conventional PSO algorithm, the algorithm has better convergence speed and precision.