Research on inversion of mining subsidence prediction parameters based on improved SPSO algorithm

Abstract

In order to make full use of the monitoring data and improve the efficiency of parameter calculation, this study, based on the measured data of surface deformation in 2516 working face of a mining area in Handan, introduces the improved standard particle swarm optimization（SPSO） algorithm into the process of calculating the parameters of the probability integral method, constructs a probability integral method to calculate parameters model based on improved SPSO algorithm, takes the sum of the squares of the difference between the fitted value and the measured value of each monitoring point as the fitness function, the optimal solution of the parameters within the constraints is obtained through iteration. The test results show that: the average number of iterations of the improved SPSO algorithm is 47.3 times, and the average number of iterations of the PSO algorithm is 300.4 times. The operation efficiency and stability of the improved SPSO algorithm are better than that of the PSO algorithm; inversion of parameter fitting error σ by probability integral method based on improved SPSO algorithm is 4.66%, fitting error σ of empirical value in mining area is 10.2%, the inversion parameter accuracy of the improved SPSO algorithm is higher than the empirical value of the mining area. The inversion probability integral method of surface fitting parameter model based on improved SPSO algorithm has reliable parameter accuracy and high operation efficiency, and has certain application value for improving the prediction accuracy of mining subsidence in mining area.

Keywords

• mining subsidence
• probability integral method
• spso algorithm
• parameter inversion
• surface fitting method