Prediction and field application of water-conducting fracture zone height using a PSO-BP neural network optimised by dynamic mutation.

Abstract

Accurate prediction of the water-conducting fracture zone height is essential for water inrush prevention and safe production in coal mining. Based on extensive in-situ measurements collected from longwall panels in different mining districts, five key indicators-mining thickness, mining depth, coal seam dip angle, panel length along dip, and the hard-rock lithology ratio coefficient-were analysed. Using regression analysis, the empirical formula for predicting the water-conducting fracture zone height was refined and a multivariate nonlinear regression model was fitted. An optimal BP neural network model with the Levenberg-Marquardt algorithm and a 5:8:4:1 topology was validated, and subsequently an LWMA-PSO-BP neural network model was developed by jointly introducing the mutation operator from genetic algorithms and a linearly decreasing inertia weight (LDIW) strategy. Model fitting accuracy and generalisation were evaluated; the results indicate that the LWMA-PSO-BP model achieved the best overall performance, with a mean absolute error of 2.40 m and a mean absolute percentage error of 4.27%. In the Hebi mining district, a joint geophysical investigation integrating a microtremor survey, borehole coring, and drilling fluid loss measurements was conducted, and the water-conducting fracture zone heights for Panels 2301, 2302, 2303, and 2304 at Hemei No. 5 Mine were determined as 129.05 m, 134.21 m, 141.50 m, and 138.20 m, respectively. Field validation shows that the relative errors of the multivariate nonlinear regression and BP neural network models were 5.52% and 4.85%, respectively, whereas the LWMA-PSO-BP model yielded a relative error of only 2.99%. These results provide a reference for predicting the water-conducting fracture zone height under varied coal mining conditions.