The accurate inversion of mining subsidence prediction parameters is key to the precise prediction of deformation during mining. However, the use of traditional genetic algorithms (GA) for inversion prediction has problems such as poor resistance to differences, and the accuracy of inversion parameters is affected when key monitoring points are missing. In response to these issues, a probability integral parameter inversion method is proposed in this study that integrates a selection-weighted iterative robust genetic algorithm. This method combines the selection-weighted iteration method with a genetic algorithm to determine the weights of different observation values, and then a probability integral parameter inversion method is constructed for the fusion selection-weighted iterative robust GA. The results indicate that the fusion selection-weighted iterative robust GA is stronger than the traditional GA, and the parameters obtained have higher accuracy and greater reliability. An experiment using real working face engineering showed that, compared with the GA method, the RMSE (root mean square error) of the proposed method is reduced by 24.4 mm and 37.5 mm, thus verifying the usability of this method.

Accurate positioning of mining working faces and reliable acquisition of their spatial characteristics play a key role in controlling illegal mining, in addition to identifying underlying hazards in coal mine goafs. However, when errors are present in observation deformation data, the traditional approach used to precisely locate rectangular working faces and invert their spatial characteristics cannot be used to accurately describe the properties of mining working faces. To address this issue, based on the relationship between surface deformation and the mining-induced response of the underground working face, in combination with the weighted iterative robust genetic algorithm (GA), we construct a precise positioning method for mining working faces. The simulation test results of this method demonstrate that, compared with the conventional GA, it not only has lower fitting errors (reduced from 73.5 mm to 49.0 mm and from 80.8 mm to 48.8 mm, respectively) but also significantly decreases the maximum relative error in the mining characteristic parameter inversion results. By applying it in the actual case of Guqiao Mine’s 1414 (1) mining working face, the proposed method’s reliability is further validated. The obtained results offer practical support for underground goaf detection and mining supervision efforts.