Heterogeneous information phase space reconstruction and stability prediction of filling body-surrounding rock combination

Traditional research believes that the filling body can effectively control stress concentration while ignoring the problems of unknown stability and the complex and changeable stress distribution of the filling body-surrounding rock combination under high-stress conditions. Current monitoring data processing methods cannot fully consider the complexity of monitoring objects, the diversity of monitoring methods, and the dynamics of monitoring data. To solve this problem, this paper proposes a phase space reconstruction and stability prediction method to process heterogeneous information of backfill-surrounding rock combinations. The three-dimensional monitoring system of a large-area filling body-surrounding rock combination in Longshou Mine was constructed by using drilling stress, multipoint displacement meter, and inclinometer. Varied information, such as the stress and displacement of the filling body-surrounding rock combination, was continuously obtained. Combined with the average mutual information method and the false nearest neighbor point method, the phase space of the heterogeneous information of the filling body-surrounding rock combination was then constructed. In this paper, the distance between the phase point and its nearest point was used as the index evaluation distance to evaluate the stability of the filling body-surrounding rock combination. The evaluated distances (ED) revealed a high sensitivity to the stability of the filling body-surrounding rock combination. The new method was then applied to calculate the time series of historically ED for 12 measuring points located at Longshou Mine. The moments of mutation in these time series were at least 3 months ahead of the roadway return dates. In the ED prediction experiments, the autoregressive integrated moving average model showed a higher prediction accuracy than the deep learning models (long short-term memory and Transformer). Furthermore, the root-mean-square error distribution of the prediction results peaked at 0.26, thus outperforming the no-prediction method in 70% of the cases.