Chaotic time series prediction for surrounding rock's deformation of deep mine lanes in soft rock

Based on the measured displacements, the change laws of the effect of distance in phase space on the deformation of mine lane were analyzed and the chaotic time series model to predict the surrounding rocks deformation of deep mine lane in soft rock by nonlinear theory and methods was established. The chaotic attractor dimension(D) and the largest Lyapunov index(E-max) were put forward to determine whether the deformation process of mine lane is chaotic and the degree of chaos. The analysis of examples indicates that when D>2 and E-max>0, the surrounding rock's deformation of deep mine lane in soft rock is the chaotic process and the laws of the deformation can still be well demonstrated by the method of the reconstructive state space. Comparing with the prediction of linear time series and grey prediction, the chaotic time series prediction has higher accuracy and the prediction results can provide theoretical basis for reasonable support of mine lane in soft rock. The time of the second support in Maluping Mine of Guizhou, China, is determined to arrange at about 40 d after the initial support according to the prediction results.