Chaotic Time Series Reconstruction and Safety System of Terrane Deformation in Undersea Mining
|School||Central South University|
|Keywords||stratum displacement monitoring chaos neural network security early warning|
As land resources have been developed and used in large scale, it was depleted day by day. People gradually turn their gaze to the ocean which contains rich mineral resources. Now, mining of bedrock deposit undersea water pressure is still at an early stage and the relative research on undersea mining work is seldom seen. The primary difference between mining under the sea and mining on land is that the seawater above undersea deposit. Once the seawater rush into the stope in undensea, it would result in an escalating probability of disaster. So, the key to safety mining of the bedrock deposit undersea is to control the deformation of the overlying strata.The stratum displacement during is very complicated, which contains a lot of uncertain and random parameters. During mining process, there are the exchange substance and energy with outside and the displacement shows a complicated nonlinear feature. Therefore, this paper adopt a nonlinear theory, that is chaostheory, to analyze stratum displacement of undersea mining.The basis of the analysis of displacement of undersea strata with chaos theory is the phase space reconstruction of time series. The paper calculates the time delay and embedding dimension by using both geometrical invariant method and compound autocorrelation function method. The time series of stratum displacement of undersea mining in Sanshandao gold mine are reconstructed in phase space. The chaotic invariants of measured time series for Sanshandao gold mine such as correlation dimension and the Lyapunov exponent, are calculated. The results show that the time series obtained in Sanshandao gold mine are chaotic time series. The changing laws of distance between two phase points for the displacement of strata at different heights in the phase space are revealed by using the chaos theory. The power spectrum curves for stratum displacement has been got by Fourier transform and the laws of stratum displacement energy are obtained.A prediction model for the evolution laws of phase space distance of stratum displacement is established based on the neural network, by which the stratum displacement of undersea mining in Xinli mining area is predicted. Then the safety warning system of strata displacement for the undersea mining is established. A neural network is trained through the combination of gradient descent method and chaos optimization method. The neural network model can achieve the merit of rapid training. Meanwhile, the defect of local minimum is avoided, and the calculation precision of the model is improved, and some control measures are given for different warning areas.The results show that the strata at different heights have different chaotic behaviors. After the reconstruction of phase space, subtle features of strata displacement change are enlarged, and the inherent law of strata is adequately demonstrated, which is the basis of the safety warning system of the undersea mining.