Displacement predication of surrounding rock based on gray system and evolutionary support vector machine

The in-situ monitoring data of surrounding rock displacements reflect the change of mechanical situation.Considering the monotonously increasing characteristics of the displacement time series of surrounding rock,a new intelligent prediction method combining gray system and evolutionary support vector machine(SVM) is proposed.In the method,based on the principles of displacement decomposition,the trend of displacement time series is extracted by gray system and the deviation of gray system is approximated by the SVM whose algorithm parameters evolve through particle swarm optimization(PSO).The method can rolling forecast the surrounding rock displacements based on monitoring data,in order to discover abnormal situation in time,adjust the supporting schemes dynamically and ensure the stability of the surrounding rock of cavern.The engineering case studies indicate that it is scientific and there is an extensive prospect for real time forecasting.