Forecast model of GA-SVM for shaft-lining non-mining fracture
Fan Xiao-gang · Meitan xuebao · 2011
The parameters of support vector machine were optimized by using genetic algorithm;six factor indexes,including thickness of surface soil,thickness of basal aquifers,falling rate of basal aquifer water level,outer diameters of wellbore,thickness of shaft wall and service time of wellbore were regarded as attributes of shaft-lining fracture.The GA-SVM forecast model for shaft-lining non-mining fracture of mine was trained by training samples which received from a set of engineering data,and was tested by test samples.The results show that the model has high prediction accuracy and low error rate.It provides a new method and approach for the accurate forecast of shaft-lining non-mining fracture.