Application of GA-SVM in classification of surrounding rock based on model reliability examination

• 出 处: Mining Science and Technology
• 发表日期: 2010年03期
• 关键词: surrounding rock discrimination universal trained optimize clustering generaliza

In order to improve the discrimination precision of support vector machine(SVM) in classification of surrounding rock, a Genetic Algorithm(GA) was used to optimize SVM parameters in the solution space.The idea of examination of model reliability was introduced to check the reliability of the SVM parameters,obtained by genetic algorithms.In the process of model reliability,a trend examination method is presented,which checks the reliability of the model via the influence trend of impact factors on the object of evaluation and their evaluation level.Trend examination methods are universal,showing new ideas in model reliability examination and can be used in any problems of examination of reliability of models,based on previous experience.We established a GA-SVM based reliability model of a classification the surrounding rock and applied it to a practical engineering situation.The result shows that the improved SVM has a high capability for generalization and prediction accuracy in classification of surrounding rock.

In order to improve the discrimination precision of support vector machine (SVM) in classification of surrounding rock, a Genetic Algorithm (GA) was used to optimize SVM parameters in the solution space. The idea of ​​examination of model reliability was introduced to check the reliability of the SVM parameters, obtained by genetic algorithms. The process of model reliability, a trend examination method is presented, which checks the reliability of the model via the influence trend of impact factors on the object of evaluation and their evaluation level. Trend examination methods are universal, showing new ideas in model reliability examination and can be used in any problems of examination of reliability of models, based on previous experience. We established a GA-SVM based reliability model of a classification of surrounding rock and applied it to a practical engineering situation.The result shows that the improved SVM has a high capability for generalization and prediction accuracy in classi fication of surrounding rock.