Grouting stratum identification based on fuzzy SVM

A new support vector machine (SVM) approach with fuzzy rules decisions is proposed for grout stratum identification, which integrates with SVM and fuzzy systempsila s merits. SVM is a novel machine tool and fuzzy Takagi-Sugeno model is easy to process uncertain system. Through defining lambda -sigmoid fuzzy function, we put forward SVM decision function rules-based expression and proved they are consistent. The matching degree between the antecedent part of the rules and current system inputs is usually t-norm; and we adopt t-uninorm symmetric sum operators which compensation between small and large degrees of membership takes place. By the method, the rules and membership functions are very simple, and fuzzy propositions in each rule only depends on the cardinality of the set of support vectors. At last, .the important data are obtained from the real grouting project. we separately choose 59 group datum from two typical stratum. A part of date set is used to training set of SVM, the other is used to check up the classification effect. The results demonstrates lambda -SVM with fuzzy decisions identification method is excelled the other two methods. So the method can applied to the automatic grout instruments