A hybrid artificial bee colony algorithm and support vector machine for predicting blast-induced ground vibration

Because nearby construction has harmful effects,precisely predicting blast-induced ground vibration is critical.In this paper,a hybrid artificial bee colony(ABC)and support vector machine(SVM)model was proposed for predicting the value of peak particle velocity(PPV),which is used to describe blast-induced ground vibration.To construct the model,5 potentially relevant factors,including controllable and uncontrollable parameters,were considered as input parameters,and PPV was set as the output parameter.Forty-five samples were recorded from the Hongling lead-zinc mine.An ABC-SVM model was developed and trained on 35 samples via 5-fold cross-validation(CV).A testing set(10 samples)was used to evaluate the prediction performance of the ABC-SVM model.SVM and four empirical models(United States Bureau of Mines(USBM),Amraseys-Hendron(A-H),Langefors-Kihstrom(L-K),and Central Mining Research Institute(CMRI))also were introduced for comparison.Next,the performances of the models were analyzed by using 3 statistical parameters:the correlation coefficient(R2),root-mean-square error(RMSE),and variance accounted for(VAF).ABC-SVM had the highest R2 and VAF values followed by the SVM,A-H,USBM,CMRI,and L-K methods.The results demonstrated that ABC-SVM outperformed SVM and the empirical predictors for predicting PPV.Moreover,the best results from the R2,RMSE,and VAF indices were 0.9628,0.2737,and 96.05%for the ABC-SVM model.The sensitivities of the parameters also were investigated,and the height difference between the blast point and the monitoring station was found to be the parameter that had the most influence on PPV.