SVM Prediction Model of Tunnel Blasting Excavation for the Destruction of the Ancient Great Wall

摘要

Taking the blasting excavation of a highway tunnel engineering in Shanxi Province as an example,using the principle of support vector machine (SVM) learning,with aperture,hole depth,hole spacing and row spacing,the maximal segment charge,total quantity and distance from an explosive source as the main factors influencing the blasting vibration,SVM model is built.To predict respectively the particle radial,tangential and vertical direction of the peak vibration velocity and frequency,the prediction results were compared with the measured values.The experimental results show that SVM prediction model predict the peak velocity and frequency of blasting vibration,it has fast convergence,high precision,small error characteristics.The model can be used to accurately forecast blasting vibration parameters,according to the forecast results can be better to take measures to protect the ancient Great Wall.