A Study on the prediction of Surface Roughness and Material Removal in Powder Blasting using Neural Network

신경회로망에 의한 분사가공공정의 표면거칠기 및 재료제거량 예측에 관한연구

The old technique of sandblasting which has been used for paint or scale removing, deburring and glass decorating has recently been developed into a powder blasting technique for brittle materials, capable of producing micro structures larger than $100{\mu}m$. In this paper, The surface characteristics of powder blasted glass surface were tested under different blasting parameter. Finally, we proposed a predictive model for powder blasting process using a neural network. A detailed analysis of the simulation results has been carried out and compared with experimental results.