Application of artificial neural networks in abrasive waterjet cutting process

This paper presents and discusses the application of artificial neural networks (ANN) in the abrasive watejet (AWJ) cutting process. Backpropagation networks are chosen for the proposed network, which is written using the programming package MAT-LAB. The overall results are observed and compared with the experimental data for the performance of the networks. Based on the application it was found that the ANN is able to learn the complicated relationships between the main abrasive watedet input parameters and cutting speed with necessary cutting quality. The proposed prediction model for certain AWJ system can be used for parameter optimization and numerical simulation of AWJ cutting process.