Influence of ECAP Parameters on the Structural, Electrochemical and Mechanical Behavior of ZK30: A Combination of Experimental and Machine Learning Approaches

Several physics-based models have been utilized in material design for the simulation and prediction of properties. In this study, several machine-learning (ML) approaches were used to construct a model analyze influence equal-channel angular pressing (ECAP) parameters on microstructural, corrosion mechanical behavior biodegradable magnesium alloy ZK30. The ML employed linear regression, Gaussian process, support vector regression. For optimization alloy’s performance, experiments conducted ZK30 billets using different ECAP routes, channel angles, number passes. adopted is an adequate predictive which agreed with experimental results. die angles had insignificant effect grain refinement, compared route type. via four passes Bc (rotating sample 90° its longitudinal axis after each pass same direction) was most effective condition producing homogenous ultrafine distribution 1.92 µm. Processing 4-Bc angle produced highest hardness (97-HV) coupled tensile strength (344 MPa). optimum rate 0.140 mils penetration per year (mpy) resistance 1101 ?·cm2 resulted from processing through 1-pass 120°-die. Grain refinement reducing rates increased resistance, findings.