Corrosion Behavior of LENS Deposited CoCrMo Alloy Using Bayesian Regularization-Based Artificial Neural Network (BRANN)

Abstract The well-known fact of metallurgy is that the lifetime a metal structure depends on material's corrosion rate. Therefore, applying an appropriate prediction process for manufactured metals or alloys trigger extended life product. At present, current models additive are either complicated built restricted basis towards depletion. This paper presents novel approach to estimate rate and potential by considering significant major parameters such as solution time, aging temperature, test time. Laser Engineered Net Shaping (LENS), which manufacturing used in health care equipment, was investigated present research. All accumulated information manufacture LENS-based Cobalt-Chromium-Molybdenum (CoCrMo) alloy considered from previous literature. They enabled create robust Bayesian Regularization (BR)-based Artificial Neural Network (ANN) order predict with accuracy material best properties. achieved data were validated investigating its experimental behavior. It found very good agreement between predicted values generated BRANN model values. robustness proposed allows implement materials successfully biomedical implants.