Hybrid metamodel - NSGA-III - EDAS based optimal design of thin film coatings

In this work, diamond-like carbon (DLC) thin film coatings are deposited on silicon substrates by using plasma-enhanced chemical vapour deposition (PECVD) technique. By varying the hydrogen (H₂) flow rate, CH₄-Argon (Ar) flow rate and deposition temperature (Td) as per a Box-Behnken experimental design (BBD), 15 DLC deposition experiments are carried out. The Young's modulus (E) and the coefficient of friction (COF) for the DLCs are measured. By using a second-order polynomial regression approach, two metamodels are built for E and COF, that establish them as functions of H₂flow rate, CH₄-Ar flow rate and T_d. A non-dominated sorting genetic algorithm (NSGA-III) is used to obtain a set of Pareto solutions for the multi-objective optimization of E maximization and COF minimization. According to various practical scenarios, evaluation based on distance from average solution (EDAS) approach is used to identify the most feasible solutions out of the Pareto solution set. Confirmation experiments are conducted which shows the efficacy of the polynomial regression - NSGA-III - EDAS hybrid approach. The surface morphology of the DLCs deposited as per the optimal predictions is also studied by using atomic force microscopy.