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 H2 flow rate,CH4-Ar flow rate and Td.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.

Multi-Objective High-Fidelity Optimization Using NSGA-III and MO-RPSOLC

Optimizing the performance of composite structures is a real-world application with significant benefits.In this paper,a high-fidelity finite element method(FEM)is combined with the iterative improvement capability of metaheuristic optimization algorithms to obtain optimized composite plates.The FEM module comprises of ninenode isoparametric plate bending element in conjunction with the first-order shear deformation theory(FSDT).A recently proposed memetic version of particle swarm optimization called RPSOLC is modified in the current research to carry out multi-objective Pareto optimization.The performance of the MO-RPSOLC is found to be comparable with the NSGA-III.This work successfully highlights the use of FEM-MO-RPSOLC in obtaining highfidelity Pareto solutions considering simultaneous maximization of the fundamental frequency and frequency separation in laminated composites by optimizing the stacking sequence.