Meta-Models and Genetic Algorithm Application to Approximate Optimization with Discrete Variables for Fire Resistance Design of A60 Class Bulkhead Penetration Piece

A60 class bulkhead penetration piece is a fire-resistance apparatus installed on compartments to protect lives and prevent flame diffusion in case of fire accident ships offshore plants. In this study, approximate optimization with discrete variables was carried out for the design an (A60 BPP) using various meta-models multi-island genetic algorithms. Transient heat transfer analysis evaluate piece, we verified results via test. The experiment’s method applied generate be used optimization, transient were integrated method. response surface model, Kriging, radial basis function-based neural network. length, diameter, material type, insulation density variables, constraints that considered include temperature, productivity, cost. optimum problem based meta-model formulated such determined by minimizing weight subject limit values constraints. context accuracy, solution from compared actual results. It concluded network, among showed most accurate piece.