A multi-objective genetic algorithm for jacket optimization

Abstract

Jackets are massive steel towers supporting offshore installations such as oil platforms and wind turbines. Due to the high costs of material, construction, and installation, there is an interest in optimizing such jacket designs. This is an example of the broader problem of structural design optimization. In this paper, we describe underlying concepts related to the problem of jacket design as well as previous research on jacket design optimization. Motivated by the complexity of the problem, including the multiple objectives typically involved, we develop a novel multi-objective genetic algorithm, NSGA-J, which is tailored to jacket design optimization. NSGA-J is based on the prominent Non-Dominated Sorting Genetic Algorithm (NSGA-II), but tailors it to the problem of designing jackets. Experimentally, we study a cloud-based implementation of NSGA-J and present our results and experiences. The paper ends with a discussion of lessons learned and sketches opportunities for future research. We hope to inspire future work on complex applications of structural design optimization including jacket design optimization.