A new neural network-assisted hybrid chaotic hiking optimization algorithm for optimal design of engineering components

Abstract

In the era of artificial intelligence (AI), optimization and parametric studies of engineering and structural systems have become feasible tasks. AI and ML (machine learning) offer advantages over classical optimization techniques, which often face challenges such as slower convergence, difficulty handling multiobjective functions, and high computational time. Modern AI and ML techniques may not effectively address all critical design engineering problems despite these advancements. Nature-inspired algorithms based on physical phenomena in nature, human behavior, swarm intelligence, and evolutionary principles present a viable alternative for multidisciplinary design optimization challenges. This article explores the optimization of various engineering problems using a newly developed modified hiking optimization algorithm (HOA). The algorithm is inspired by human hiking techniques, such as hill climbing and hiker speed. The advantages of the modified HOA are compared with those of several famous algorithms from the literature, demonstrating superior results in terms of statistical measures.