Opinion - (2023) Volume 12, Issue 4
Received: 02-Sep-2023, Manuscript No. iem-23-118020;
Editor assigned: 04-Sep-2023, Pre QC No. P-118020;
Reviewed: 16-Sep-2023, QC No. Q-118020;
Revised: 21-Sep-2023, Manuscript No. R-118020;
Published:
28-Sep-2023
, DOI: 10.37421/2169-0316.2023.12.206
Citation: Yooin, Dootr. “Multi-aim Optimisation of Thin-walled Composite Axisymmetric Structures Employing Genetic Algorithms and Neural Surrogate Models.” Ind Eng Manag 12 (2023): 206.
Copyright: © 2023 Yooin D. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
In the field of structural engineering, the design and optimization of thinwalled composite axisymmetric structures pose unique challenges. These structures are widely used in various applications, including aerospace, automotive, and civil engineering, due to their lightweight, high strength, and superior structural performance. Achieving optimal designs for these structures requires addressing multiple objectives, such as minimizing weight, maximizing strength, and reducing manufacturing costs. Traditional optimization techniques can be computationally expensive and time-consuming, making them less practical for complex problems. In this context, Genetic Algorithms (GAs) and neural surrogate models offer a powerful solution for multi-objective optimization [1,2].
This article explores the application of genetic algorithms and neural surrogate models in the multi-objective optimization of thin-walled composite axisymmetric structures. We will delve into the key concepts and methodologies associated with this approach, highlighting its advantages and practical implications. Thin-walled composite axisymmetric structures consist of cylindrical or conical shapes with relatively thin walls. These structures are typically constructed by layering composite materials, such as carbon fiber or glass fiber, to achieve the desired mechanical properties. Due to their rotational symmetry, they are often found in components like pressure vessels, pipes, and aerospace components like rocket motor casings and aircraft fuselages [3,4]. The optimization of such structures is essential to ensure they meet performance requirements while minimizing weight and production costs. Genetic algorithms are a powerful optimization technique inspired by the process of natural selection. They are well-suited for solving complex problems with multiple objectives. GAsoperate by evolving a population of candidate solutions over several generations to reach the optimal solution or a set of Pareto-optimal solutions. The Pareto-optimal solutions represent the best trade-offs between conflicting objectives [5,6].
Designers can now make informed decisions based on the trade-offs between weight, strength, and manufacturing costs, tailoring the design to meet specific project requirements. Multi-objective optimization of thinwalled composite axisymmetric structures is a complex task with conflicting objectives. Genetic algorithms, in conjunction with neural surrogate models, provide a powerful and efficient solution to address these challenges. By combining the exploration capabilities of GAs with the prediction capabilities of surrogate models, designers can efficiently find optimal trade-offs and make informed decisions for their designs. This approach is particularly useful in industries such as aerospace, automotive, and civil engineering, where the performance, weight, and cost of structural components are critical factors. As computational power and machine learning techniques continue to advance, the integration of genetic algorithms and surrogate models in multi-objective optimization will become increasingly valuable, enabling the design of more efficient and cost-effective thin-walled composite axisymmetric structures.
None.
None.
Industrial Engineering & Management received 739 citations as per Google Scholar report
