Back to Search
Start Over
Cooperative Co-Evolution-Based Design Optimization: A Concurrent Engineering Perspective.
- Source :
- IEEE Transactions on Evolutionary Computation; Apr2018, Vol. 22 Issue 2, p173-188, 16p
- Publication Year :
- 2018
-
Abstract
- As a well-known engineering practice, concurrent engineering (CE) considers all elements involved in a product’s life cycle from the early stages of product development, and emphasizes executing all design tasks simultaneously. As a result, there exist various complex design problems in CE, which usually have many design parameters or require different disciplinary knowledge to solve them. To address these problems and enable concurrent design, different methods have been developed. The original problem is usually divided into small subproblems so that each subproblem can be solved individually and simultaneously. However, good decomposition, optimization, and communication strategies among subproblems are still needed in the field of CE. This paper attempts to study and analyze cooperative co-evolution (CC) based design optimization in CE by employing a parallel CC framework. Furthermore, it aims to develop new concurrent design methods based on parallel CC to solve different kinds of CE problems. To achieve this goal, a new novelty-driven CC is developed for design problems with complex structures and a novel concurrent design method is presented for quasi-separable multidisciplinary design optimization (MDO) problems. The efficacy of the new methods is studied on universal electric motor design problems and a general MDO problem, and compared to that of some existing methods. Additionally, this paper studies how the communication frequency among subpopulations affects the performance of the proposed methods. The optimal communication frequencies under different communication costs are reported as experimental results for both proposed methods on the test problems. Based on this paper, an effective self-adaptive method is proposed to be used in both optimization schemes, which is able to adapt the communication frequency during the optimization process. [ABSTRACT FROM PUBLISHER]
Details
- Language :
- English
- ISSN :
- 1089778X
- Volume :
- 22
- Issue :
- 2
- Database :
- Complementary Index
- Journal :
- IEEE Transactions on Evolutionary Computation
- Publication Type :
- Academic Journal
- Accession number :
- 128843373
- Full Text :
- https://doi.org/10.1109/TEVC.2017.2713949