We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Gaussian bare-bone slime mould algorithm: performance optimization and case studies on truss structures.
- Authors
Wu, Shubiao; Heidari, Ali Asghar; Zhang, Siyang; Kuang, Fangjun; Chen, Huiling
- Abstract
The slime mould algorithm (SMA) is a new meta-heuristic algorithm recently proposed. The algorithm is inspired by the foraging behavior of polycephalus slime moulds. It simulates the behavior and morphological changes of slime moulds during foraging through adaptive weights. Although the original SMA's performance is better than most swarm intelligence algorithms, it still has shortcomings, such as quickly falling into local optimal values and insufficient exploitation. This paper proposes a Gaussian barebone mutation enhanced SMA (GBSMA) to alleviate the original SMA's shortcomings. First of all, the Gaussian function in the Gaussian barebone accelerates the convergence while also expanding the search space, which improves the algorithm exploration and exploitation capabilities. Secondly, the differential evolution (DE) update strategy in the Gaussian barebone, using rand as the guiding vector. It also enhances the algorithm's global search performance to a certain extent. Also, the greedy selection is introduced on this basis, which prevents individuals from performing invalid position updates. In the IEEE CEC2017 test function, the proposed GBSMA is compared with a variety of meta-heuristic algorithms to verify the performance of GBSMA. Besides, GBSMA is applied to solve truss structure optimization problems. Experimental results show that the convergence speed and solution accuracy of the proposed GBSMA are significantly better than the original SMA and other similar products.
- Subjects
MYXOMYCETES; METAHEURISTIC algorithms; FORAGING behavior; DIFFERENTIAL evolution; GAUSSIAN function; SWARM intelligence; GLOBAL optimization
- Publication
Artificial Intelligence Review, 2023, Vol 56, Issue 9, p9051
- ISSN
0269-2821
- Publication type
Article
- DOI
10.1007/s10462-022-10370-7