Back to Search
Start Over
Mixture Optimization of Cementitious Materials Using Machine Learning and Metaheuristic Algorithms: State of the Art and Future Prospects.
- Source :
- Materials (1996-1944); Nov2022, Vol. 15 Issue 21, p7830, 30p
- Publication Year :
- 2022
-
Abstract
- The hybrid optimization of modern cementitious materials requires concrete to meet many competing objectives (e.g., mechanical properties, cost, workability, environmental requirements, and durability). This paper reviews the current literature on optimizing mixing ratios using machine learning and metaheuristic optimization algorithms based on past studies on varying methods. In this review, we first discuss the conventional methods for mixing optimization of cementitious materials. Then, the problem expression of hybrid optimization is discussed, including decision variables, constraints, machine learning algorithms for modeling objectives, and metaheuristic optimization algorithms for searching the best mixture ratio. Finally, we explore the development prospects of this field, including, expanding the database by combining field data, considering more influencing variables, and considering more competitive targets in the production of functional cemented materials. In addition, to overcome the limitation of the swarm intelligence-based multi-objective optimization (MOO) algorithm in hybrid optimization, this paper proposes a new MOO algorithm based on individual intelligence (multi-objective beetle antenna search algorithm). The development of computationally efficient robust MOO models will continue to make progress in the field of hybrid optimization. This review is adapted for engineers and researchers who want to optimize the mixture proportions of cementitious materials using machine learning and metaheuristic algorithms. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 19961944
- Volume :
- 15
- Issue :
- 21
- Database :
- Complementary Index
- Journal :
- Materials (1996-1944)
- Publication Type :
- Academic Journal
- Accession number :
- 160221450
- Full Text :
- https://doi.org/10.3390/ma15217830