Abstract | ||
---|---|---|
A truss is one of the most used engineering structures in daily life due to several advantages. A process for truss optimisation is usually set to minimise its mass while structural safety constraints are imposed. This design problem always leads to structures with less reliability since the solution is generally on the borderline of structural failure. Such a phenomenon can be alleviated by adding effects of all possible load cases with safety factors to design constraints. Alternatively, the design problem should be many-objective optimisation assigned to optimise mass and reliability indicators for all load cases. This paper is the first attempt to study such a design process. A number of many-objective meta-heuristics are employed to solve the test problems for many-objective truss optimization where their performances are compared. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1007/978-3-319-59072-1_18 | ADVANCES IN NEURAL NETWORKS, PT I |
Keywords | Field | DocType |
Many-objective optimisation,Truss design,Meta-heuristics,Evolutionary computation,Constrained optimisation | Truss,Mathematical optimization,Computer science,Safety constraints,Evolutionary computation,Artificial intelligence,Engineering structures,Design process,Machine learning,Metaheuristic | Conference |
Volume | ISSN | Citations |
10261 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 12 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nantiwat Pholdee | 1 | 39 | 8.08 |
Sujin Bureerat | 2 | 64 | 11.36 |
Papot Jaroenapibal | 3 | 0 | 0.68 |
Thana Radpukdee | 4 | 0 | 1.35 |