Reducing bias and inefficiency in the selection algorithm
Proceedings of the Second International Conference on Genetic Algorithms on Genetic algorithms and their application
Design of truss-structures for minimum weight using genetic algorithms
Finite Elements in Analysis and Design
An Introduction to Genetic Algorithms
An Introduction to Genetic Algorithms
Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
A First Course in Fuzzy and Neural Control
A First Course in Fuzzy and Neural Control
Cost Optimization of Structures: Fuzzy Logic, Genetic Algorithms, and Parallel Computing
Cost Optimization of Structures: Fuzzy Logic, Genetic Algorithms, and Parallel Computing
A neuro-fuzzy evaluation of steel beams patch load behaviour
Advances in Engineering Software
Nature-Inspired Metaheuristic Algorithms
Nature-Inspired Metaheuristic Algorithms
ICNC '09 Proceedings of the 2009 Fifth International Conference on Natural Computation - Volume 04
Comparison of non-deterministic search techniques in the optimum design of real size steel frames
Computers and Structures
Engineering Optimization: An Introduction with Metaheuristic Applications
Engineering Optimization: An Introduction with Metaheuristic Applications
Quantum-inspired evolutionary algorithm for a class of combinatorial optimization
IEEE Transactions on Evolutionary Computation
Multiobjective topology optimization of truss structures with kinematic stability repair
Structural and Multidisciplinary Optimization
Sensitivity analysis of fuzzy-genetic approach applied to cabled-truss design
Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology
Hi-index | 0.00 |
This paper demonstrates an application of a hybrid fuzzy-genetic system in the optimisation of lightweight cabled-truss structures. These structures are described as a system of cables and triangular bar formations jointed at their ends by hinged connections to form a rigid framework. The optimised lightweight structure is determined through a stochastic discrete topology and sizing optimisation procedure that uses ground structure approach, nonlinear finite element analysis, genetic algorithm, and fuzzy logic. The latter is used to include expertise into the evolutionary search with the aim of filtering individuals with low survival possibility, thereby decreasing the total number of evaluations. This is desired because cables, which are inherently nonlinear elements, demand the use of iterative procedures for computing the structural response. Such procedures are computationally costly since the stiffness matrix is evaluated in each iteration until the structure is in equilibrium. Initially, the proposed system is applied to truss benchmarks. Next, the use of cables is investigated and the system's performance is compared against genetic algorithms. The results indicate that the hybrid system considerably decreased the number of evaluations over genetic algorithms. Also, cabled-trusses showed a significant improvement in structural mass minimisation when compared with trusses.