Showing 25 results for Metaheuristic Algorithm
V. Goodarzimehr, F. Salajegheh,
Volume 14, Issue 1 (1-2024)
Abstract
The analysis and design of high-rise structures is one of the challenges faced by researchers and engineers due to their nonlinear behavior and large displacements. The moment frame system is one of the resistant lateral load-bearing systems that are used to solve this problem and control the displacements in these structures. However, this type of structural system increases the construction costs of the project. Therefore, it is necessary to develop a new method that can optimize the weight of these structures. In this work, the weight of these significant structures is optimized by using one of the latest metaheuristic algorithms called special relativity search. The special relativity search algorithm is mainly developed for the optimization of continuous unconstrained problems. Therefore, a penalty function is used to prevent violence of the constraints of the problem, which are tension, displacement, and drift. Also, using an innovative technique to transform the discrete problem into a continuous one, the optimal design is carried out. To prove the applicability of the new method, three different problems are optimized, including an eight-story one-span, a fifteen-story three-span bending frame, and a twenty-four-story three-span moment frame. The weight of the structure is the objective function, which should be minimized to the lowest possible value without violating the constraints of the problem. The calculation of stress and displacements of the structure is done based on the regulations of AISC-LRFD requirements. To validate, the results of the proposed algorithm are compared with other advanced metaheuristic methods.
S. L. Seyedoskouei, Dr. R. Sojoudizadeh, Dr. R. Milanchian, Dr. H. Azizian,
Volume 14, Issue 3 (6-2024)
Abstract
The optimal design of structural systems represents a pivotal challenge, striking a balance between economic efficiency and safety. There has been a great challenge in balancing between the economic issues and safety factors of the structures over the past few decades; however, development of high-speed computing systems enables the experts to deal with higher computational efforts in designing structural systems. Recent advancements in computational methods have significantly improved our ability to address this challenge through sophisticated design schemes. The main purpose of this paper is to develop an intelligent design scheme for truss structures in which an optimization process is implemented into this scheme to help the process reach lower weights for the structures. For this purpose, the Artificial Rabbits Optimization (ARO) algorithm is utilized as one of the recently developed metaheuristic algorithms which mimics the foraging behaviour of the rabbits in nature. In order to reach better solutions, the improved version of this algorithm is proposed as I-ARO in which the well-known random initialization process is substituted by the Diagonal Linear Uniform (DLU) initialization procedure. For numerical investigations, 5 truss structures 10, 25, 52, 72, and 160 elements are considered in which stress and displacement constraints are determined by considering discrete design variables. By conducting 50 optimization runs for each truss structure, it can be concluded that the I-ARO algorithm is capable of reaching better solutions than the standard ARO algorithm which demonstrates the effects of DLU in enhancing this algorithm’s search behaviour.
P. Hosseini, A. Kaveh, A. Naghian, A. Abedi,
Volume 14, Issue 3 (6-2024)
Abstract
This study aimed to develop and optimize artificial stone mix designs incorporating microsilica using artificial neural networks (ANNs) and metaheuristic optimization algorithms. Initially, 10 base mix designs were prepared and tested based on previous experience and literature. The test results were used to train an ANN model. The trained ANN was then optimized using SA-EVPS and EVPS algorithms to maximize 28-day compressive strength, with aggregate gradation as the optimization variable. The optimized mixes were produced and tested experimentally, revealing some discrepancies with the ANN predictions. The ANN was retrained using the original and new experimental data, and the optimization process was repeated iteratively until an acceptable agreement was achieved between predicted and measured strengths. This approach demonstrates the potential of combining ANNs and metaheuristic algorithms to efficiently optimize artificial stone mix designs, reducing the need for extensive physical testing.
F. Biabani, A. A. Dehghani, S. Shojaee, S. Hamzehei-Javaran,
Volume 14, Issue 3 (6-2024)
Abstract
Optimization has become increasingly significant and applicable in resolving numerous engineering challenges, particularly in the structural engineering field. As computer science has advanced, various population-based optimization algorithms have been developed to address these challenges. These methods are favored by most researchers because of the difficulty of calculations in classical optimization methods and achieving ideal solutions in a shorter time in metaheuristic technique methods. Recently, there has been a growing interest in optimizing truss structures. This interest stems from the widespread utilization of truss structures, which are known for their uncomplicated design and quick analysis process. In this paper, the weight of the truss, the cross-sectional area of the members as discrete variables, and the coordinates of the truss nodes as continuous variables are optimized using the HGPG algorithm, which is a combination of three metaheuristic algorithms, including the Gravity Search Algorithm (GSA), Particle Swarm Optimization (PSO), and Gray Wolf Optimization (GWO). The presented formulation aims to improve the weaknesses of these methods while preserving their strengths. In this research, 15, 18, 25, and 47-member trusses were utilized to show the efficiency of the HGPG method, so the weight of these examples was optimized while their constraints such as stress limitations, displacement constraints, and Euler buckling were considered. The proposed HGPG algorithm operates in discrete and continuous modes to optimize the size and geometric configuration of truss structures, allowing for comprehensive structural optimization. The numerical results show the suitable performance of this process.
A. Kaveh, N. Khavaninzadeh,
Volume 14, Issue 4 (10-2024)
Abstract
In this paper, a neural network is trained for optimal nodal ordering of graphs to obtain a small wavefront using soft computing. A preference function consists of six inputs that can be seen as a generalization of Sloan's function. These six inputs represent the different connection characteristics of graph models. This research is done with the aim of comparing Sloan's theoretical numbering method with Sloan's developed method with neural networks and WSA meta-heuristic algorithm. Unlike the Sloan algorithm, which uses two fixed coefficients, six coefficients are used here, based on the evaluation of artificial neural networks. The weight of networks is obtained using Water Strider algorithm. Examples are included to demonstrate the performance of the present hybrid method.
