---

This article aims to study the self-supporting truss towers used to support large wind turbines. The goal is to evaluate and validate numerically by finite element method the structural analysis when the lattice structures of the towers of wind turbines are subjected to static loads and these from common usage. With this, it is expected to minimize the cost of transportation and installation of the tower and maximize the generation of electricity, considering technical standards and restrictions of structural integrity and safety, making vibration analysis and the required static and dynamic loads, thereby preventing failures by fractures or mechanical fatigue. Practical examples of towers will be designed by the system and will be tested in structural simulation programs using the Finite Element Method. This analysis is performed on the entire region coupling action of the turbine, with variable sensitivity to vibration levels. The results obtained for freestanding lattice tower are compared with the information of a tubular one designed to support the generator with the same characteristics. At the end of this work it was possible to observe the feasibility of using lattice towers that proved better as its structural performance but with caveats about its dynamic performance since the appearance of several other modes natural frequency thus reducing the intervals between them in low frequency and theoretically increase the risk of resonance.

---

The artificial neural network is such a model of biological neural networks containing some of their characteristics and being a member of intelligent dynamic systems. The purpose of applying ANN in civil engineering is their efficiency in some problems that do not have a specific solution or their solution would be very time-consuming. In this study, four different neural networks including FeedForward BackPropagation (FFBP), Radial Basis Function (RBF), Extended Radial Basis Function (ERBF), and Generalized Regression Neural Network (GRNN) have been efficiently trained to analyze large-scale space structures specifically double-layer barrel vaults focusing on their maximum element stresses. To investigate the efficiency of the neural networks, an example has been done and their corresponding results have been compared with their exact amounts obtained by the numerical solution.

---

Jellyfish Search (JS) is a recently developed population-based metaheuristic inspired by the food-finding behavior of jellyfish in the ocean. The purpose of this paper is to propose a quantum-based Jellyfish Search algorithm, named Quantum JS (QJS), for solving structural optimization problems. Compared to the classical JS, three main improvements are made in the proposed QJS: (1) a quantum-based update rule is adopted to encourage the diversification in the search space, (2) a new boundary handling mechanism is used to avoid getting trapped in local optima, and (3) modifications of the time control mechanism are added to strike a better balance between global and local searches. The proposed QJS is applied to solve frequency-constrained large-scale cyclic symmetric dome optimization problems. To the best of our knowledge, this is the first time that JS is applied in frequency-constrained optimization problems. An efficient eigensolution method for free vibration analysis of rotationally repetitive structures is employed to perform structural analyses required in the optimization process. The efficient eigensolution method leads to a considerable saving in computational time as compared to the existing classical eigensolution method. Numerical results confirm that the proposed QJS considerably outperforms the classical JS and has superior or comparable performance to other state-of-the-art optimization algorithms. Moreover, it is shown that the present eigensolution method significantly reduces the required computational time of the optimization process compared to the classical eigensolution method.

---

Despite the advantages of the plastic limit analysis of structures, this robust method suffers from some drawbacks such as intense computational cost. Through two recent decades, metaheuristic algorithms have improved the performance of plastic limit analysis, especially in structural problems. Additionally, graph theoretical algorithms have decreased the computational time of the process impressively. However, the iterative procedure and its relative computational memory and time have remained a challenge, up to now. In this paper, a metaheuristic-based artificial neural network (ANN), which is categorized as a supervised machine learning technique, has been employed to determine the collapse load factors of two-dimensional frames in an absolutely fast manner. The numerical examples indicate that the proposed method's performance and accuracy are satisfactory.