Application of a Machine Learning Algorithm for the Structural Optimization of Circular Arches with Different Cross-Sections

Abstract

Arches are employed for bridges. This particular type of structures, characterized by a very old use tradition, is nowadays, widely exploited because of its strength, resilience, cost-effectiveness and charm. In recent years, a more conscious design approach that focuses on a more proper use of the building materials combined with the increasing of the computational capability of the modern computers, has led the research in the civil engineering field to the study of optimization algorithms applications aimed at the definition of the best design parameters. In this paper, a differential formulation and a MATLAB code for the calculation of the internal stresses in the arch structure are proposed. Then, the application of a machine learning algorithm, the genetic algorithm, for the calculation of the geometrical parameters, that allows to minimize the quantity of material that constitute the arch structures, is implemented. In this phase, the method used to calculate the stresses has been considered as a constraint function to reduce the range of the solutions to the only ones able to bear the design loads with the smallest volume. In particular, some case studies with different cross-sections are reported to prove the validity of the method and to compare the obtained results in terms of optimization effectiveness.

Constraint handling techniques for metaheuristics: a state-of-the-art review and new variants

“…The solution of real-world, large-scale optimization problems within the field of structural engineering can only be achieved with a synergy of the following aspects (Melchiorre et al 2021;Lagaros et al 2022;Cucuzza et al 2022): (i) efficient numerical modelling of the physical problem; (ii) reliable numerical optimization algorithms for enhanced structural design; (iii) rationalized modelling of the system uncertainties (in the case of probabilistic design problems); and (iv) exploitation of modern High-Performance Computing (HPC) facilities. The original OCP (Lagaros 2014) and its evolution HP-OCP offer all aforementioned capabilities, including efficient numerical modelling tools and several MOAs with a great variety of embedded features and CHTs, while its implementation enables its straightforward upgrade to incorporate new tools and features.…”

Size and Shape Optimization of a Guyed Mast Structure under Wind, Ice and Seismic Loading

“…In optimization problems, the main goal is to find the best conditions in terms of the optimal set of design parameters collected in the design vector x, which minimizes an objective function (OF) f (x) [45][46][47]. These problems can be categorized into single-objective or multi-objective based on the number of OFs involved, and a further classification is based on the presence (or not) of constraints [48][49][50].…”

Child Identification Optimization Algorithm for AEB System of Autonomous Vehicle based on Machine Learning

“…The upper controller will transmit the relative speed and distance data between the vehicle and the obstacles in front obtained from the radar to the controller ECU after data filtering and coordinate system conversion. ECU integrates radar data and vehicle intrinsic sensor data, classifies the movement state of environmental targets, and grades the safety state of the current vehicle: if the current vehicle state is judged as safe, the brake actuator will not be triggered; If it is determined that the current vehicle motion status is maintained and there is a possibility of collision with obstacles in front (vehicle or stationary object), the brake actuator will be activated for automatic braking [10][11]. The lower controller controls the vehicle braking system to respond according to the expected deceleration output by the upper controller.…”