A Constraint-Handling Technique for Genetic Algorithms using a Violation Factor

This article presents a newly proposed selection process for genetic algorithms on a class of unconstrained optimization problems. The k-means genetic algorithm selection process (KGA) is composed of four essential stages: clustering, membership phase, fitness scaling and selection. Inspired from the hypothesis that clustering the population helps to preserve a selection pressure throughout the evolution of the population, a membership probability index is assigned to each individual following the clustering phase. Fitness scaling converts the membership scores in a range suitable for the selection function which selects the parents of the next generation. Two versions of the KGA process are presented: using a fixed number of clusters K (KGA_f) and via an optimal partitioning K_opt (KGA_o) determined by two different internal validity indices. The performance of each method is tested on seven benchmark problems.

Wind Turbine Design: Multi‐Objective Optimization | InTechOpen, Published on: 2016-07-27. Authors: Adam Chehouri, Rafic Younes, Adrian Ilinca, et

The search for more efficient and sustainable renewable energies is rapidly growing. Throughout the years, wind turbines matured towards a lowered cost-of-energy and have grown in rotor size therefore stretched the role of composite materials that offered the solution to more flexible, lighter and stronger blades. The objective of this paper is to present an improved version of the preliminary optimization tool called Co-Blade, which will offer designers and engineers an accelerated design phase by providing the capabilities to rapidly evaluate alternative composite layups and study their effects on static failure and fatigue of wind turbine blades. In this study, the optimization formulations include non-linear failure constraints. In addition a comparison between 3 formulations is made to show the importance of choosing the blade mass as the main objective function and the inclusion of failure constraints in the wind turbine blade design.

Executed outdoors in high-wind areas, adverse weather conditions represent a significant risk to onshore wind farm construction activities. While methods for considering historical weather data during pre-construction scheduling are available, approaches capable of quantitatively assessing how short-term weather fluctuations may impact upcoming construction activities have yet to be developed. This study is proposing a hybrid simulation-based approach that uses short-term precipitation, wind speed, and temperature forecasts together with planned and as-built activity durations to develop lookahead (e.g., upcoming 14-day) schedules for improved project planning and control. Functionality and applicability of the method was demonstrated on a case study of a 40 MW onshore wind project, and the method was validated using event validity, face validation, and sensitivity analysis. As expected, favorable weather conditions experienced during the tested lookahead periods resulted in a negligible impact (less than 10% reduction) on the productivity of weather-sensitive activities, which translated into a project delay of one day. The responsiveness of the framework was confirmed through sensitivity analysis, which demonstrated a 50% reduction in productivity resulting from poor weather conditions. The ability of the method to provide decision-support not currently offered by commercially-available scheduling systems was confirmed by subject experts, who endorsed the ability of the method to enhance lookahead scheduling and to facilitate the monitoring and control of weather impact uncertainty on project durations.