Название: Metaheuristics Algorithm and Optimization of Engineering and Complex Systems
Автор: Thanigaivelan R., Suchithra M., Kaliappan S., Mothilal T.
Издательство: IGI Global
Год: 2024
Страниц: 416
Язык: английский
Формат: pdf (true), epub
Размер: 23.6 MB

In the field of engineering, optimization and decision-making have become pivotal concerns. The ever-increasing demand for data processing has given rise to issues such as extended processing times and escalated memory utilization, posing formidable obstacles across various engineering domains. Problems persist, requiring not only solutions but advancements beyond existing best practices. Creating and implementing novel heuristic algorithms is a time-intensive process, yet the imperative to do so remains strong, driven by the potential to significantly lower computational costs even with marginal improvements. This book, titled Metaheuristics Algorithm and Optimization of Engineering and Complex Systems, is a beacon of innovation in this context. It examines the critical need for inventive algorithmic solutions, exploring hyperheuristic approaches that offer solutions such as automating search spaces through integrated heuristics. Designed to cater to a broad audience, this book is a valuable resource for both novice and experienced dynamic optimization practitioners. By addressing the spectrum of theory and practice, as well as discrete versus continuous dynamic optimization, it becomes an indispensable reference in a captivating and emerging field. With a deliberate focus on inclusivity, the book is poised to benefit anyone with an interest in staying abreast of the latest developments in dynamic optimization.

Chapter 1 investigates the possibilities of solving complex fluid dynamics problems using Navier-Stokes equations, through simulation based techniques using deep neural networks in real time and along with provision of a singular architecture that achieves cutting-edge performance while maintaining a very high accuracy and precision at par with ground truth. The study employs Graph Network-based Simulators (GNS) to compute system dynamics.

Chapter 2 proposes an integrated approach combining grey relational analysis (GRA) and particle swarm optimization (PSO) to optimize process parameters for Fused Deposition Modeling (FDM) 3D printing using Polylactic Acid (PLA) material. Experimental design based on definitive screening designs (DSD) is employed to identify optimal printing parameters, focusing on improving surface finish, dimensional accuracy, and impact strength.

Chapter 3 focuses on the optimisation of the wire electric discharge machining (WEDM) process for WE43 alloy using Machine Learning methods.
...
Chapter 12 discusses the extensive Investigation of Meta-Heuristics Algorithms for Optimization Problems. Metaheuristic algorithms represent a class of optimization techniques tailored to tackle intricate problems that defy resolution through conventional means. Drawing inspiration from natural phenomena like genetics, swarm dynamics, and evolution, these algorithms traverse expansive search spaces in pursuit of identifying the optimal solution to a given problem. Well-known examples include genetic algorithms, particle swarm optimization, ant colony optimization, simulated annealing, and tabu search. These methodologies find widespread application across diverse domains such as engineering, finance, and Computer Science.
...
Chapter 15 discusses the enhancement of system performance using pesche scheduling algorithm on multiprocessors. The scheduling techniques have been investigated by the job execution process in a system in order to maximize multiprocessor utilization. DPM (Dynamic Power Management) and DVFS (Dynamic Voltage and Frequency Scaling) are two general strategies for lowering energy use. PeSche (Performance enhanced Scheduling) is a proposed scheduling algorithm that has been designed for an optimal solution.
...
Chapter 17 presents an integrated approach to enhance the performance of grid-connected photovoltaic (PV) systems by combining sensor-based orientation with the Practical Swarm Optimization (PSO) algorithm for Maximum Power Point Tracking (MPPT) and a Proportional-Integral (PI) controller for DC voltage regulation. Solar positioning and infrared sensors provide real-time data, guiding the dynamic movement of the solar panel.