This book presents recent advances in data-driven global optimization methods, combining theoretical foundations with real-world applications to address complex engineering optimization challenges.
This book presents recent advances in data-driven global optimization methods, combining theoretical foundations with real-world applications to address complex engineering optimization challenges.
The book begins with an overview of the state of the art, key technologies and standard benchmark problems in the field. It then delves into several innovative approaches: space reduction-based, hybrid surrogate model-based and multi-surrogate model-based global optimization, followed by surrogate-assisted constrained global optimization, discrete global optimization and high-dimensional global optimization. These methods represent a variety of optimization techniques that excel in both optimization capability and efficiency, making them ideal choices for complex engineering optimization problems. Through benchmark test problems and real-world engineering applications, the book illustrates the practical implementation of these methods, linking established theories with cutting-edge research in industrial and engineering optimization.
Both a professional book and an academic reference, this title will provide valuable insights for researchers, students, engineers and practitioners in a variety of fields, including optimization methods and algorithms, engineering design and manufacturing and artificial intelligence and machine learning.
1. Introduction
2. Data-Driven Optimization Framework
3. Benchmark
Functions for Data-Driven Optimization Methods
4. MSSR: Multi-Start Space
Reduction Surrogate-Based Global Optimization Method
5. SOCE: Surrogate-Based
Optimization with Clustering-Based Space Exploration for Expensive Multimodal
Problems
6. HSOSR: Hybrid Surrogate-Based Optimization Using Space Reduction
for Expensive Black-Box Functions
7. MGOSIC: Multi-Surrogate-Based Global
Optimization Using a Score-Based Infill Criterion
8. SCGOSR: Surrogate-Based
Constrained Global Optimization Using Space Reduction
9. KTLBO:
Kriging-Assisted Teaching-Learning-Based Optimization to Solve
Computationally Expensive Constrained Problems
10. KDGO: Kriging-Assisted
Discrete Global Optimization for Black-Box Problems with Costly Objective and
Constraints
11. SAGWO: Surrogate-Assisted Grey Wolf Optimization for
High-Dimensional, Computationally Expensive Black-Box Problems
Huachao Dong is Associate Professor at the School of Marine Science and Technology at Northwestern Polytechnical University, China. His research includes underwater vehicle design, digital design, multidisciplinary optimization, digital twins for underwater vehicles and data-driven global optimization, with over 50 peer-reviewed papers and 1 book published.
Peng Wang is Professor at the School of Marine Science and Technology at Northwestern Polytechnical University, China. His research focuses on surrogate-based design optimization, multidisciplinary design optimization, multicriteria decision-making and the design of underwater vehicles, with over 150 peer-reviewed papers and 6 books published.
Jinglu Li is an assistant researcher at Harbin Engineering University, China. His research includes underwater vehicle design, multidisciplinary optimization, digital twins and data-driven global optimization and he has published over 20 peer-reviewed papers.
