Multi-fidelity Surrogates

Modeling, Optimization and Applications
1. Auflage 2023
ISBN: 978-981-19-7209-6
Verlag: Springer

Buch, Englisch, 456 Seiten, Format (B × H): 160 mm x 241 mm, Gewicht: 940 g

Reihe: Engineering Applications of Computational Methods

This book investigates two types of static multi-fidelity surrogates modeling approaches, sequential multi-fidelity surrogates modeling approaches, the multi-fidelity surrogates-assisted efficient global optimization, reliability analysis, robust design optimization, and evolutionary optimization. Multi-fidelity surrogates have attracted a significant amount of attention in simulation-based design and optimization in recent years. Some real-life engineering design problems, such as prediction of angular distortion in the laser welding, optimization design of micro-aerial vehicle fuselage, and optimization design of metamaterial vibration isolator, are also provided to illustrate the ability and merits of multi-fidelity surrogates in support of engineering design. Specifically, lots of illustrative examples are adopted throughout the book to help explain the approaches in a more “hands-on” manner. This book is a useful reference for postgraduates and researchers of mechanical engineering, as well as engineers of enterprises in related fields.

Zielgruppe

Research

Autoren/Hrsg.

Zhou, Qi

Zhao, Min

Hu, Jiexiang

Ma, Mengying

Fachgebiete

• Mathematik | Informatik Mathematik Numerik und Wissenschaftliches Rechnen Angewandte Mathematik, Mathematische Modelle
• Mathematik | Informatik Mathematik Numerik und Wissenschaftliches Rechnen Optimierung
• Technische Wissenschaften Technik Allgemein Mathematik für Ingenieure
• Technische Wissenschaften Technik Allgemein Konstruktionslehre und -technik
• Technische Wissenschaften Maschinenbau | Werkstoffkunde Maschinenbau Konstruktionslehre, Bauelemente, CAD

Inhaltsverzeichnis

Preface

Chapter 1 Introduction

1.1 Merits of multi-fidelity surrogates

1.2 Multi-fidelity surrogates in engineering design: a short review

Chapter 2 Hierarchical multi-fidelity surrogates modeling

2.1 Generalized hierarchical Co-Kriging for multi-fidelity surrogates modeling

2.2 Space mapping method for multi-fidelity surrogates modeling

2.3 Bumpiness of scaling function reduction method for multi-fidelity surrogates modeling

2.4 Differing mapping method for multi-fidelity surrogates modeling

Chapter 3 Non-Hierarchical multi-fidelity surrogates modeling

3.1 Variance-weighted sum method for multi-fidelity surrogates modeling

3.2 Derivative of scaling function reduction method for multi-fidelity surrogates modeling

3.3 Multi-output Gaussian process model for multi-fidelity surrogates modeling

Chapter 4 Sequential multi-fidelity surrogates modeling

4.1 Predicted improvement level based sequential multi-fidelity surrogates modeling

4.2 Weighted cumulative error based sequential multi-fidelity surrogates modeling

4.3 Bootstrap estimator based sequential multi-fidelity surrogates modeling

Chapter 5 Multi-fidelity surrogates assisted efficient global optimization

5.1 Lower confidence bounding method for multi-fidelity efficient global optimization

5.2 Probability of improvement method for multi-fidelity efficient global optimization

5.3 Space preselection method for multi-fidelity efficient global optimization

Chapter 6 Multi-fidelity surrogates assisted reliability design optimization

6.1 Lower confidence bounding method for multi-fidelity surrogates assisted reliability design optimization

6.2 A contour prediction method for multi-fidelity surrogates assisted reliability design optimization

Chapter 7 Multi-fidelity surrogates assisted robust design optimization

7.1 Multi-fidelity surrogates assisted six sigma robust optimization

7.2 Multi-fidelity surrogates assisted sequential robust optimization

7.3 Conservative multi-fidelity surrogates assisted robust optimization

Chapter 8 Multi-fidelity surrogates assisted evolutional optimization

8.1 Multi-fidelity surrogates assisted multi-objective genetic algorithm

8.2 Multi-level multi-fidelity surrogates assisted multi-objective genetic algorithm

8.3 On-line multi-fidelity surrogates assisted multi-objective genetic algorithm

Chapter 9 Engineering Applications

9.1 Prediction of angular distortion in the laser welding

9.2 Optimization design of micro-aerial vehicle fuselage

9.3 Optimization design of metamaterial vibration isolator

9.4 Optimization design of the radome of the missile

9.5 Optimization design of a stiffened cylindrical shell with variable ribs

Chapter 10 Concluding remarks

10.1 Conclusions

10.2 Challenges

Appendix

Reference

Über Autor(innen)

Dr. Qi Zhou is an associate professor at the School of Aerospace Engineering, Huazhong University of Science and Technology (HUST), Wuhan, China. Dr. Zhou was a visiting scholar of Imperial College London and a joint Ph.D. of Georgia Tech. He was awarded the first batch of national defense innovation "leading funds". Also, he was selected for the China Science and Technology Association's "Young Talent Trusted Project", the major talent plan of the department of education, Hubei Province, the plan of "Excellent Young Teacher Training", "Huazhong Excellent Scholars", and the "Academic Newcomer Award" of Huazhong University of Science and Technology. His research expertise areas include the intelligent design of equipment, multi-fidelity surrogate model, and design optimization under uncertainty. He was the session chair of the International Conference on System Modeling and Optimization and the 9th International Conference on Control, Mechatronics, and Automation. He also served as the special editor for the international journal "Sensors" and "Applied sciences". He is a senior member of the American Institute of Aeronautics and Astronautics (AIAA) and the Chinese Society of Mechanical Engineering (CMES). He has published over 100 peer-reviewed international journal and conference papers.

Min Zhao is the chief engineer of the China Academy of Launch Vehicle Technology (CALT), Beijing. He began his career at the CALT as an engineer for overall rocket design. He has successively worked as an engineer, a senior engineer, a research fellow, a department leader, and a chief engineer since 1987. He also completed his Ph.D. in 2005. He has been engaged in the overall design of aerospace craft for the past 30 years, gathering unique insights into aircraft performance. Due to his outstanding achievements, he has been selected for the National Prize for Progress in Science and Technology (Top Grade) twice and the Aerospace Merit Award once. Thanks to the support of Tsinghua University, the China Academy of Aerospace Aerodynamics, the Institute of Mechanics (CAS), and the CALT, he has conducted extensive research on engineering application technologies.

Dr. Jiexiang Hu is an assistant professor at the School of Aerospace Engineering, Huazhong University of Science and Technology (HUST), Wuhan, China. His research interests include multi-fidelity surrogate models, model calibration and validation, and surrogate model-based aircraft structural design and optimization. He has published over 30 peer-reviewed international journal and conference papers.

Mengying Ma is a senior engineer of the China Academy of Launch Vehicle Technology (CALT). She has been engaged in the overall design of the launch vehicle since 2011. Her research interests include multidisciplinary design optimization of vehicles and integrated design of vehicles. She has published over 10 peer-reviewed international journal and conference papers and authorized over 10 patents.