Search

Functionally Graded Porous Structures: Applied Methods in Mechanical Performance Evaluation, Machine Learning Aided Analysis, and Additive Manufacturing presents a state-of-the-art review of the latest advances and cutting-edge technologies in this important research field. The book is divided into three key sections. The first section begins with an introduction to functionally graded porous structures and details the effects of graded porosities on bending, buckling, and vibration behaviours within the framework of Timoshenko beam theory, and first-order shear deformable plate theory. The second section is focused on the usage of machine learning techniques for smart structural analysis of porous components as an evolution from traditional engineering, methods. The third section focuses on additive manufacturing of structures with graded porosities for end-user applications. The book follows a clear path from design and analysis to fabrication and applications. Readers will find extensive knowledge and examples of functionally graded porous structures that are suitable for innovative research and market needs, with applications relevant to a diverse range of industrial fields, including mechanical, structural, aerospace, energy, and biomedical engineering. - Provides a comprehensive picture of novel porous materials and advanced lightweight structural technologies that are applicable to a diverse range of industrial sectors - Updated with the most recent advances in the field of porous structures - Goes beyond traditional structural aspects and covers novel evaluation strategies, machine learning aided analysis, and additive manufacturing - Covers weight management strategies for structural components to achieve multifunctional purposes - Addresses key issues in the design of lightweight structures, offering significant environmental benefits

In recent years, the support vector machine (SVM), a new data processing method, has been applied to many fields of chemistry and chemical technology. Compared with some other data processing methods, SVM is especially suitable for solving problems of small sample size, with superior prediction performance. SVM is fast becoming a powerful tool of chemometrics. This book provides a systematic approach to the principles and algorithms of SVM, and demonstrates the application examples of SVM in QSAR/QSPR work, materials and experimental design, phase diagram prediction, modeling for the optimal control of chemical industry, and other branches in chemistry and chemical technology.