Название: Artificial Intelligence in Tribology
Автор: Jashanpreet Singh, Hitesh Vasudev
Издательство: CRC Press
Серия: Advances in Surface Engineering and Tribology
Год: 2027
Страниц: 300
Язык: английский
Формат: True PDF, True EPUB
Размер: 73.8 MB

Artificial Intelligence in Tribology presents the use of Machine Learning, AI, neural networks, and optimization algorithms in studying friction, wear, and lubrication. It explores the selection of materials, modeling of the tribo‑system, prediction of tribological behavior, and assessment and optimization of performance across numerous systems.

Addressing tribological problems from macroscale to nanoparticles, this book discusses AI‑driven methods to improve productivity, detect disasters, and support sustainable engineering. Case studies from various industries, such as automotive, aerospace, renewable energy, and marine engineering, highlight the transformative impact of AI in real‑world scenarios.

This book is structured into different chapters to target diverse audience. It will be useful to researchers and academicians as a reference point to study the novelties in the existing approaches and future developments. Many engineers and industry specialists will find real-world methods that they could then use to apply AI to the tribological process. Students and young practitioners will find the material basics and case descriptions useful for understanding the gap between the academic and practical approaches.

In this book, the readers will explore a range of diverse topics such as Machine Learning models for wear analysis and optimization procedures for lubrication and surface engineering. Various case studies from different industries, such as automotive, aerospace and renewable, biomedical, and marine, will be presented to highlight the transformative impact of AI in real-world scenarios. Moreover, this book refers to difficulties and constraints, which makes it possible to acquire a critical view and invent solutions by questioning.

Machine Learning (ML) and Deep Learning (DL) are the subfields of AI that are the most applicable in terms of engineering and tribological practice. ML can be described as the process of training computers to learn by observing data and make predictions or decisions without their programmed implementation. It can be divided into three broad categories: first, supervised learning in which models are trained using labelled data to perform predictions (e.g., wear rate prediction); second, unsupervised learning where algorithms discover concealed patterns or groups in unclassified data (e.g., assembling materials in tribologically useful groupings); and third, reinforcement learning where systems can be taught on trial and error to maximize performance amid volatile environments. DL is a branch of ML deploying multi-layered ANNs in order to handle non-linear relationships that are not easy to handle. Neural networks are inspired by human brain structure and are composed of interconnected nodes (neurons) in layers- input, hidden, and output layers. These networks can be trained on complex relationships in large data sets and are therefore applicable to tribological analysis with a combination of several dependent parameters, including load and speed, among others. DL is based on neural networks.

This book will interest researchers and graduate students studying AI integration and advances in surface engineering, tribology, and materials science.

Contents: