Tyagi A.K., Tiwari S., Soni G. (eds.) Data Analytics and Artificial Intelligence for Predictive Maintenance in Smart Manufacturing

CRC Press, 2025. — 419 p. — (Advances in Intelligent Decision-Making, Systems Engineering, and Project Management). – ISBN 978-1-032-77016-1.Аналитика данных и искусственный интеллект для предиктивного обслуживания в интеллектуальном производстве.
Data analytics and Artificial Intelligence (AI) or data mining techniques have emerged as essential tools for this decade which invite a new revolution in the way manufacturers manage their operations. This has resulted in a transformation in predictive maintenance (PdM), an indispensable strategy that uses the power of data and AI to optimize maintenance practices and, in doing so, redefine the manufacturing landscape/process. Hence, this book provides detail of various topics such as where it uses data analytics and Artificial Intelligence techniques in predictive maintenance in the manufacturing industry. This book will start with fundamental concepts, the transformative impact, and reasons why this convergence of technology and industry is not just a trend but a revolution.As we move on this journey through the realms of data, algorithms, sensors, and real-time decision-making, this book explain essential implications of these emerging (data analytics/data mining techniques) technologies on the future of manufacturing. It starts from data collection and preprocessing to the deployment of required Machine Learning models in the respective area. Through this book, we will discover how predictive analytics can identify equipment failures, extend the life of machinery, enhance safety, and drive cost-efficiency in manufacturing operations. The manufacturing industry has always been an essential of innovation, and today, it finds itself at a crossroads where tradition meets the future. Data analytics and AI are being used to transform the industry, its machinery, making manufacturing smarter, more efficient, and more sustainable. In the last, this book can serve as a reference guide to our readers which will inform about the latest advancements, trends, and tools relevant to predictive maintenance (with a global audience and addressing universal challenges faced by manufacturers).Data Analytics and Artificial Intelligence for Predictive Maintenance in Smart Manufacturing provides an extensive and in-depth exploration of the intersection of data analytics, Artificial Intelligence, and predictive maintenance in the manufacturing industry and covers fundamental concepts, advanced techniques, case studies, and practical applications. Using a multidisciplinary approach, this book recognizes that predictive maintenance in manufacturing requires collaboration among engineers, data scientists, and business professionals and includes case studies from various manufacturing sectors showcasing successful applications of predictive maintenance. The real-world examples explain the useful benefits and ROI achieved by organizations. The emphasis is on scalability, making it suitable for both small and large manufacturing operations, and readers will learn how to adapt predictive maintenance strategies to different scales and industries. This book presents resources and references to keep readers updated on the latest advancements, tools, and trends, ensuring continuous learning.Machine Learning, a subset of Artificial Intelligence (AI), has become a fundamental aspect of contemporary computing. Its capacity to enable systems to learn from data and independently make informed choices has sparked revolutionary advancements across various sectors. In recent years, the field has witnessed unprecedented growth, driven by advancements in computational power, data availability, and algorithmic sophistication. The essence of Machine Learning lies in its departure from traditional rule-based programming paradigms. Instead of relying on explicitly defined instructions, Machine Learning algorithms learn iteratively from data, continuously improving their performance as they encounter new examples. This change in perspective has unlocked numerous opportunities for diverse applications across a wide array of fields, spanning from healthcare and finance to transportation and entertainment.The allure of Machine Learning lies in its capability to extract insights, patterns, and relationships from vast amounts of data that may be too complex for human analysts to decipher manually. By discerning these patterns, Machine Learning algorithms can make predictions, identify anomalies, recommend actions, and automate decision-making processes, thus offering valuable assistance to human operators and augmenting their capabilities. In the Chapter 1, we embark on a journey to explore the fundamental concepts and principles that underpin Machine Learning. We delve into the core types of machine learning, namely supervised, unsupervised, and reinforcement learning, elucidating their respective methodologies and applications. Additionally, we examine key techniques such as feature engineering, model selection, and evaluation, which play pivotal roles in the development and deployment of Machine Learning systems.Serving as a reference guide, this book focuses on the latest advancements, trends, and tools relevant to predictive maintenance and can also serve as an educational resource for students studying manufacturing, Data Science, or related fields.Preface
Introduction to Machine Learning Fundamentals
AI Applications in Production
Data Analytics and Artificial Intelligence for Predictive Maintenance in Manufacturing
Scalability and Deployment of Emerging Technologies in Predictive Maintenance
AI Models for Predictive Maintenance
Role of Machine Learning and Deep Learning Models for Predictive Maintenance
Data Analytics and AI for Predictive Maintenance in Pharmaceutical Manufacturing
Real-time Violence Detection in Video Streams: Exploiting ResNet-50 for Enhanced Accuracy
The Analytics Advantage: Sculpting Tomorrow’s Decisions Today
Using Ensemble Model to Reduce Downtime in Manufacturing Industry: An Advanced Diagnostic Framework for Early Failure Detection
Use Cases of Digital Twin in Smart Manufacturing
Data Analytics and Visualization in Smart Manufacturing Using AI-based Digital Twins
Business Analytics, Business Intelligence, and Paradigm Shift in Organizational Structure
Applications of Human Computer Interaction, Explainable Artificial Intelligence and Conversational Artificial Intelligence in Real-life Sectors
AI for Industry 4.0 with Real-world Problems
Industry 4.0 in Manufacturing, Communication, Transportation, Healthcare
Advancing IoT Anomaly Detection through Dynamic Learning