This book systematically analyzes the applicability of big data analytics and Industry 4.0 from the perspective of semiconductor manufacturing management. It reports in real examples and presents case studies as supporting evidence. In recent years, technologies of big data analytics and Industry 4.0 have been frequently applied to the management of semiconductor manufacturing. However, related research results are mostly scattered in various journal issues or conference proceedings, and there is an urgent need for a systematic integration of these results. In addition, many related discussions have placed too much emphasis on the theoretical framework of information systems rather than on the needs of semiconductor manufacturing management. This book addresses these issues.
Author(s): Tin-Chih Toly Chen
Series: SpringerBriefs in Applied Sciences and Technology
Edition: 1st ed. 2023
Publisher: Springer
Year: 2022
Language: English
Pages: 105
Contents
1 Big Data Analytics for Semiconductor Manufacturing
1.1 Big Data and Big Data Analytics
1.2 Big Data Analytics for Manufacturing
1.3 Classification of Big Data Analytics Techniques and Tools
1.4 Big Data Analytics for Semiconductor Manufacturing
1.5 Assessing the Benefits of Big Data Analytics for Semiconductor Manufacturing
1.6 Problems with Existing Methods
1.7 Organization of This Book
References
2 Industry 4.0 for Semiconductor Manufacturing
2.1 Industry 4.0
2.2 Industry 4.0 for Manufacturing
2.2.1 Cyber-Physical Systems
2.2.2 Digital Twins
2.2.3 Internet of Machines
2.2.4 Cloud and Ubiquitous Manufacturing
2.3 Industry 4.0 for Semiconductor Manufacturing
2.3.1 Cyber-Physical System Applications
2.3.2 Internet of Things Applications
2.3.3 Problems with Existing Methods
References
3 Cycle Time Prediction and Output Projection
3.1 Cycle Time Prediction in Semiconductor Manufacturing
3.2 Industry 4.0 and Big Data Analytics for Cycle Time Prediction
3.3 Cycle Time Prediction Methods
3.3.1 Production Simulation
3.3.2 Principal Component Regression
3.3.3 Parallel Radial Basis Function Networks
3.3.4 Classifying Feedforward Neural Networks
3.3.5 Fuzzy C-Means-Back Propagation Network Ensemble
3.3.6 Random Forest
References
4 Defect Pattern Analysis, Yield Learning Modeling, and Yield Prediction
4.1 Defect Pattern Analysis
4.2 k-means Application
4.3 Parallel k-means Application
4.4 Applications of Other Machine Learning and Artificial Intelligence Techniques
4.5 Yield Learning Modeling and Yield Forecasting
References
5 Job Sequencing and Scheduling
5.1 Job Sequencing and Scheduling in Semiconductor Manufacturing
5.2 Industry 4.0 Applications
5.2.1 Cyber-Physical System and Internet of Things Applications
5.2.2 Radio Frequency Identification and Internet of Machines Applications
5.3 Big Data Analytics Applications
5.3.1 Dispatching Rules Based on Big Data Analytics
5.3.2 Optimization Using Big Data Analytics
5.3.3 Multiple-Criteria Job Dispatching Based on Big Data Analytics
5.3.4 Optimization Using Big Data Analytics
5.3.5 Decomposition of a Big-Data Job Scheduling Problem
References
