Machine Learning for Powder-Based Metal Additive Manufacturing
- 1st Edition - September 4, 2024
- Imprint: Elsevier
- Editors: Gurminder Singh, Farhad Imani, Asim Tewari, Sushil Mishra
- Language: English
- Paperback ISBN:9 7 8 - 0 - 4 4 3 - 2 2 1 4 5 - 3
- eBook ISBN:9 7 8 - 0 - 4 4 3 - 2 2 1 4 6 - 0
Machine Learning for Powder-based Metal Additive Manufacturing outlines machine learning (ML) methods for additive manufacturing (AM) of metals that will improve product quality,… Read more
Purchase options
Institutional subscription on ScienceDirect
Request a sales quoteMachine Learning for Powder-based Metal Additive Manufacturing outlines machine learning (ML) methods for additive manufacturing (AM) of metals that will improve product quality, optimize manufacturing processes, and reduce costs. The book combines ML and AM methods to develop intelligent models that train AM techniques in pre-processing, process optimization, and post-processing for optimized microstructure, tensile and fatigue properties, and biocompatibility for various applications. The book covers ML for design in AM, ML for materials development and intelligent monitoring in metal AM, both geometrical deviation and physics informed machine learning modeling, as well as data-driven cost estimation by ML.
In addition, optimization for slicing and orientation, ML to create models of materials for AM processes, ML prediction for better mechanical and microstructure prediction, and feature extraction by sensing data are all covered, and each chapter includes a case study.
- Covers machine learning (ML) methods for additive manufacturing (AM) of metals that will improve product quality, optimize manufacturing processes, and reduce costs
- Combines ML and AM methods to develop intelligent models that train AM techniques in pre-processing, process optimization, and post-processing for optimized microstructure, tensile and fatigue properties, and biocompatibility for various applications
- Discusses algorithm development of ML for metal AM, metal AM process modeling and optimization, mathematical and simulation studies of metal AM, and pre- and post-processing smart methods for metal AM
Academics and industry professionals working in mechanical engineering, material science, product design and development, metallurgy, biomedical engineering, pharmaceutical, automobile, and aerospace engineering field, Graduate and doctoral students at universities and laboratory levels affiliated with mechanical engineering, materials science, product design and development, biomedical engineering, etc.
- Cover image
- Title page
- Table of Contents
- Copyright
- List of contributors
- 1. Overview of machine learning for additive manufacturing
- Abstract
- 1.1 Introduction
- 1.2 Additive manufacturing
- 1.3 Challenges in additive manufacturing
- 1.4 Machine learning
- 1.5 Machine learning in additive manufacturing
- 1.6 Potential and challenges
- 1.7 Summary
- References
- 2. Machine learning for design in additive manufacturing
- Abstract
- 2.1 Introduction
- 2.2 Hierarchical clustering for additive manufacturing design feature
- 2.3 Topological optimization in additive manufacturing
- 2.4 Trained geometric compensations
- 2.5 Geometrical optimization for slicing and orientation in additive manufacturing
- 2.6 Conclusions and future scope
- Acknowledgments
- References
- 3. Machine learning for materials developments in metals additive manufacturing
- Abstract
- 3.1 Introduction
- 3.2 Algorithm regarding the material analysis
- 3.3 Design space with data sources in additive manufacturing
- 3.4 Featurization and curation of material data
- 3.5 Precise alloy design and feedstock selection
- 3.6 Machine learning to create models of materials for additive manufacturing processes
- 3.7 Case study
- 3.8 Conclusions
- References
- 4. Physics-informed machine learning for metal additive manufacturing
- Abstract
- 4.1 Introduction
- 4.2 Background
- 4.3 Multiphysics-constrained neural networks with minimax architecture for predicting dendritic growth
- 4.4 Physics-constrained Bayesian neural network for grain growth
- 4.5 Physics-based compressive sensing
- 4.6 Physics-constrained dictionary learning for monitoring and diagnosis
- 4.7 Conclusions and future scope
- References
- 5. Machine learning-enabled powder-spreading process
- Abstract
- 5.1 Introduction
- 5.2 Physics-based discrete element method modeling for powder spreading
- 5.3 Application of discrete element method to powder spreading
- 5.4 Considerations and assumptions in physics-based modeling
- 5.5 Design of simulations for virtual spreading
- 5.6 Input parameters and boundary conditions
- 5.7 Validation of simulations
- 5.8 Machine learning-based spreading predictions
- 5.9 Spreading process mean average precision comparison with conventional methods
- 5.10 Evaluation metrics for comparison
- 5.11 Results and analysis
- 5.12 Application of machine learning-enabled powder spreading
- 5.13 Results and lessons learned
- 5.14 Conclusion and future scope
- References
- 6. Machine learning for metal additive manufacturing process optimization
- Abstract
- 6.1 Introduction
- 6.2 Literature review
- 6.3 Machine learning methods for process optimizations
- 6.4 Case studies for machine learning in the closed-loop system
- 6.5 Methodology
- 6.6 Machine learning prediction for better mechanical and microstructure prediction
- 6.7 Conclusion
- References
- 7. In situ monitoring and feature extraction in laser powder bed fusion
- Abstract
- 7.1 Introduction
- 7.2 Defect-inducing process phenomena
- 7.3 Monitoring equipment
- 7.4 Melt pool in situ monitoring
- 7.5 Plume and spatter in situ monitoring
- 7.6 Powder thickness and solid surface topography in situ monitoring
- 7.7 Other monitoring techniques and features
- 7.8 Summary, conclusions, and future directions
- References
- 8. Postprocessing optimization for surface finishing by machine learning
- Abstract
- 8.1 Postprocessing methods for surface finishing
- 8.2 Significant process parameters
- 8.3 ML literature for surface finishing
- 8.4 Optimization to minimize surface roughness
- 8.5 Case study
- 8.6 Conclusion and future scope
- References
- 9. Data-driven cost estimation in additive manufacturing using machine learning approaches
- Abstract
- 9.1 Introduction
- 9.2 Cost estimation in manufacturing
- 9.3 Advancements in big data processing and analytics
- 9.4 Cost estimation model in additive manufacturing
- 9.5 Case studies and applications of data-driven cost estimation in additive manufacturing
- 9.6 Challenges and limitations of data-driven cost estimation
- 9.7 Discussion on models
- 9.8 Conclusion
- References
- Index
- Edition: 1
- Published: September 4, 2024
- Imprint: Elsevier
- No. of pages: 400
- Language: English
- Paperback ISBN: 9780443221453
- eBook ISBN: 9780443221460
GS
Gurminder Singh
Prof. Gurminder Singh is currently working as an assistant professor at the mechanical engineering department, Indian Institute of Technology Bombay, India. He worked as a postdoc researcher in the school of mechanical and materials engineering at University College Dublin (UCD), Dublin, Ireland. Before joining UCD, Dr Singh was a Postdoc fellow at SIMAP Lab, University of Grenoble Alpes, France, where his research focused on the experimental and simulation studies of the extrusion 3D printing of metals. Dr Singh was Gandhian young Technological Innovation Award for the development of a 3D printing method for the fabrication of patient-specific stents in 2020. He has published over 26 articles in peer-reviewed international journals, conference proceedings and books. He has published in leading journals such as Additive Manufacturing, Materials Science and Engineering: A, Journal of Manufacturing Processes, Rapid Prototyping, etc.
Affiliations and expertise
Assistant Professor, Department of Mechanical Engineering, Indian Institute of Technology Bombay, Powai, Mumbai, IndiaFI
Farhad Imani
Prof. Farhad Imani is an assistant professor in the Department of Mechanical Engineering at the University of Connecticut (UConn). He is also an affiliated faculty in Institute of Material Science and Management and Engineering for Manufacturing programs at UConn. His research interests focus on data analytics, machine learning, statistical learning, and decision theory for process monitoring and control, system diagnostics and prognostics, quality and reliability improvement with applications in advanced manufacturing). Since his start of his appointment at University of Connecticut from 2020, he has obtained fundings (in total more than $4M) from multiple federal agencies, including ONR National Institute for Undersea Vehicle Technology (NIUVT), ARMY Combat Capabilities Development Command (DEVCOM) Ground Vehicle Systems Center (GVSC), Department of Army, and Department of Education. He has published over 40 articles in peer-reviewed international journals and conference proceedings such as Journal of Manufacturing Processes, ASME Journal of Manufacturing Science and Engineering, Journal of Manufacturing Systems, Smart and Sustainable Manufacturing Systems, IEEE Design Automation Conference, and International Solid Freeform Fabrication Symposium.
Affiliations and expertise
Assistant Professor, Department of Mechanical Engineering, University of Connecticut, Connecticut, USAAT
Asim Tewari
Prof. Asim Tewari is a Professor in the Department of Mechanical Engineering and a faculty member of the Center for Machine Intelligence and Data Science (C-MInDS) at the Indian Institute of Technology Bombay, Mumbai. Prior to this, he was a staff researcher at General Motors, Global R&D center in Bangalore. At IIT Bombay, he has been instrumental in setting up the National Center for Aerospace Innovation and Research and Center for Technical Textiles. He teaches short courses to industries on theory and application of machine learning data analytics and applied Finite Element Analysis. His personal area of research is in mathematical models for microstructural-mechanics. He has over 100 international journal & conference publications and ten international patents. His pioneering work in 3D microscopy imaging has been widely cited, including reproduction in ASM handbooks. He is on the editorial board of several international Journals, including Metallurgical and Materials Transactions and Image Analysis & Stereology. He is an advisory committee member for various national & international research boards and has won several awards and recognition for his research and teaching.
Affiliations and expertise
Professor, Department of Mechanical Engineering, Indian Institute of Technology Bombay, Mumbai, India
Faculty member, Center for Machine Intelligence and Data Science (C-MInDS), Indian Institute of Technology Bombay, Mumbai, IndiaSM
Sushil Mishra
Prof. Sushil Mishra is currently Professor in the Department of Mechanical Engineering, IIT Bombay. Prior to joining this position, he worked as Senior Manager in Aditya Birla Science and Technology Center, Mumbai and as senior researcher at General Motors Global R&D, Bangalore. He has more than four years of post doctorate research experience in corporate R&D. The focus of his research is multiscale physics based formability studies of metallic alloys. Currently he is heading Micro- Forming lab ( www.microforming.in )in IIT Bombay, where more than 15 postgraduate students are working in the area of forming, Additive manufacturing, microstructure, microtexture and materials modeling. He has published more than 70 peer reviewed international journal papers and 3 patents. Under his supervision 12 PhD and 15 M Tech students are graduated and currently 15 students are working under him as a postgraduate student at various sponsored project.
Affiliations and expertise
Professor, Department of Mechanical Engineering, Indian Institue of Technology, Bombary, IndiaRead Machine Learning for Powder-Based Metal Additive Manufacturing on ScienceDirect