Additive manufacturing (AM), which builds a single part directly from a 3D CAD model in a layer-by-layer manner, can fabricate complex component with intricate geometry in a time- and cost-saving manner.AM is thus gaining ever-increasing popularity across many industries. However, accompanied with its unique building manner and benefits thereof are the significantly complicated physics behind the AM process. This fact poses great challenges in modeling and understanding the underlying process-structure-property (P-S-P) relationship, which however is vital to efficient AM process optimization and quality control. With the advancement of machine learning (ML) models and increasing availability of AM-related digital data, ML-based data-driven modeling has recently emerged as a promising approach towards exhaustively exploring and fully understanding AM P-S-P relationship. Nonetheless, many of existing ML-based AM modeling severely under-utilize the powerful ML models by using them as simple regression tools, and largely neglect their distinct advantage in explicitly handling complex-data (e.g., image and sequence) involved data-driven modeling problems and other versatilities. To further explore and unlock the tremendous potential of ML, this research aims to attack two significant research problems: (1) from the data or pre-data-driven-modeling aspect: can we use ML to improve AM data via ML-assisted data collection, processing and acquirement? (2) from the data driven modeling aspect: can we use ML to build more capable data-driven models, which can act as a full (or maximum) substitute of physics-based model for high-level AM modeling or even realistic AM simulation? To adequately address the above questions, the current research presents a ML-based data-driven AM modeling framework. It attempts to provide a comprehensive ML-based solution to data-driven modeling and simulation of various physical events throughout the AM lifecycle, from process to structure and property. A variety of ML models, including Gaussian process (GP), multilayer perceptron (MLP), convolutional neural network (CNN), recurrent neural network (RNN) and their variants, are leveraged to handle representative data-driven modeling problems with different quantities of interest (QoI). They include data-driven process modeling (melt pool, temperature field), structure modeling (porosity structure) and property modeling (stress field, stress-strain curve). The results show that this research can break existing limitations of those five data-driven AM modeling in terms of modeling fidelity, accuracy and/or efficiency. It thus well addresses the two research questions that are key in significantly advancing data-driven AM modeling. In addition, although the current research uses five representative physical events in AM as examples, the data-driven methodologies developed should shed light on data-driven modeling of many other physical events in AM and beyond.

Additive manufacturing (AM) is the process in which a three-dimensional object is built by adding subsequent layers of materials. AM enables novel material compositions and shapes, often without the need for specialized tooling. This technology has the potential to revolutionize how mechanical parts are created, tested, and certified. However, successful real-time AM design requires the integration of complex systems and often necessitates expertise across domains. Simulation-based design approaches, such as those applied in engineering product design and material design, have the potential to improve AM predictive modeling capabilities, particularly when combined with existing knowledge of the underlying mechanics. These predictive models have the potential to reduce the cost of and time for concept-to-final-product development and can be used to supplement experimental tests. The National Academies convened a workshop on October 24-26, 2018 to discuss the frontiers of mechanistic data-driven modeling for AM of metals. Topics of discussion included measuring and modeling process monitoring and control, developing models to represent microstructure evolution, alloy design, and part suitability, modeling phases of process and machine design, and accelerating product and process qualification and certification. These topics then led to the assessment of short-, immediate-, and long-term challenges in AM. This publication summarizes the presentations and discussions from the workshop.

"Additive manufacturing (AM) is the process in which a three-dimensional object is built by adding subsequent layers of materials. AM enables novel material compositions and shapes, often without the need for specialized tooling. This technology has the potential to revolutionize how mechanical parts are created, tested, and certified. However, successful real-time AM design requires the integration of complex systems and often necessitates expertise across domains. Simulation-based design approaches, such as those applied in engineering product design and material design, have the potential to improve AM predictive modeling capabilities, particularly when combined with existing knowledge of the underlying mechanics. These predictive models have the potential to reduce the cost of and time for concept-to-final-product development and can be used to supplement experimental tests. The National Academies convened a workshop on October 24-26, 2018 to discuss the frontiers of mechanistic data-driven modeling for AM of metals. Topics of discussion included measuring and modeling process monitoring and control, developing models to represent microstructure evolution, alloy design, and part suitability, modeling phases of process and machine design, and accelerating product and process qualification and certification. These topics then led to the assessment of short-, immediate-, and long-term challenges in AM. This publication summarizes the presentations and discussions from the workshop"--Publisher's description

Machine 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

This book is a comprehensive guide to the latest developments in data-driven additive manufacturing (AM). From data mining and pre-processing to signal processing, computer vision, and more, the book covers all the essential techniques for preparing AM data. Readers willl explore the key physical and synthetic sources of AM data throughout the life cycle of the process and learn about feature engineering techniques, pipelines, and resulting features, as well as their applications at each life cycle phase. With a focus on featurization efforts from reviewed literature, this book offers tabular summaries for major data sources and analyzes feature spaces at the design, process, and structure phases of AM to uncover trends and insights specific to feature engineering techniques. Finally, the book discusses current challenges and future directions, including AI/ML/DL readiness of AM data. Whether you're an expert or newcomer to the field, this book provides a broader summary of the status and future of data-driven AM technology.

Additive manufacturing (AM) is a revolutionary technology that greatly improves the flexibility of fabricating parts with complex structures and eliminates the cost of making molds. While AM techniques offer unique benefits over traditional manufacturing processes, it is challenging to predict the mechanical behaviors of additively manufactured parts based on design and process parameters. With recent advances in machine learning, data-driven methods have the potential to overcome such limitations. In this work, data-driven modeling frameworks were proposed to predict the tensile, flexural, and compressive behaviors of additively manufactured plastics and composites. Ensemble learning was used to predict the tensile strength of polylactic acid (PLA) with cooperative AM process parameters. A 12.97% mean absolute percentage error (MAPE) was achieved by combining lasso, support vector regression, and extreme gradient boosting in the computational framework. An enhanced ensemble learning method that combines eight different machine learning algorithms was introduced to predict the flexural strength of continuous carbon fiber and short carbon fiber reinforced nylon (CCF-SCFRN) composites with design parameters. Learned knowledge from CCF-SCFRN composites was transferred to continuous glass fiber and short carbon fiber reinforced nylon (CGF-SCFRN) composites for flexural stress-strain curve prediction using an optimal transport (OT) integrated transfer learning framework. Compared with traditional transfer learning, the OT-integrated framework improves the stress-strain curve prediction accuracy by 10.46% in terms of MAPE. The transfer learning framework was further demonstrated in predicting the compressive stress-strain curves of PLA scaffolds with both AM process and design parameters. Three cases were studied by selecting different parameters for domain transfer to validate the generalizability of the proposed framework in predicting mechanical behaviors of additively manufactured materials with limited data.

In the manufacturing environment, high volume of data can be easily generated. However, to provide valuable insight, the right tools, medium, and communication flow within stakeholders are crucial. This thesis presents a comprehensive exploration of developing data products in the manufacturing sector. It includes modeling industrial coffee roaster systems, improving the interpretability of machine learning models, and analyzing stakeholder flow to develop effective manufacturing data products. The first study involves modeling an industrial coffee roaster system. Using production data collected during the roasting process and multiple experiments, an 11-stacked long short-term memory (LSTM) neural network was developed and trained to model the dynamics of the industrial coffee roaster plant. The model was validated, and an initial closed-loop system was developed in MATLAB to further validate the model. The second study focused on improving the interpretability of machine learning models in the Semiconductor Fab. The SHapley Additive exPlanations (SHAP) methodology was applied to generate beeswarm and bar plots for the SHAP results, which identified the most important features to improve the throughput prediction. The study showed that Machine E utilization has a significant influence on the throughput prediction. Finally, the third study involved conducting a qualitative analysis of stakeholder flow in developing data products for manufacturing cases using interview methods and design structure matrix (DSM). The study found that the stakeholder flow varied based on the resources and stage of an organization, with the interaction with end-users being the main driver of the flow. The study also highlighted the importance of identifying and managing stakeholders with the highest coupled interaction for the development of data products.

Within the last decade, several industrialized countries have stressed the importance of advanced manufacturing to their economies. Many of these plans have highlighted the development of additive manufacturing techniques, such as 3D printing which, as of 2018, are still in their infancy. The objective is to develop superior products, produced at lower overall operational costs. For these goals to be realized, a deep understanding of the essential ingredients comprising the materials involved in additive manufacturing is needed. The combination of rigorous material modeling theories, coupled with the dramatic increase of computational power can potentially play a significant role in the analysis, control, and design of many emerging additive manufacturing processes. Specialized materials and the precise design of their properties are key factors in the processes. Specifically, particle-functionalized materials play a central role in this field, in three main regimes: (1) to enhance overall filament-based material properties, by embedding particles within a binder, which is then passed through a heating element and the deposited onto a surface, (2) to “functionalize” inks by adding particles to freely flowing solvents forming a mixture, which is then deposited onto a surface and (3) to directly deposit particles, as dry powders, onto surfaces and then to heat them with a laser, e-beam or other external source, in order to fuse them into place. The goal of these processes is primarily to build surface structures which are extremely difficult to construct using classical manufacturing methods. The objective of this monograph is introduce the readers to basic techniques which can allow them to rapidly develop and analyze particulate-based materials needed in such additive manufacturing processes. This monograph is broken into two main parts: “Continuum Method” (CM) approaches and “Discrete Element Method” (DEM) approaches. The materials associated with methods (1) and (2) are closely related types of continua (particles embedded in a continuous binder) and are treated using continuum approaches. The materials in method (3), which are of a discrete particulate character, are analyzed using discrete element methods.

This book introduces the approach of Machine Learning (ML) based predictive models in the design of composite materials to achieve the required properties for certain applications. ML can learn from existing experimental data obtained from very limited number of experiments and subsequently can be trained to find solutions of the complex non-linear, multi-dimensional functional relationships without any prior assumptions about their nature. In this case the ML models can learn from existing experimental data obtained from (1) composite design based on various properties of the matrix material and fillers/reinforcements (2) material processing during fabrication (3) property relationships. Modelling of these relationships using ML methods significantly reduce the experimental work involved in designing new composites, and therefore offer a new avenue for material design and properties. The book caters to students, academics and researchers who are interested in the field of material composite modelling and design.