Statistical and Data-Driven Methods for Additive Manufacturing Qualification: Proceedings of a Workshop (2024)
Chapter: 1 Introduction
1
Introduction
Additive manufacturing (AM), the process in which a three-dimensional (3D) object is built by adding subsequent layers of materials, enables novel material compositions and shapes, often without the need for specialized tooling. The complex design and processing systems that enable AM start with computer models. Because AM processes can be difficult to measure experimentally and empirical models for AM can be expensive to create, advanced mathematical and statistical models can be used to better understand underlying physical mechanisms. 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 of Sciences, Engineering, and Medicine hosted a workshop in 2018 that brought together experts from various communities to discuss the frontiers of data-driven modeling for AM of metals. A concern that was raised during this workshop and in follow-on conversations with the sponsors was the need for improved approaches to enhance dimensional accuracy in AM and post-additive processes as well as dimensional stability in usage. Some of these approaches may include potential innovations in process, control, and materials design, all of which are becoming more data-driven and have the potential to utilize new statistical, computational, and data science methods.
On March 11–13, 2024, the Board on Mathematical Sciences and Analytics of the National Academies held a workshop on Statistical and Data-Driven Methods for Additive Manufacturing sponsored by the
Department of Energy (DOE). Each day of the 3-day workshop approximately aligns with each of the key bullet points from the statement of task (see Box 1-1), as shown in the agenda listed in Appendix A. Day 1 was organized around dimensional accuracy, part quality, and process stability. The themes of day 2 included statistics, data analytics, and artificial intelligence (AI). Day 3 focused on material qualification and part certification, as well as the conclusion of the meeting. The workshop brought together researchers from different AM communities, statisticians, data scientists, and AI/machine learning (ML) experts to examine approaches that enhance dimensional accuracy and dimensional stability; recent advances and future directions in statistics, data analytics, AI, and ML; and the issues associated with a rapid advance of AM material qualification and part certification.
BOX 1-1
Statement of Task
A planning committee appointed by the National Academies of Sciences, Engineering, and Medicine will organize a workshop to examine the following topics:
- Approaches that enhance dimensional accuracy in additive manufacturing and post-additive processes and dimensional stability in usage, including potential innovations in process, control, and materials design.
- Recent advances and future directions in statistics, data analytics, artificial intelligence, and machine learning that have the potential to aid automated procedures for machine calibration and processing parameters along the toolpath correction in additive manufacturing processes.
- Based on the outcome of (1) and (2), what are the issues associated with a rapid advance of additive manufacturing material qualification and part certification?
In addressing these topics, the workshop will:
- Bring together domain researchers from different additive manufacturing communities, statisticians, data scientists, and artificial intelligence/machine learning experts to share ideas, best practices, and opportunities; and
- Identify new research program areas that have the potential to advance additive manufacturing.
One or more rapporteurs who are not members of the committee will be designated to prepare a workshop proceedings.
This Proceedings of a Workshop summarizes the presentations and discussions that occurred over the course of the meeting. The sessions described in this document are presented chronologically and follow the flow outlined in the agenda (see Appendix A). The proceedings is not intended to provide a comprehensive summary of information shared during the workshop. The information summarized here reflects the knowledge and opinions of individual workshop participants. This proceedings should not be seen as a consensus of the workshop participants, the planning committee, or the National Academies.
