Advanced Informatics and Artificial Intelligence for Additive Manufacturing

Summary

Advancements in additive manufacturing are progressively driven by digital technologies, with advanced sensors and measurements informing increasingly complex modeling and simulation paradigms and playing an important role in part design, production and qualification.  Advanced informatics are providing new opportunities to harness trusted data and information to acquire knowledge and develop actionable assessments in complex AM systems and environments. Burgeoning efforts in artificial intelligence are reducing the cognitive requirements for analyzing and understanding these complexities, however their fidelity in relation to ground truths remains problematic and not well understood.  The Advanced Informatics and Artificial Intelligence for Additive Manufacturing (AI2AM) project aims to develop the methods, models, standards, and best practices to leverage these (and related) technologies to reduce unknowns in AM part fabrication and qualification towards “born qualified” and “first part correct” outcomes.  

The AI2AM project leverages technologies such as machine learning, digital twins, digital threads, and cybersecurity frameworks to promote process assurance and quality assurance during AM part fabrication.  The complex systems addressed in this project extend beyond the design-to-part transformation, allowing for considerations in production, operations management, supply chain agility, and end use scenarios. This holistic approach will support industry, including SMEs and LSIs, in efforts to enhance AM capabilities and fully integrate additive manufacturing technologies in meaningful, beneficial use cases.

Description

Objective
To develop and deploy the metrics, models, and best practices for implementing and adopting advanced informatics (including product definition, digital twins, machine learning and advanced analytics) and artificial intelligence to enhance additive manufacturing design, process planning, and fabrication with the intent of reducing lead times, supporting first-part-correct goals, and exploiting the inherent advantages of additive manufacturing processes.

Technical Idea
The AI2AM project will leverage information sciences to address the four highlighted challenges. Specifically, project lays forth six primary objectives:

1. Reduce trial-and-error through enhanced predictive analytic capabilities for first-part-correct design and manufacture,
2. Reduce overhead adoption costs of a new process configurations by developing best practices, guidance, and case studies for meeting cybersecurity guidelines,
3. Reduce the “Brain-drain” phenomena associated with experienced AM practitioners by testing and validating the application of emerging AI and ML technologies in the design-to-product-transformation,
4. Increase the attractiveness of AM design alternatives by developing methods, models, and best practices to mature nascent AM capabilities to meet the needs of individual sectors (e.g., functionally graded materials for medical applications),
5. Reduce the uncertainties and unknowns associated with the qualification and acceptance of an AM part through the development of advanced, comprehensive digital twins and associated analytics to support the continuous validation of an AM part throughout the design-to-product transformation,
6. Improve the capabilities of AM technologies to provide viable, robust supply chain alternatives through multi-scale digital twins.

Advances in predictive analytics will include addressing the uncertainties associated with increasingly available empirical and physics-based models.  New methods to quantify the fidelity of individual models will facilitate their continued reuse, including model aggregation and composition, amongst AM partners. Establishing baselines and best practices for the adoption of tools founded in ML and AI technologies will provide practitioners with much needed insight into their applicability, utility, and practicality. New methods for incorporating end-use requirements, such fatigue life or loading conditions, will allow for predictive models to assume a greater role in quality assurance.  Such methods can be developed leveraging digital twin technologies.

Digital twins provide the ability to digitally “manifest” a physical part at various stages of the transformation and with high rates of observation.  Accompanied by deliberate, precise analytics, digital twins have the potential to provide previously unachievable quality assurance in a digital manufacturing process.  Advances in querying digital twins, especially with sector-specific considerations, will open new pathways to quality assurance of AM parts. The project will develop the framework for the adoption of digital twins for both process and quality assurance.

Scaling digital twins beyond the part, to the machine, facility, enterprise, and supply chain can provide newfound transparency into AM industrialization scenarios. Methodically incorporated, these multi-scale digital twins can provide uninhibited access to understanding and mapping the integration of AM technologies in the creation of robust, AM-supported supply chains. This transparency can be used to both increase confidence in the technology and expedite adoption and acceptance.  The development of case studies and best practices in this area will alleviate the initial burden on SMM adoption of AM technologies.

Research Plan
Towards the development of improved predictive analytic capabilities, the AI2AM project will: 1) Develop new methods and standards to quantify the fidelity of AM models and simulations through VVUQ and 2) Develop new methods and best practices for leveraging AI and ML tools and building trust into their application.

To develop VVUQ methods, the AI2AM project look to develop a strategy and framework for implementing VVUQ to support predictive analytics in AM. The project will engage relevant efforts in model validation and standards development while initiating new efforts as needed.  

ASME has established a suite of activities to develop VVUQ standards in various domains, including advanced manufacturing and machine learning.  The AI2AM project will explore how current best practices in various domains can be adopted to support VVUQ specifically for AM, including the unique challenges stemming from the many variations of process physics, sensor configurations, and parameter combinations.  The project will leverage the ongoing efforts of the NIST AM Bench competition for the reference data and models to prove out the VVUQ activities, including how to verify and validate the use and re-use of high-dimensional data.

Predictive analytics are increasingly realized through the adoption of ML and AI techniques.  To support the adoption of ML and AI techniques in AM, AI2AM will develop methods, models, and best practices for their application. The project will explore and characterize the behaviors of various approaches such as neural networks and large language models towards the establishment of best practices for developing training data and managing unintended bias. The use of AM-derived ontologies will be explored as a means for introducing and maintaining context when training various models for AM applications, including the development of data-driven design rules.

Towards the development of improved “first part correct” goals, and process and quality assurance for intended applications, the AI2AM project will develop the methods, models, and representations necessary to realize robust digital twins of AM processes and parts.  The project will undertake several fundamental activities towards establishing digital twins for AM:

• Develop methods and models for correlating physical parts, at different stages of maturity, to part specifications, at multiple scales (micro, meso, macro) to facilitate in situ process and part assurance,
• Develop domain and application-specific digital twin models that integrate specific acceptance requirements into the design and process planning,
• Develop the methods and models necessary to create aggregate digital twins, customizable to an AM part and process, and the methods to establish qualification thresholds with these digital twins.

Towards the development of robust AM-enabled supply chains, the AI2AM project will: 1) Define and develop the methods and models necessary for realizing agile, multi-scale digital twins for supply chain integration and 2) Define and develop the methods and best practices for securing supply chain integrity.

Integration of part and system-level digital twins into the larger enterprise requires characterization of AM processes within a production environment, including build times, preparation times, and post processing times.  To inform enterprise-level decision making, these part and system digital twins must be normalized to be interoperable with digital twins of traditional production environments, including defining multi-scale interactions. To support transparency through digital twins, new methods and communication protocols are needed to convey the state of a part at different stages of fabrication.  To support production agility, new system-level digital twins, including machine emulators, are necessary to support machine selection and reconfiguration.

A robust AM-enable supply chain includes building trust into network. General security considerations and recommendations have been developed for advanced manufacturing technologies, but AM has shown to create some unique risks.  Existing guidelines will be adopted and leveraged to inform the development of new guidelines for establishing secure AM-enabled supply chains.  These guidelines will include best practices for applying NIST’s Risk Management Framework, amongst others, to address AM security considerations.  To support the adoption of secure AM practices, the project will explore different AM scenarios where risks are observed and mitigated using best practices.  Findings will be published as internal reports and contributions to AM security standards.

Major Accomplishments 

• Methods for Data packages
• Standard for Product Definition
• Models for advanced simulation and path planning
• Reference models for AM  digital thread and digital twin