Probabilistic calibration framework for finite element thermal process modeling of metallic additive manufacturing. Application to promote certification/qualification of load critical aerospace flight parts.

Overview

Development stage

In development or acquisitionSource: a) Pre-deployment – The use case is in a development or acquisition status.

High-impact designation

Not high-impactSource: c) Not high-impact

Impact justification

Not reported

Start date

Not reported

Withheld from public reporting

NoSource: a) No

Mission

Topic area

Science

Operational functions

No function tag matched Derived by keyword rules; see methodology

Problem the AI is intended to solve

Application of active learning paradigm to efficiently develop Gaussian Process Regression surrogate where run time for the target finite element thermal process model is significant.  Fully trained surrogate is then used by monte carlo process to develop probabilistic distribution of finite element model calibration variables which result in finite element model predictions that are in line with input empirical measurement distributions.

Expected benefits

In short, this technique enables the robust and efficient calibration of a model simulating the manufacture of metallic parts by additive manufacturing.  This is important because pure simulation of these processes is not possible without calibration due to large uncertainties in fundamental physical and material properties currently available due to the nature of the manufacturing process.  The inherent variation in mechanical properties of parts produced using metallic additive manufacturing result in significant challenges to certification/qualification for flight.  The goal is to alleviate these challenges with better probabilistic quantification of the fundamentals resulting in this inherent variation, thus promoting further adoption of this fledgling manufacturing technique by industry within the aeronautics industry.

System outputs

probabilistic distribution of finite element model calibration variables

Technology

AI classification

Classical / predictive MLSource: Classical/Predictive Machine Learning: Models trained on data to make predictions or classifications based on identified patterns or relatio…

System name(s)

Not reported

Custom-developed code

Not reported

Public source code

Not reported

Sourcing

How it was built

Not reported

Vendor (as reported)

Not reported

Vendors (standardized)

None on the standard list

A vendor is the supplier named by the agency. It does not identify the underlying model or AI technology.

Data and privacy

Involves PII

Not reported

Privacy Impact Assessment

Not reported

Authorization to Operate

Not reported

Demographic features

Not reported

Training and evaluation data

Not reported

Federal Data Catalog

Not reported

Governance

0 of 8 minimum-practice questions answered. A blank answer means the agency reported nothing; it does not mean the practice is absent.

Potential impacts and how they were identified

Not reported