An Agent-Based Solution for Printed Part Verification in Additive Manufacturing

Additive manufacturing (3D printing) offers new design freedom and complex geometries for engineered parts; however, verifying whether printed parts meet the intended design remains a unique challenge. In traditional manufacturing, dimensional inspection methods are mature, repeatable, and supported by long-standing standards. In contrast, verification in 3D printing is often manual, inconsistent, and fragmented. To confirm part accuracy, engineers must consider multiple factors simultaneously: design rules (such as GD&T), process-related distortions, material behavior, measurement uncertainty, and an expanding set of process and testing standards. Because these issues involve design engineering, manufacturing process physics, materials science, metrology, and regulatory standards, part verification in 3D printing requires a true multidisciplinary approach and is difficult to execute consistently.

To address this challenge, we present an agent-based system powered by large language models (LLMs) that automates specification-aware part verification. The proposed framework uses an orchestrator to coordinate three specialized agents. The design agent applies retrieval-augmented generation (RAG) to extract nominal dimensions, GD&T specifications, and relevant standards from engineering documents. The metrology agent processes measurement data, such as CMM point clouds. It computes feature dimensions using defined association criteria, such as least-squares (GG) and maximum inscribed (GX). The QA agent compares computed results with tolerance limits and produces a clear pass/fail decision. It also generates traceable and human-readable reports.

We demonstrate the approach using a laser powder bed fusion (LPBF) case study focused on hole diameter verification. The system automatically retrieves the nominal value and tolerance, processes measurement data, and evaluates compliance. Results are compared against a golden dataset with known outcomes. The system achieves consistent and explainable decisions across multiple test cases. It also highlights how different measurement criteria affect verification results.

Overall, the results show that the approach reduces manual effort, improves consistency in applying standards, and delivers explainable and auditable verification decisions.