SBIR-STTR Award

Machine agnostic real-time monitoring and flaw detection for metal additive manufacturing
Award last edited on: 9/9/2023

Sponsored Program
STTR
Awarding Agency
DOD : AF
Total Award Amount
$799,990
Award Phase
2
Solicitation Topic Code
AF21A-TCSO1
Principal Investigator
Shuchi P Khurana

Company Information

Addiguru LLC

4016 Lake Villa Drive
Metairie, LA 70002
   (504) 858-6357
   sk@addiguru.com
   www.addiguru.com

Research Institution

Ohio State University

Phase I

Contract Number: FA8649-21-P-1344
Start Date: 4/19/2021    Completed: 7/19/2021
Phase I year
2021
Phase I Amount
$49,998
Real-time monitoring can save a lot of money and time for DMLS process, which is very important to the Air Force. By our calculations the saving can be as much as $150,000 per machine per year. However, current real-time monitoring solutions either use ve

Phase II

Contract Number: FA8649-22-P-0696
Start Date: 3/11/2022    Completed: 6/12/2023
Phase II year
2022
Phase II Amount
$749,992
Real-time or in situ monitoring can reduce cost and build time for Laser Powderbed Fusion (LPBF) Additive Manufacturing processes, which is important for the Air Force as well as the industry. Estimates indicate savings can be as much as $150,000 per machine per year. However, current real-time monitoring solutions use very expensive sensors and/or require a lot of calibration time to detect defects. The Air Force benefits from an accelerated integration of this technology across its service depots and labs. Moreover, the Air Force and its suppliers use different brands of machines, thus a brand agnostic solution is required. Addiguru’s real-time monitoring solution for additive manufacturing is based on utilizing low-cost, off-the-shelf sensors that can be deployed quickly and inexpensively. In the Phase I STTR, Addiguru’s current solution, using high-resolution optical cameras, was shown to be machine agnostic and rapidly deployable. Addiguru’s solution is agnostic to not only machine brand, but also material, lighting, angle of camera, and type of camera. In this Phase II STTR effort, Addiguru, in teaming with The Ohio State University (OSU), will demonstrate the ability of Addiguru’s solution to detect defects on a variety of different machine types which OSU possesses. Different materials, lighting, and camera angles will be used to prove the robustness of Addiguru’s solution. Addiguru will also collect data on OSU’s LPBF machines and train Addiguru’s artificial intelligence (AI) models to improve flaw detection. The link between anomaly and flaw characterization will be addressed, and a machine control decision-tree will be created to mitigate flaws in situ. The success of this STTR will lead to completion of TRL 7 and the solution will be ready for deployment at REACT’s machines at Tinker AF base and Air Force Research Labs (AFRL).