Sentient Science

Overview

Problem Thousands of military parts are candidates for transition to additive manufacturing, due to obsolescence or excessive lead times. The main obstacle is qualifying the AM process.

Solution DigitalClone physics-based modeling framework predicts the fatigue life performance of metals – and when integrated with AM machines enables layer-by-layer monitoring that can autonomously detect and correct defects to ensure part fatigue life and accelerate qualification.

Field Validation SBIR Phase II (NASA JPL), SBIR Phase II (US Army DEVCOM AvMC), ongoing SBIR Phase II (AFWERX)

Technology Maturity (TRL) TRL 6 (results from Army Ph II: 25% less defects, 60% longer fatigue life vs parts printed in traditional AM process)

Strategic Advantage Fatigue modeling relies on patented component life prediction (CLP) technology

Go-to-Market Access Awarded 5-yr/$9M SBIR Phase III IDIQ (2023) from US Army Futures Command DEVCOM AvMC for DigitalClone enhancements Access to Amazon Migration Acceleration Program (private cost-share up to $10M)

Dual-Use Potential Automotive, Civil Aerospace, Energy, Industrial Equipment

Team Jason Rios (Defense lead, USMA grad, MBA, former Honeywell) Dr Nathan Bolander (CTO, PhD Purdue University) Dr Behrooz Jalalahmadi (Additive Manufacturing VP, PhD Purdue University) Dr Guru Madireddy (Additive Manufacturing Scientist, PhD Univ of Nebraska-Lincoln, formerly at Oak Ridge National Lab)

Competitive Landscape AM machine manufacturers are able to monitor the print process, but no capability to autonomously detect and correct defects to ensure part fatigue life.

Primary User Engineers (qualification) and DoD AM machine operators (printing)

User-Critical Problem Lack of access to qualified AM parts magnifies part availability issues