The path to industrializing AM is to achieve a truly efficient and reliable process enabling automation and self-regulated autonomous controls in our true end-to-end manufacturing workflows. The key enablers of these transformations are accurate data sets, with a fast and reliable digital thread, combined with real-time applications.
The proposed case study is an end-to-end project executed for one of our product releases, aiming for production stability and quality assurance, showcasing the leverage in the digital framework including building simulation tools and real-time process monitoring tools. Harvesting the power of machine learning, and artificial intelligence.
These developed tools level down the expertise level and human intervention required to keep at bay the intense data-driven controls targeting an agnostic machine manufacturing environment. Each build is monitored in real-time with automatic defect recognition applications, and it automatically notifies the production floor of any potential defect identified.
Each part produced has a unique digital fingerprint with an extensive digital data thread, including the steps of post-processing that produce automatically robust quality assurance documentation enabling a transparent traceability end to end, that complies with the most stringent regulatory process in our industry.
These cases demonstrate the results of years of R&D investment as well as collaborative efforts among industry partners including software providers and equipment manufacturers.
The speakers are:
Juan Carlos Flores, Executive Director - Additive Manufacturing, Baker Hughes
Tommaso Tamarozzi, Product Director Additive Monitoring Inspection and Simulation, Oqton
Tags
- Automation and Handling