Discover, Connect & Collaborate at TECHINNOVATION 2021
Intelligent Quality Control for Metal 3D Printing
This proprietary technology, intelligent quality control system (IQCS), provides a holistic approach for the inspection of metal 3D printing process with the following features:
- Real-time detection & classification of defects using machine learning (ML)
- Quality prediction for additive manufactured parts using ML (algorithm validated experimentally)
- Prediction of new design printability and avoidance of printing issues in future prints
- Cloud-based distributed manufacturing network
- Stand-alone system and can be used for wide range of machines and technologies
The IQCS has attracted active feedbacks and supports from both standardization bodies and industrial companies including:
- Standardization bodies: American Society for Testing and Materials (ASTM), DNV-GL, National Institute of Standards and Technology (NIST)
- End users: Sembcorp
- Design software company: Autodesk
- National Additive Manufacturing – Innovation Cluster (NAMIC)
The technology owner is currently working with ASTM, an international standards organization, to develop industrial standards in association with data acquired by the IQCS. A working group comprising of DNV-GL, NIST, Sembcorp and Autodesk has been formed by ASTM to actively support the use of IQCS for standard development in 3D printing.
This technology aims to creating intelligent service-oriented production for the additive manufacturing industry as demonstrated in the representative image. It is an essential step towards fully automated, autonomous factories of the future.
Technology Features, Specifications and Advantages
The IQCS provides real-time insights to the print quality of the part as the job progresses. The method entails the intelligent use of an optical sensor and an infrared (IR) sensor to acquire thermal and visual information of the part being fabricated. Through deep learning and data analysis of the thermal map and optical images, surface anomalies and defect signatures (e.g. elevated areas, low energy input, or overheated regions) of the part being fabricated can be early identified for remedial actions. The technology owner provides installation and calibration of the intelligent monitoring system, as well as a licensable software for quality management of the 3D printed products.
The Global Additive Manufacturing market, including hardware software, materials and services, stands at $9.3 billion in 2018, and is projected to reach $41.6 billion in 2027. Printing large components like propellers can take days or even weeks to complete. If anomalies occur during the printing process affecting part quality, the whole part may have to be discarded. According to published cost models, the risk related cost due to build failure is the second largest cost, occupying 26% of the total unit cost. This highlights that process instability can severely affect the overall value proposition of AM. This technology thus has the potential to minimize risk-related costs and significantly reduce the production costs of the PBF process.
- Cost and time saving due to early detection of defects
- Alert on print job failure and powder batch quality
- Assurance of quality and consistency of 3D printed parts
- Timely maintenance of printers from early warnings of damaged or defective components