End-to-End IIoT Integration for LPBF 3D Printing

Role

Engineer Intern

Organisation

A*STAR Advanced Remanufacturing and Technology Centre (ARTC)

Period

Sep 2022 – Apr 2023

Tech Stack

C++, Python, M5Stack FIRE, NI DAQ, InfluxDB, Grafana

Industrial Metal 3D Printer and Data Pipeline

The Challenge

A major hurdle in Industrial Additive Manufacturing is the lack of real-time feedback during the fabrication process. Because complex metal parts take long periods to construct using Laser Powder Bed Fusion (LPBF), hidden flaws or excessive residual stresses can result in unusable parts and wasted machine life.

Phase 1: Hardware Instrumentation

To achieve real-time telemetry, I engineered a custom sensor instrumentation system directly onto a commercial EOS M 290 3D printer.

Phase 2: Edge Computing

With the hardware safely routing data, I integrated an M5Stack FIRE Industrial IoT device using C++ firmware developed in the Platform.io IDE.

Phase 3: The Data Pipeline

Beyond edge alerts, the hardware data needed to be logged for deep process optimization. I built an end-to-end industrial data pipeline that funneled high-frequency sensor data into a time-series database.

https://github.com/ClementToh/Clement-Toh-Engineering-Portfolio/blob/main/project-artc-integration.html

The Impact

The integrated system provided unprecedented visibility into the LPBF process. Through rigorous validation experiments, the telemetry system successfully identified micro-level powder bed surface deviations of just ~50 µm. Furthermore, it reliably verified that chamber oxygen levels were maintained strictly below 0.1% under controlled conditions, ensuring optimal print quality.

Project Resources

Download Project Report (PDF) Download Project Poster (PDF)