Researcher, Data Labeling for Defect Detection in Additive Manufacturing
I developed and applied novel analysis methods for detecting anomalies and defects in in-situ process monitoring data collected from additive manufacturing experiments. My work involved gathering, cleaning, and accurately labeling large volumes of experimental sensor data to support research in defect detection. I evaluated various data cleaning and anomaly identification techniques to ensure high-quality training data for machine learning and digital twin projects. • Labeled photodiode and sensor data linked to images of porous titanium laser builds. • Applied classification and validation strategies for defect identification. • Collaborated on multi-disciplinary Industry 4.0 digital manufacturing and ML/AI research. • Processed and annotated hundreds of experimental trials for algorithm development.