Graduate Research Engineer – AI for Power Systems
Labeled and annotated simulated high-voltage transmission line data for automated fault detection using deep learning models. Prepared and validated ground truth datasets derived from voltage/current waveforms, FFT spectra, and symmetrical components for supervised ML pipelines. Fine-tuned and evaluated classifiers to distinguish fault types across diverse grid scenarios and conditions. • Designed and applied labeling for line-to-ground, phase-to-phase, and three-phase fault scenarios. • Utilized PSCAD and RSCAD to generate and process high-fidelity simulation data for model training. • Assisted in dataset partitioning for benchmarking model generalization and accuracy. • Documented all labeling protocols for reproducibility and cross-team collaboration.