Final-year engineering internship conducted within the Digital Engineering Division of ASDL, focusing on the integration of emerging digital technologies in aerospace systems engineering. My role encompassed end-to-end design, simulation, and data pipeline development across three core research projects in collaboration with key institutional partners including NASA.

• Design and Deployment of a NASA-Partnered Energy Monitoring Dashboard.

  
  Engineered an interactive web-based dashboard leveraging Python (Dash/Plotly) and SQL to visualize and analyze real-time energy consumption, distribution, and cost metrics across a simulated space-based manufacturing facility :

  • Integrated multiple telemetry data streams using a modular backend architecture, ensuring scalable and secure data processing.

  • Enabled cross-platform operability and deployment through containerization (Docker) and cloud interfacing.

  • Directly contributed to a larger NASA digital twin initiative aiming to enhance sustainability and mission planning for off-Earth manufacturing.

  
  

• Development of an Immersive Lunar Habitat Simulation in NVIDIA Omniverse.

  
  Designed and simulated a virtual lunar habitat using NVIDIA Omniverse, incorporating physical realism, structural modeling, and astronaut-centric human factors :

  • Created parametric 3D models using USD (Universal Scene Description) and integrated physics-based environmental conditions (gravity, temperature, pressure) to simulate in-situ resource utilization and astronaut behavior.

  • Built an interactive VR interface enabling real-time manipulation of habitat parameters (e.g., airlock control, life support system toggles) using Omniverse XR extension and custom Python scripts.

  • Enhanced realism by connecting user inputs to live state changes in Omniverse, supporting procedural interaction scenarios.

  
  

• Predictive Maintenance System for Aerospace Manufacturing Equipment.

  
  Developed and deployed a data processing and analytics pipeline to optimize condition-based monitoring (CBM) of critical aerospace production machinery :

  • Implemented data ingestion modules for high-frequency sensor data (vibration, temperature, current) and applied signal processing (FFT, wavelet transforms) for feature extraction.

  • Used machine learning models (Random Forest, Isolation Forest) to detect anomalies and estimate Remaining Useful Life (RUL).

  • Enabled integration with the existing digital thread architecture to inform maintenance planning and reduce unplanned downtime.

Technical environment: C#, Python, Git, Unreal Engine 5, Nvidia Omniverse, Virtual Machines