Lunar Heat Pump: Edge-Compute & Predictive Machin Learning using ACCEPT

We are seeking a student intern to support an investigation centered on the autonomous operations and predictive maintenance of mechanical equipment for future Lunar and Martian habitats, as well as resilient terrestrial smart-building management. The project will employs NASA's likelihood-by-consequences risk assessment framework using NASA's ACCEPT (Adverse Condition and Critical Event Prediction Toolbox) machine learning framework.

The intern will utilize data generated from a physical, hardware-in-the-loop habitat analog testbed located in NASA Ames’ SHARP Lab, which features an inverter-driven Air-to-Water heat pump and advanced industrial edge-controllers.

Role Objective: This specific position will focus on edge-computing architecture and applied machine learning. The intern will develop and deploy Fault Detection and Diagnostics (FDD) algorithms for advanced HVAC systems. Duties include integrating edge-compute environments (e.g., VOLTTRON, Python, GCP) with physical sensors and applying machine learning and transfer learning techniques to high-frequency Electrical Signature Analysis (ESA) datasets to predict mechanical degradation (e.g., compressor wear)

**Eligible Applicants:** Student
**Academic Level:** Undergraduate Sophomore, Undergraduate Junior, Undergraduate Senior, Graduate Master's, Graduate Doctoral, Post Doctoral
**Activity Type:** In-person
**Citizenship:** US Citizen Only
**Type:** Internships