What is it about?
Sensor failures have a significant impact on the health monitoring of space habitats. To address this challenge, we have developed an unsupervised learning approach utilizing convolutional autoencoders (CAEs) to detect sensor faults in extraterrestrial habitats. We have systematically compared the performance of CAEs with existing methods, including auto-associative neural networks (AANNs) and variational autoencoders (VAEs), using a habitat simulator.
Featured Image
Photo by NASA on Unsplash
Read the Original
This page is a summary of: Sensor Fault Detection in Smart Extraterrestrial Habitats Using Unsupervised Learning, AIAA Journal, September 2024, American Institute of Aeronautics and Astronautics (AIAA),
DOI: 10.2514/1.j063815.
You can read the full text:
Contributors
The following have contributed to this page