The Air Force Research Lab is betting $ 750,000 on a new system that Albuquerque-based data analysis company RS21 built to extend satellite operations through remote monitoring and response.
The system – dubbed Space Prognostic AI Custodian Ecosystem, or SPAICE – applies artificial intelligence to detect problems before they arise, allowing operators on the ground to intervene before failures to extend the functionality of the satellite, Kameron said. Baumgardner, Chief Technology Officer of RS21.
SPAICE has already shown enough promise for AFRL to skip its normal âPhase Iâ proof of concept seed funding entirely and proceed with a âDirect to Phase IIâ Small Business Innovation Research Grant. This allows RS21 to immediately build and install the new system for real-world testing on a satellite that launched from the International Space Station earlier this year, Baumgardner said.
When fully installed, SPAICE will provide a constant flow of data from the satellite and the space environment in which it operates, including real-time information on everything from component operation to heat levels inside the spacecraft and satellite positioning to current weather conditions in space, fuel tank levels and vehicle battery charge level.
All of this data will automatically combine with detailed information about the spacecraft itself, such as the manufacturing process used to build it, creating a “neural network” for instant monitoring and evaluation.
âSPAICE is based on deep learning AI that mimics the structure of the brain,â Baumgardner told the Journal. âHe’s looking at a set of inputs to understand how they correlate to identify patterns and predict things. In this case, we are looking at the health of the satellite system. “
This can allow satellite operators to spot anomalies and take action to correct them before something goes wrong, Baumgardner said.
SPAICE provides real-time automated monitoring, data flow and analysis, but it allows operators to make final decisions on the actions needed to help them build confidence in the information received.
âWith AI, people who have done everything themselves for years often find it difficult to trust algorithms to do things for them,â Baumgardner said. âSPAICE presents data in a way that adds context for decision making, but it doesn’t actually make decisions for operators. “
RS21 won first place last December in the annual âHyperspace Challengeâ run by AFRL and ABQid business accelerator, run by CNM Ingenuity, which oversees all business activities at Central New Mexico Community College. This has sparked widespread interest in the new AI system from government agencies and commercial satellite manufacturers and operators, said Charles Rath, president and CEO of RS21.
âWe believe our AI-powered platform will be transformational for the industry to improve situational awareness of satellite operations and save money,â Rath told the Journal. âOur phone is ringing off the hook by government entities and satellite producers. â¦ We believe that the SPAICE system could become the standard for AI and machine learning for preventive maintenance throughout the industry.