Description: In Phase II we demonstrated our system on a NASA cubesat flight (at time of writing launch scheduled for January 12th, 2022). This will show the utility of our system in finding anomalies onboard a satellite while monitoring live telemetry streams. As part of this work we developed an approach to modelling multichannel time series data that is optimized for low power implementation but also flexible enough to be implemented on different hardware platforms. The highest performance was demonstrated on Research and Development hardware, not currently viable commercially. Therefore, we request additional scope for Phase II-E to extend the Phase II work into a system that both uses commercially viable neural-inspired hardware and is power efficient enough for our entry market aerospace applications.

Benefits: The prototype developed in Phase II-E can potentially be used by NASA for anomaly detection onboard the ISS, the planned Lunar Gateway, and future missions to Mars. The NSFM software can also be used by ground crews to augment their ability to monitor spacecraft telemetry once it reaches the ground. Importantly, if used throughout the entire lifecycle from integration and test through operations, the expertise of the ground crews, the full test and verification cycle, and commissioning, onboard with the astronauts as they move into deep space.

The prototype developed in Phase II-E can potentially be used for anomaly detection onboard any of the new large constellations planned by private companies. It can also be applied to crewed space missions, deep space probes, UUVs, UAVs, and many industrial applications on Earth. The NSFM prototype developed in Phase II-E can also be used during Integration and Test of any commercial satellite.