Bosch has announced that it has partnered with Astrobotic Technology Inc. to send an experimental sensor platform dubbed SoundSee to the International Space Station (ISS) — in order to detect equipment failure by sound alone.
"Machines, such as motors and pumps, emit noise signatures while they operate," notes Dr. Samarjit Das, principal researcher and SoundSee project lead at the Bosch Research and Technology Center in Pittsburgh. "Our SoundSee AI [artificial intelligence] algorithm uses machine learning to analyse these subtle acoustic clues and determine whether a machine, or even a single component of a machine, needs to be repaired or replaced.”
It's not the company's first attempt at listening in to the operation of machines in order to diagnose potential faults, but it will be the first to enter the Earth's orbit. “Bosch has long been interested in using audio analytics to monitor critical machines and equipment, such as car engines or HVAC systems," says Dr. Joseph Szurley, a Bosch research scientist working on the project. “The ISS will allow us to study how these techniques can extend to even more challenging and unique environments."
To assist with making the platform space-ready, Bosh has enlisted Astrobotic. "Conducting research in space, even when you have an asset like the ISS, is significantly more challenging than testing on the ground," explains Dr. Andrew Horchler, Astrobotic research scientist and director of Future Missions and Technology for the company. "As a space robotics company, we are able to help Bosch prepare for operating in this highly controlled space environment."
SoundSee has been in development since early this year, when funding was approved by the Center for the Advancement of Science in Space (CASIS). The company's latest announcement confirms the creation of engineering units, which are undergoing tests, as well as the addition of former ISS Commander Dr. Colin Foale to the project team. "Since meeting the team at Astrobotic in Pittsburgh for the SoundSee preliminary design review," Dr. Foale claims, "I am convinced that this novel, cutting-edge approach to using machine learning in space will not only have great benefits for troubleshooting ISS problems, but especially throughout industry on Earth."