Machine Intelligence to Heal Computers in Space
We have heard many times about critical systems failing in NASA, with their engineers losing touch for some reason or another with the spacecraft. Not only are missions compromised, but the lives of astronauts. Computers and related hardware do not have the accessibility of the engineers to do a “quick fix” while they are in space. According to the University Communications at the University of Arizona, that may change soon through assistant professor of electrical and computer engineering, Ali Akoglu, and his students. Their new project for the future involves working on a hybrid hardware/software system, teaching it to hopefully allow machine intelligence to heal a spacecraft through its computer system .
The program being used is Field Programmable Gate Arrays (FPGA) which builds a self-healing system by combining software and hardware together, producing a flexible system that can be reconfigured at its chip level. The chip level allows some of the hardware functions to be carried out through software through a mimicking process, with the FPGA “firmware” able to emulate different kinds of hardware through. “When we create a test malfunction, we try to recover in two ways,” Akoglu explained. “First, the unit tries to heal itself at the node level by reprogramming the problem circuits.”
The FPGA system has been programmed to carry on several tasks at once, while also being configured to process at a lightening-speed. “So if you’re running a loop, and it is running 10,000 times, you can replicate the loop as a processing element in the FPGA ‘n’ number of times,” Akoglu explained. “That means you have an ‘n’ times speed-up. It’s like creating a huge multicore processor configured for a specific task.”
A Tuscon company by the name of Ridgetop Group is now working with Akoglu, a company considered to be a leading provider of fault-tolerant electronics and electronic prognostic solutions, specializing in diagnosing circuit faults using statistical methods. “This is the next phase of our project,” Akoglu said. “Our objective is to go beyond predicting a fault to using a self-healing system to fix the predicted fault before it occurs.” This could lead to extremely stable computer systems that could operate for long periods without failure, according to the University of Arizona.
This entry was posted on Friday, April 25th, 2008 at 1:28 am and is filed under Public Relations, Technical Concerns. You can follow any responses to this entry through the RSS 2.0 feed. You can leave a response, or trackback from your own site.
