eduzhai > Applied Sciences > Engineering >

Hardware-irrelevant parallel processing system

  • Save

... pages left unread,continue reading

Document pages: 22 pages

Abstract: Parallel processing technology has been a primary tool for achievinghigh-speed, high-accuracy, and broadband processing for many years acrossmodern information systems and data processing such as optical and radar,synthetic aperture radar imaging, digital beam forming, and digital filteringsystems. However, hardware deviations in a parallel processing system (PPS)severely degrade system performance and pose an urgent challenge. We propose ahardware-irrelevant PPS of which the performance is unaffected by hardwaredeviations. In this system, an embedded convolutional recurrent autoencoder(CRAE), which learns inherent system patterns as well as acquires and removesadverse effects brought by hardware deviations, is adopted. We implement ahardware-irrelevant PPS into a parallel photonic sampling system to accomplisha high-performance analog-to-digital conversion for microwave signals with highfrequency and broad bandwidth. Under one system state, a category of signalswith two different mismatch degrees is utilized to train the CRAE, which canthen compensate for mismatches in various categories of signals with multiplemismatch degrees under random system states. Our approach is extensivelyapplicable to achieving hardware-irrelevant PPSs which are either discrete orintegrated in photonic, electric, and other fields.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×