Consensus-based evaluation for fault isolation and on-line evolutionary regeneration

    Authors

    K. N. Zhang; R. F. DeMara;C. A. Sharma

    Comments

    Authors: contact us about adding a copy of your work at STARS@ucf.edu

    Keywords

    Computer Science, Artificial Intelligence; Computer Science, Hardware &; Architecture; Computer Science, Theory & Methods

    Abstract

    While the fault repair capability of Evolvable Hardware (EH) approaches have been previously demonstrated, further improvements to fault handling capability can be achieved by exploiting population diversity during a phases of the fault handling process. A new paradigm for online EH regeneration using Genetic Algorithms (GAs) called Consensus Based Evaluation (CBE) is developed where the performance of individuals is assessed based on broad consensus of the population instead of a conventional fitness function. Adoption of CBE enables information contained in the population to not only enrich the evolutionary process, but also support fault detection and isolation. On-line regeneration of functionality is achieved without additional test vectors by using the results of competitions between individuals in the population. Relative fitness measures support adaptation of the fitness evaluation procedure to support graceful degredation even in the presence of unpredictable changes in the operational environment, inputs, or the FPGA application. Application of CBE to FPGA-based multipliers demonstrates 100% isolation of randomily injected stuck-at faults and evolution of a complete regeneration within 135 repair iterations while precluding the propagation of any discrepant output. The throughput of the system is maintained at 85.35% throughout the repair process.

    Journal Title

    Evolvable Systems: From Biology to Hardware

    Volume

    3637

    Publication Date

    1-1-2005

    Document Type

    Article

    Language

    English

    First Page

    12

    Last Page

    24

    WOS Identifier

    WOS:000232222700002

    ISSN

    0302-9743; 3-540-28736-1

    Share

    COinS