TY - GEN
T1 - FPGA based fault detection, isolation and healing for integrated vehicle health
AU - Akoglu, Ali
AU - Vohnout, Sonia
AU - Judkins, Justin
PY - 2007
Y1 - 2007
N2 - Advances in VLSI technology have led to fabrication of chips with number of transistors projected to reach 10 billion in the near future. Affordable fault tolerant solutions transparent to applications with minimal hardware overhead in the micro architecture are necessary to mitigate component level errors for emerging system-on-chip (SoC) platforms. Ridgetop Group and the University of Arizona have developed innovative methods and systems for -detection of anomalous conditions- that lead to faults in highly-complex electronic systems. Through built-in self-testing and fault detection, isolation and recovery capabilities we can offer 100% system availability and proactively avoid false or missed alarms, and estimate the remaining useful life of critical electronic components and their associated subsystems. A novel self-healing mechanism for SoC using field programmable gate array (FPGA) technology that localizes and isolates the faulty area and then replaces the functionality through partial configuration of the FPGA is introduced. Prognostic techniques are leveraged to address resource allocation and distribution to enable a more fault-tolerant, time efficient, and robust system. When prognostic detection methods are combined with reconfiguration strategies, system reliability and availability improve, reducing the probability of failure without compromise of either service quality or performance or requiring redundant components on the chip.
AB - Advances in VLSI technology have led to fabrication of chips with number of transistors projected to reach 10 billion in the near future. Affordable fault tolerant solutions transparent to applications with minimal hardware overhead in the micro architecture are necessary to mitigate component level errors for emerging system-on-chip (SoC) platforms. Ridgetop Group and the University of Arizona have developed innovative methods and systems for -detection of anomalous conditions- that lead to faults in highly-complex electronic systems. Through built-in self-testing and fault detection, isolation and recovery capabilities we can offer 100% system availability and proactively avoid false or missed alarms, and estimate the remaining useful life of critical electronic components and their associated subsystems. A novel self-healing mechanism for SoC using field programmable gate array (FPGA) technology that localizes and isolates the faulty area and then replaces the functionality through partial configuration of the FPGA is introduced. Prognostic techniques are leveraged to address resource allocation and distribution to enable a more fault-tolerant, time efficient, and robust system. When prognostic detection methods are combined with reconfiguration strategies, system reliability and availability improve, reducing the probability of failure without compromise of either service quality or performance or requiring redundant components on the chip.
UR - http://www.scopus.com/inward/record.url?scp=58349089466&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=58349089466&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:58349089466
SN - 9781577353478
T3 - AAAI Fall Symposium - Technical Report
SP - 1
EP - 8
BT - Artificial Intelligence for Prognostics - Papers from the AAAI Fall Symposium
T2 - Artificial Intelligence for Prognostics - Papers from the AAAI Fall Symposium
Y2 - 9 November 2007 through 11 November 2007
ER -