Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

Using machine learning for anomaly detection on a system-on-chip under gamma radiation

  • Eduardo Weber Wachter (School of Computer Science and Electronic Engineering, University of Essex) ;
  • Server Kasap (School of Computing, Electronics and Mathematics, Coventry University) ;
  • Sefki Kolozali (School of Computer Science and Electronic Engineering, University of Essex) ;
  • Xiaojun Zhai (School of Computer Science and Electronic Engineering, University of Essex) ;
  • Shoaib Ehsan (School of Computer Science and Electronic Engineering, University of Essex) ;
  • Klaus D. McDonald-Maier (School of Computer Science and Electronic Engineering, University of Essex)
  • Received : 2022.03.22
  • Accepted : 2022.06.26
  • Published : 2022.11.25
Download PDF
⟨ Previous Next ⟩

Abstract

The emergence of new nanoscale technologies has imposed significant challenges to designing reliable electronic systems in radiation environments. A few types of radiation like Total Ionizing Dose (TID) can cause permanent damages on such nanoscale electronic devices, and current state-of-the-art technologies to tackle TID make use of expensive radiation-hardened devices. This paper focuses on a novel and different approach: using machine learning algorithms on consumer electronic level Field Programmable Gate Arrays (FPGAs) to tackle TID effects and monitor them to replace before they stop working. This condition has a research challenge to anticipate when the board results in a total failure due to TID effects. We observed internal measurements of FPGA boards under gamma radiation and used three different anomaly detection machine learning (ML) algorithms to detect anomalies in the sensor measurements in a gamma-radiated environment. The statistical results show a highly significant relationship between the gamma radiation exposure levels and the board measurements. Moreover, our anomaly detection results have shown that a One-Class SVM with Radial Basis Function Kernel has an average recall score of 0.95. Also, all anomalies can be detected before the boards are entirely inoperative, i.e. voltages drop to zero and confirmed with a sanity check.

Keywords

Acknowledgement

We acknowledge the support of The University of Manchester's Dalton Cumbrian Facility (DCF), a partner in the National Nuclear User Facility, the EPSRC UK National Ion Beam Centre and the Henry Royce Institute. We recognise Kevin Warren for their assistance during the experiments.

References

  1. Nuclear Provision: explaining the cost of cleaning up Britain's nuclear legacy. https://www.gov.uk/government/. 
  2. O. Goncalves, G. Prenat, B. Dieny, Radiation hardened mram-based fpga, IEEE Transactions on Magnetics 49 (7) (2013) 4355-4358.  https://doi.org/10.1109/TMAG.2013.2247744
  3. S. Ramaswamy, L. Rockett, D. Patel, S. Danziger, R. Manohar, C.W. Kelly, J.L. Holt, V. Ekanayake, D. Elftmann, A radiation hardened reconfigurable fpga, in: 2009 IEEE Aerospace Conference, 2009, pp. 1-10. 
  4. A. Lindoso, L. Entrena, M. Garcia-Valderas, L. Parra, A hybrid fault-tolerant LEON3 soft core processor implemented in low-end SRAM FPGA, IEEE Transactions on Nuclear Science 64 (1) (Jan 2017) 374-381.  https://doi.org/10.1109/TNS.2016.2636574
  5. H. Quinn, W.H. Robinson, P. Rech, M. Aguirre, A. Barnard, M. Desogus, L. Entrena, M. Garcia-Valderas, S.M. Guertin, D. Kaeli, F.L. Kastensmidt, B.T. Kiddie, A. Sanchez-Clemente, M.S. Reorda, L. Sterpone, M. Wirthlin, Using benchmarks for radiation testing of microprocessors and FPGAs, IEEE Transactions on Nuclear Science 62 (6) (2015) 2547-2554.  https://doi.org/10.1109/TNS.2015.2498313
  6. S.M. Trimberger, Three ages of fpgas: a retrospective on the first thirty years of fpga technology, Proceedings of the IEEE 103 (3) (2015) 318-331.  https://doi.org/10.1109/JPROC.2015.2392104
  7. Tomas Fried, Antonio Di Buono, David Cheneler, Neil Cockbain, Jonathan M. Dodds, Peter R. Green, Lennox Barry, C. James Taylor, Stephen D. Monk, Radiation testing of low cost, commercial off the shelf microcontroller board, Nuclear Engineering and Technology 53 (10) (2021) 3335-3343.  https://doi.org/10.1016/j.net.2021.05.005
  8. Andrew West, Jordan Knapp, Lennox Barry, Steve Walters, Stephen Watts, Radiation Tolerance of a Small Cots Single Board Computer for Mobile Robots, Nuclear Engineering and Technology, 2021. 
  9. Joerg Leukel, Julian Gonzalez, Martin Riekert, Adoption of machine learning technology for failure prediction in industrial maintenance: a systematic review, Journal of Manufacturing Systems 61 (2021) 87-96.  https://doi.org/10.1016/j.jmsy.2021.08.012
  10. S. Kasap, E. Weber Wachter, X. Zhai, S. Ehsan, K. Mcdonald-Maier, Survey of soft error mitigation techniques applied to LEON3 soft processors on SRAM-based FPGAs, IEEE Access 8 (2020) 28646-28658.  https://doi.org/10.1109/ACCESS.2020.2969714
  11. Yufan Lu, Xiaojun Zhai, Sangeet Saha, Shoaib Ehsan, D. Klaus, McDonald-Maier, A self-adaptive seu mitigation scheme for embedded systems in extreme radiation environments, IEEE Systems Journal (2022) 1-12. 
  12. Carl Carmichael, Triple Module Redundancy Design Techniques for Virtex FPGAs, Xilinx Inc., San Jose, CA, USA, XAPP197 Application Note, 2006. 
  13. D.K. Pradhan, N.H. Vaidya, Roll-forward and rollback recovery: performance-reliability trade-off, IEEE Transactions on Computers 46 (3) (March 1997) 372-378.  https://doi.org/10.1109/12.580435
  14. L. Parra, A. Lindoso, M. Portela-Garcia, L. Entrena, B. Du, M.S. Reorda, L. Sterpone, A new hybrid nonintrusive error-detection technique using dual control-flow monitoring, IEEE Transactions on Nuclear Science 61 (6) (Dec 2014) 3236-3243.  https://doi.org/10.1109/TNS.2014.2361953
  15. H. Quinn, Z. Baker, T. Fairbanks, J.L. Tripp, G. Duran, Robust duplication with comparison methods in microcontrollers, IEEE Transactions on Nuclear Science 64 (1) (Jan 2017) 338-345.  https://doi.org/10.1109/TNS.2016.2634781
  16. Kuang-Hua Huang, J.A. Abraham, Algorithm-based fault tolerance for matrix operations, IEEE Transactions on Computers, C- 33 (6) (June 1984) 518-528.  https://doi.org/10.1109/TC.1984.1676475
  17. J.R. Azambuja, M. Altieri, J. Becker, F.L. Kastensmidt, HETA: hybrid error-detection technique using assertions, IEEE Transactions on Nuclear Science 60 (4) (Aug 2013) 2805-2812.  https://doi.org/10.1109/TNS.2013.2246798
  18. E. Chielle, G.S. Rodrigues, F.L. Kastensmidt, S. Cuenca-Asensi, L.A. Tambara, P. Rech, H. Quinn, S-SETA: selective software-only error-detection technique using assertions, IEEE Transactions on Nuclear Science 62 (6) (Dec 2015) 3088-3095.  https://doi.org/10.1109/TNS.2015.2484842
  19. Harn Hua Ng, PPC405 Lockstep System on ML310, Xilinx Inc., San Jose, CA, USA, XAPP564 Application Note, 2007. 
  20. F. Abate, L. Sterpone, C.A. Lisboa, L. Carro, M. Violante, New techniques for improving the performance of the lockstep architecture for SEEs mitigation in FPGA embedded processors, IEEE Transactions on Nuclear Science 56 (4) (Aug 2009) 1992-2000.  https://doi.org/10.1109/TNS.2009.2013237
  21. M. Violante, C. Meinhardt, R. Reis, M. Sonza Reorda, A low-cost solution for deploying processor cores in harsh environments, IEEE Transactions on Industrial Electronics 58 (7) (July 2011) 2617-2626.  https://doi.org/10.1109/TIE.2011.2134054
  22. H. Pham, S. Pillement, S.J. Piestrak, Low-overhead fault-tolerance technique for a dynamically reconfigurable softcore processor, IEEE Transactions on Computers 62 (6) (June 2013) 1179-1192.  https://doi.org/10.1109/TC.2012.55
  23. A.B. de Oliveira, G.S. Rodrigues, F.L. Kastensmidt, N. Added, E.L.A. Macchione, V.A.P. Aguiar, N.H. Medina, M.A.G. Silveira, Lockstep dual-core ARM A9: implementation and resilience analysis under heavy ion-induced soft errors, IEEE Transactions on Nuclear Science 65 (8) (Aug 2018) 1783-1790.  https://doi.org/10.1109/TNS.2018.2852606
  24. E.W. Wachter, S. Kasap, X. Zhai, S. Ehsan, K. McDonald-Maier, Survey of € lockstep based mitigation techniques for soft errors in embedded systems, in: Computer Science and Electronic Engineering Conference (CEEC 2019), 2019, pp. 124-127. 
  25. N. Rezzak, J. Wang, M. Traas, A. Zerrouki, G. Bakker, F. Xue, A. Cai, F. Hawley, J. McCollum, E. Hamdy, Investigation of tid and dynamic burn-in-induced vT shift on rtg4 flash-based fpga, IEEE Transactions on Nuclear Science 65 (1) (2018) 64-70.  https://doi.org/10.1109/TNS.2017.2768038
  26. P. Villa, E. Bezerra, R. Goerl, L. Poehls, F. Vargas, N. Medina, N. Added, V. de Aguiar, E. Macchione, F. Aguirre, M. da Silveira, Analysis of cots fpga seu-sensitivity to combined effects of conducted-emi and tid, in: 2017 11th International Workshop on the Electromagnetic Compatibility of Integrated Circuits (EMCCompo), 2017, pp. 27-32. 
  27. J. Tarrillo, J.R. Azambuja, F.L. Kastensmidt, E.C.P. Fonseca, R. Galhardo, O. Goncalez, Analyzing the effects of tid in an embedded system running in a flash-based fpga, IEEE Transactions on Nuclear Science 58 (6) (2011) 2855-2862.  https://doi.org/10.1109/TNS.2011.2170855
  28. G. Lentaris, K. Maragos, D. Soudris, F. Di Capua, L. Campajola, M. Campajola, A. Costantino, G. Furano, A. Tavoularis, L. Santos, Tid evaluation system with on-chip electron source and programmable sensing mechanisms on fpga, IEEE Transactions on Nuclear Science 66 (1) (2019) 312-319.  https://doi.org/10.1109/TNS.2018.2885713
  29. Minized board product brief. http://zedboard.org/. 
  30. Zynq-7000 SoC data sheet. https://www.xilinx.com/. 
  31. DA9062 data sheet. https://www.dialog-semiconductor.com/. 
  32. MiniZed power architecture. zedboard.org. 
  33. Elegoo R3 board. https://www.elegoo.com/. 
  34. ATmega data sheet. http://ww1.microchip.com/. 
  35. PmodTC1 board reference manual. https://reference.digilentinc.com/. 
  36. J. Cohen, Statistical Power Analysis for the Behavioral Sciences, second ed., Lawrence Erlbaum Associates., Hillsdale, NJ, 1977. 
  37. Ben Hoyle, Markus Michael Rau, Kerstin Paech, Christopher Bonnett, Stella Seitz, Jochen Weller, Anomaly detection for machine learning redshifts applied to SDSS galaxies, Monthly Notices of the Royal Astronomical Society 452 (4) (2015) 4183-4194.  https://doi.org/10.1093/mnras/stv1551
  38. Malak Alshawabkeh, Byunghyun Jang, David Kaeli, Accelerating the local outlier factor Algorithm on a GPU for intrusion detection systems, in: Proceedings of the 3rd Workshop on General-Purpose Computation on Graphics Processing Units, Association for Computing Machinery, New York, NY, USA, 2010. GPGPU-3, page 104-110. 
  39. Katherine A. Heller, Krysta Marie Svore, Angelos D. Keromytis, salvatore J. Stolfo, One class support vector machines for detecting anomalous windows registry accesses, in: Proceedings of the ICDM Workshop on Data Mining for Computer Security, 2003. 
  40. David S. Broomhead, David Lowe, Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks, Royal Signals and Radar Establishment Malvern, United Kingdom), 1988. Technical report. 
  41. D.M.W. Powers, Evaluation: From precision, recall and f-measure toroc, informedness, markedness and correlation, Journal of Machine Learning Technologies 2 (1) (2011) 37-63. 
  42. Dalton Cumbrian facility. https://www.dalton.manchester.ac.uk/research/facilities/cumbria-facilities/. 
  43. Zeba Khanam, Bilal Aslam, Sangeet Saha, Xiaojun Zhai, Shoaib Ehsan, Rustam Stolkin, Klaus McDonald-Maier, Gamma-induced image degradation analysis of robot vision sensor for autonomous inspection of nuclear sites, IEEE Sensors Journal (2021), https://doi.org/10.1109/JSEN.2021.3050168. In press.