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

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 technol-ogies 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 ef-fects. 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 mea-surements in a gamma-radiated environment. The statistical results show a highly significant relation-ship 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.(c) 2022 Korean Nuclear Society, Published by Elsevier Korea LLC. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).

Automated summary

This paper investigates the use of machine learning algorithms on consumer electronic level Field Programmable Gate Arrays (FPGAs) to tackle Total Ionizing Dose (TID) effects in radiation environments. Experimental results show a significant relationship between gamma radiation exposure levels and board measurements, and the One-Class SVM with Radial Basis Function Kernel performs well in anomaly detection.