Abnormal Event Classifier for Nuclear Power Plants

The article under consideration is titled “Dynamic bayesian networks based abnormal event classifier for nuclear power plants in case of cybersecurity threats.” It is drawn from a journal called “Progress in Nuclear Energy” and is authored by Pavan Kumar Vaddi together with seven other scholars. The article explains that nuclear power plants are increasingly susceptible to cyber-attacks since their instrumentation and controls are nowadays based on digital systems (Vaddi et al., 2020). Accordingly, cyber-attacks on nuclear power plants have the potential to cause serious problems, more so when they masquerade as safety events (Vaddi et al., 2020). The article, therefore, notes that research is required on this subject to differentiate between cyber-attacks and safety events to allow for the right responses in a timely manner.

While the standard industry practice for troubleshooting safety events has been to observe physical sensor measurements, Vaddi et al. (2020) suggest the use of the Dynamic Bayesian Networks (DBNs) methodology. The approach is justified since it is an appropriate framework for inferring hidden states of a system from variables observed through probabilistic reasoning (Vaddi et al., 2020). Using a DBN-based abnormal event classifier and architecture to implement the classifier, Vaddi et al. (2020) implement the classifier as part of the monitoring system. In the foregoing, they set up an experimental environment with a two-tank system together with a simulator of a nuclear power plant and a programmable logic controller. They then used a set of 27 cyber-attacks and 14 safety events for the experiment. Moreover, six cyber-attacks and two safety events were used to manually finetune the conditional probability tables (CPTs) of 2 timescale DBN. Consequently, results showed a successful identification of the nature of an abnormal event in all 33 cases, while the cyber-attack of fault was noted in 32 cases. It follows that the DBN methodology is applicable and thus requires more research for improvement.

Reference

Vaddi, P. K., Pietrykowski, M. C., Kar, D., Diao, X., Zhao, Y., Mabry, T., Ray, I., & Smidts, C. (2020). Dynamic bayesian networks based abnormal event classifier for nuclear power plants in case of cybersecurity threats. Progress in Nuclear Energy, 128, 103479.

Cite this paper

Select style

Reference

StudyCorgi. (2022, August 20). Abnormal Event Classifier for Nuclear Power Plants. https://studycorgi.com/abnormal-event-classifier-for-nuclear-power-plants/

Work Cited

"Abnormal Event Classifier for Nuclear Power Plants." StudyCorgi, 20 Aug. 2022, studycorgi.com/abnormal-event-classifier-for-nuclear-power-plants/.

* Hyperlink the URL after pasting it to your document

References

StudyCorgi. (2022) 'Abnormal Event Classifier for Nuclear Power Plants'. 20 August.

1. StudyCorgi. "Abnormal Event Classifier for Nuclear Power Plants." August 20, 2022. https://studycorgi.com/abnormal-event-classifier-for-nuclear-power-plants/.


Bibliography


StudyCorgi. "Abnormal Event Classifier for Nuclear Power Plants." August 20, 2022. https://studycorgi.com/abnormal-event-classifier-for-nuclear-power-plants/.

References

StudyCorgi. 2022. "Abnormal Event Classifier for Nuclear Power Plants." August 20, 2022. https://studycorgi.com/abnormal-event-classifier-for-nuclear-power-plants/.

This paper, “Abnormal Event Classifier for Nuclear Power Plants”, was written and voluntary submitted to our free essay database by a straight-A student. Please ensure you properly reference the paper if you're using it to write your assignment.

Before publication, the StudyCorgi editorial team proofread and checked the paper to make sure it meets the highest standards in terms of grammar, punctuation, style, fact accuracy, copyright issues, and inclusive language. Last updated: .

If you are the author of this paper and no longer wish to have it published on StudyCorgi, request the removal. Please use the “Donate your paper” form to submit an essay.