Temporal Data Mining in Nuclear Site Monitoring and In Situ Decommissioning

Document Type

Book Section

Publication Date

11-10-2020

Publication Title

Nuclear Power Plant Design and Analysis Codes: Development, Validation, and Application

Publisher

Woodhead Publishing

Edition

1

First page number:

553

Last page number:

581

Abstract

Temporal data mining (TDM) is an active and rapidly evolving area in big data science. Is it possible to borrow the concepts and algorithms of TDM and apply them to nuclear site monitoring and in situ decommissioning (ISD) research? Since all the data collected from the nuclear-decommissioning sites are time-specific, age-specific, and development stage–specific, they are ideal for TDM analysis to validate system performance and reveal unknown patterns of material failure, liquid leaking, and radiation field changing. Savannah River National Laboratory has established an ISD Sensor Network Test Bed—a unique, small-scale, and configurable environment—for the assessment of prospective sensors on actual ISD system at minimal cost. This chapter analyzed the baseline data collected by ISD test bed in recent years with the assistant of TDM algorithms/codes to find out frequency episodes in the event stream. The results have confirmed that TDM techniques and corresponding codes are effective tools to validate ISD performance, and the frequent episodes found in the data stream not only showed the daily cycle of the sensor responses but also established the response sequences of different types of sensors, which was verified by the actual experimental setup. Some abnormal patterns may have the potential for prediction of system failures.

Keywords

Temporal data mining; TDM; In-situ decommissioning; ISD sensor network test bed; Frequent episode

Disciplines

Nuclear | Physical Sciences and Mathematics | Physics

Language

English

UNLV article access

Search your library

Share

COinS