A New Approach to Identify and Characterize Low-Power Shutdown Initiating Events Using Machine Learning Techniques

Ma, Zhegang; Xu, Fei; Zhang, Sai; Xian, Min

Permalink

https://hdl.handle.net/2142/121838 Copy

Description

Title

A New Approach to Identify and Characterize Low-Power Shutdown Initiating Events Using Machine Learning Techniques

Author(s)

• Ma, Zhegang
• Xu, Fei
• Zhang, Sai
• Xian, Min

Issue Date

2023

Keyword(s)

• Probabilistic risk assessment
• Nuclear operating experience
• Low-power shutdown
• Initiating event analysis
• Machine learning

Abstract

Idaho National Laboratory has provided technical assistance to the U.S. Nuclear Regulatory Commission (NRC) in reliability and risk analysis including the operating experience (OpE) program since the 1980s. The U.S. nuclear OpE program provides input parameters to the NRC Standardized Plant Analysis Risk models and the industry probabilistic risk assessment (PRA) models. While earlier PRA focused on at- power, internal event analysis, the risks from external hazards and during low-power shutdown (LPSD) operations could be significant, and the need to develop LPSD PRA and external hazards PRA is on the rise. One issue in developing LPSD PRA is the reasonable estimation of shutdown initiative event (SDIE) frequencies. Idaho National Laboratory has developed and is maintaining an SDIE database for the NRC. However, this database is based on the review of Licensee Event Reports, which is believed to be only a subset of “actual” shutdown initiating events that occurred in the industry. This paper investigates a new approach to identify and characterize shutdown initiating events from the Institute of Nuclear Power Operations industry database using machine learning techniques. The main process in this approach is to find out the relationship between keywords in event descriptions and the SDIE categories as in the NRC SDIE database. The relationship can then be applied to the Institute of Nuclear Power Operations database and search for SDIEs.

Type of Resource

text

Language

eng

Handle URL

https://hdl.handle.net/2142/121838

Owning Collections