Study on Missing Data Filling Algorithm of Nuclear Power Plant Operation Parameters

Abstract

By analyzing the recorded operation data of a nuclear power plant (NPP), its results can serve the fault detection or operation experience feedback. Data missing exists in the recorded operation data. It may lower the data quality and affect the accuracy of the analysis results. In order to improve the data quality, two parts of researches are carried on. Firstly, to locate the missing data accurately the detecting algorithm for missing data of the NPP operation parameters based on wavelet analysis. Different judging basis is proposed for discrete and continuous missing respectively. Then, the filling method based on the hot deck algorithm are studied. As the dynamic properties of the parameters are closely related to the operating state of NPP, the similarity of the operation parameter vectors are formed to express the similarity of the operating states, so as to fulfill the requirements of the hot deck algorithm. To improve the accuracy of the measuring results, taken the differences between the characteristics of the analog parameters and the switch parameters into consideration, the similarity measurements using Mahalanobis distance for the analog parameter vectors and the matching measure for the switch parameter vectors are studied respectively. Finally, the operation data is taken to build the experiment data set for the algorithm verification. The results shows that the designed algorithm performs much better than the mean interpolation method and LSTM.

Analyzing Operation Logs of Nuclear Power Plants for Safety and Efficiency Diagnosis of Real-Time Operations

“…Figure 1: The operating state of NPP at a specific time is represented by a set of analog parameters and switch parameters (Wang et al, 2022). The changes in switch parameters reflect the operator's control decision.…”

“…Operators' lack of understanding of the plant's real-time state and their inaccurate predictions about future plant states are the primary causes of human errors in control room operations (NRC Web, 2011). As shown in Figure 1, the operating state of NPP at a particular time is represented by two types of parameters -1) switch parameter, which reflects the NPP component state (e.g., Valve A, valve B), and 2) analog parameter, which shows the value of process variables captured by sensor measurements (Wang et al, 2022). The analog and switch parameters within a plant have complex physical and functional interactions.…”

“…Recently, Wang et al (2022) proposed a method to fill missing operation data of an NPP by searching the similar system operation states in control histories. In this study, the operation state of NPP is represented by a combination of analog and switch parameters.…”

Research on Imputation Method for Missing Values of Nuclear Power Plants’ Operation Data

“…However, because a nuclear power plant system's data gathering, transmission, and storage equipment operates in harsh environments, breakdowns, and outside interference can result in data quality issues like missing, drifting, and jumping in operation monitoring [1]. Data quality greatly affects the application and value of data, and poor data quality can lead to ineffective utilization of data [2].…”