Application of total variation denoising in nuclear power plant signal pre-processing

Abstract

Pre-processing of generated signals from sensors installed in Nuclear Power Plant (NPP) components is a critical step towards enhancing signal characteristics and reliability of extracted data used in diagnosing the operational state of components or systems. Denoising is one of the essential features of the signal pre-processing tools in the instrument control system of a NPP. A number of denoising methods have been applied in filtering out noisy signals from sensors in NPP. This paper presents the study on the applicability of the Total Variation (TV) denoising method in NPP signal preprocessing. The Majorization-Minimization optimization framework was firstly applied to determine the optimization function suitable for the TV denoising model. An iterative algorithm was subsequently derived to solve the TV denoising model. The model was applied to denoise the water level signal of a NPP pressurizer and a simulation signal of loose parts. The results showed that the denoising method used can effectively filter out the noise mixed in the signal by selecting appropriate regularization parameter that enhances the accuracy of signal feature extraction. The results of the study indicate that the TV denoising model is applicable to NPP components.