Improved PCA method for sensor fault detection and isolation in a nuclear power plant

Li, Wei; Peng, Minjun; Wang, Qingzhong

doi:10.1016/j.net.2018.08.020

Cited by 54 publications

(26 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Currently, the most popular methods in FDD are ANNs as FDD itself can be seen as a classification problem where we need to recognize the type of fault or transients and check for the operating status of devices. This trial starts with the simplest ANN where bare backpropagation networks are trained on few transients or plant conditions for status diagnosis [39], [129] while with time going on, the network becomes more complex and more intelligent, which of course would lead to better results and performance, with the aid of optimization methods such as PCA (Principal Component Analysis) [130], [131] and genetic algorithms [132], [133] and more complex network architecture like recurrent neural network (RNN) [134]- [137], CNN [138], [139].…”

Section: ) Fault Detection and Diagnosismentioning

confidence: 99%

Nuclear Power Plants With Artificial Intelligence in Industry 4.0 Era: Top-Level Design and Current Applications—A Systemic Review

Lyu

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Nuclear energy can make an important contribution to low-carbon energy supply for Industry 4.0, while Industry 4.0 can reform this industry in return. As a typical and complex man-machine-network integration system, various faults, insufficient automation and stressed human operators limit the further popularization of nuclear power plants (NPPs) while these issues can be addressed by the aid of artificial intelligence (AI) technologies. In this work, we try to present a systemic review of how AI can benefit NPPs in a top-to-down fashion. We discuss limitations in current NPPs and introduce the concept of Nuclear Power Plant Human-Cyber-Physical System (NPPHCPS) as the top-level design. Then, we category AI-related nuclear power applications into Physical-Plant-Centered and Human-Operator-Centered technologies and review research works from 7 typical NPP functional scenarios in the recent two decades. In each NPP functional scenario, how researchers integrate AI into NPPs is presented following timeline. We hope this review can be used as the guideline for NPPs' Design in the future and contribute to green Industry 4.0.

show abstract

Section: ) Fault Detection and Diagnosismentioning

confidence: 99%

Nuclear Power Plants With Artificial Intelligence in Industry 4.0 Era: Top-Level Design and Current Applications—A Systemic Review

Lyu

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Principal component analysis (PCA), which is a data-based method, is used in [12] to detect fixed and drifting biases of temperature and pressure sensors in a refrigeration and air conditioning (R&AC) system. PCA can transform correlated variables into new sets of variables that are uncorrelated and retains the key information of the original data set [13]. Nevertheless, one assumption of using PCA is that variables should obey Gaussian distribution.…”

Section: Introductionmentioning

confidence: 99%

Sensor Drift Detection Based on Discrete Wavelet Transform and Grey Models

Han

Jiang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

“…PCA is a way of identifying patterns in data to find out the similarities or differences in the data to be used [2]. The PCA method has been widely used in various fields ([3], [4], [5], [6], [7]).…”

Section: Introductionmentioning

confidence: 99%

Using Principal Component Analysis for Factor Analysis in Indonesian Automotive Industries

Hamida

2020

IJID

View full text Add to dashboard Cite

Policies related to the automotive industry have become significant for the Ministry of Industry. The problem in determining these policies is the determination of important factors for the automotive industry so that the policies formulated are right on target. The search for these important factors can be done by using the factor analysis method. So far, no studies have been conducted to examine the factors that influence the growth of the automotive industry. In this study, factor analysis is performed on factors in the automotive industry using the principal component analysis algorithm. The algorithm seeks to describe independently the aspects that become the main factors in determining the automotive industry. Based on an analysis of factors in the automotive industry production, the most influential factors are foreign investment, vehicle ownership ratios, and at last the change in GDP.

show abstract

Improved PCA method for sensor fault detection and isolation in a nuclear power plant

Cited by 54 publications

References 16 publications

Nuclear Power Plants With Artificial Intelligence in Industry 4.0 Era: Top-Level Design and Current Applications—A Systemic Review

Nuclear Power Plants With Artificial Intelligence in Industry 4.0 Era: Top-Level Design and Current Applications—A Systemic Review

Sensor Drift Detection Based on Discrete Wavelet Transform and Grey Models

Using Principal Component Analysis for Factor Analysis in Indonesian Automotive Industries

Contact Info

Product

Resources

About