TY - JOUR
T1 - A comparative study on deep learning models for condition monitoring of advanced reactor piping systems
AU - Sandhu, Harleen Kaur
AU - Bodda, Saran Srikanth
AU - Yan, Erin
AU - Sabharwall, Piyush
AU - Gupta, Abhinav
N1 - Funding Information:
This research was supported by US Department of Energy (DOE) - Advanced Research Projects Agency - Energy (ARPA-E), United States under the grant DE-AR0000976 . In addition, this research was partially supported by Center for Nuclear Energy Facilities and Structures at North Carolina State University, United States . Resources for the Center come from the dues paid by member organizations and from the Civil, Construction, and Environmental Engineering Department and College of Engineering at the University. Due to funding agreements and related constraints, the code is not publicly available but can be viewed upon signing a non-disclosure agreement.
Funding Information:
This research was supported by US Department of Energy (DOE) - Advanced Research Projects Agency - Energy (ARPA-E), United States under the grant DE-AR0000976. In addition, this research was partially supported by Center for Nuclear Energy Facilities and Structures at North Carolina State University, United States. Resources for the Center come from the dues paid by member organizations and from the Civil, Construction, and Environmental Engineering Department and College of Engineering at the University. Due to funding agreements and related constraints, the code is not publicly available but can be viewed upon signing a non-disclosure agreement.
Publisher Copyright:
© 2023 Elsevier Ltd
PY - 2024/3/1
Y1 - 2024/3/1
N2 - Advanced nuclear reactors offer innovative applications due to their portability, reliability, resiliency, and high capacity factors. To operate them on a wider scale, reducing maintenance life-cycle costs while ensuring their integrity is essential. Autonomous operations in advanced nuclear reactors using augmented Digital Twin (DT) technology can serve as a cost-effective solution by increasing awareness about the system's health. A key component of nuclear DT frameworks is the condition monitoring of safety systems, such as piping-equipment systems, which involves acquiring and monitoring the plant's sensor data. This research proposes a condition monitoring methodology utilizing deep learning algorithms, such as multilayer perceptions (MLP) and convolutional neural networks (CNNs), to detect degradation and its severity in nuclear piping-equipment systems. Sensor signals are processed to obtain the power spectral density and the Short-Time Fourier transform, and feature extraction methodologies are proposed to develop degradation-sensitive data repositories. The performance of MLP, one-dimensional (1D) CNN, and 2D CNN within the proposed condition monitoring framework is compared using a finite element model of a 3D piping system subjected to seismic loads as the application case study. Various approaches, such as dropout, k-Fold validation, regularization, and early stopping of training the network, are investigated to avoid overfitting the models to the input sensor data. The predictive capability and computational capacity of the deep learning algorithms are also compared to detect degradation in the Z-pipe system of the Experimental Breeder Reactor II (EBRII). The Z-pipe system is subjected to harmonic excitations that represent normal operating loads, such as pump-induced vibrations. The findings of the study indicate that the proposed artificial intelligence (AI)-driven condition monitoring framework demonstrates superior prediction accuracies with a 2D CNN, whereas the MLP exhibits higher computational efficiency.
AB - Advanced nuclear reactors offer innovative applications due to their portability, reliability, resiliency, and high capacity factors. To operate them on a wider scale, reducing maintenance life-cycle costs while ensuring their integrity is essential. Autonomous operations in advanced nuclear reactors using augmented Digital Twin (DT) technology can serve as a cost-effective solution by increasing awareness about the system's health. A key component of nuclear DT frameworks is the condition monitoring of safety systems, such as piping-equipment systems, which involves acquiring and monitoring the plant's sensor data. This research proposes a condition monitoring methodology utilizing deep learning algorithms, such as multilayer perceptions (MLP) and convolutional neural networks (CNNs), to detect degradation and its severity in nuclear piping-equipment systems. Sensor signals are processed to obtain the power spectral density and the Short-Time Fourier transform, and feature extraction methodologies are proposed to develop degradation-sensitive data repositories. The performance of MLP, one-dimensional (1D) CNN, and 2D CNN within the proposed condition monitoring framework is compared using a finite element model of a 3D piping system subjected to seismic loads as the application case study. Various approaches, such as dropout, k-Fold validation, regularization, and early stopping of training the network, are investigated to avoid overfitting the models to the input sensor data. The predictive capability and computational capacity of the deep learning algorithms are also compared to detect degradation in the Z-pipe system of the Experimental Breeder Reactor II (EBRII). The Z-pipe system is subjected to harmonic excitations that represent normal operating loads, such as pump-induced vibrations. The findings of the study indicate that the proposed artificial intelligence (AI)-driven condition monitoring framework demonstrates superior prediction accuracies with a 2D CNN, whereas the MLP exhibits higher computational efficiency.
KW - Condition monitoring
KW - Convolutional neural networks
KW - Deep learning
KW - Degradation detection
KW - Feature extraction
KW - Nuclear piping
UR - http://www.scopus.com/inward/record.url?scp=85182516202&partnerID=8YFLogxK
U2 - 10.1016/j.ymssp.2023.111091
DO - 10.1016/j.ymssp.2023.111091
M3 - Article
AN - SCOPUS:85182516202
SN - 0888-3270
VL - 209
JO - Mechanical Systems and Signal Processing
JF - Mechanical Systems and Signal Processing
M1 - 111091
ER -