A noise and vibration tolerant ResNet for field reconstruction with sparse sensors. (English) Zbl 07893899
Summary: The aging of nuclear reactors presents a substantial challenge within the field of nuclear energy. Consequently, there is a critical demand for field reconstruction techniques capable of obtaining comprehensive spatial data about the condition of nuclear reactors, even when provided with limited observer data. It is worth noting that prior research has often neglected to account for the impact of noise and changes in sensor states that can occur during actual production scenarios. In this paper, the so called Noise and Vibration Tolerant ResNet (NVT-ResNet) is proposed to tackle these challenges. By introducing noise and vibrations into the training data, NVT-ResNet is able to learn the tolerance thus exhibits robustness for the field reconstruction. The influence of sensor numbers on the model’s performance is also investigated. Numerical results convincingly demonstrate that even with limited sparse sensors exposed to a noise with magnitude of 5% and vibrations, NVT-ResNet consistently achieves a reconstruction field of relative \(L_2\) error within 1% and relative \(L_\infty\) error of less than 5% in average sense. Additionally, NVT-ResNet exhibits remarkable computational efficiency, with field reconstruction taking only microseconds. This makes it a viable candidate for integration into online monitoring systems, thereby enhancing the safety performance of nuclear reactors.
MSC:
| 68T05 | Learning and adaptive systems in artificial intelligence |
| 94A12 | Signal theory (characterization, reconstruction, filtering, etc.) |
| 92F05 | Other natural sciences (mathematical treatment) |
References:
| [1] | K. Khattab, Nuclear power reactors in the world, Atom and Development, 33 (2) (2021) 43-55. |
| [2] | C. Demazière, P. Vinai, M. Hursin, S. Kollias, J. Herb, Overview of the CORTEX project, Pro-ceedings of the International Conference on the Physics of Reactors-Reactor Physics paving the way towards more efficient systems (PHYSOR2018), Cancun, Mexico, (2018). |
| [3] | A. Vidal-Ferràndiz, D. Ginestar, A. Carre ño, G. Verd ú, A. Dokhane, V. Verma, Y. Perin, J. Herb, A. Mylonakis, C. Demazière, et al., Modelling and simulations of reactor neutron noise induced by mechanical vibrations, Annals of Nuclear Energy, 177 (2022) 109300, Elsevier. |
| [4] | J. Fu, S. Cui, S. Cen, C. Li, Statistical characterization and reconstruction of heterogeneous microstructures using deep neural network, Computer Methods in Applied Mechanics and Engineering, 373 (2021) 113516, Elsevier. · Zbl 1506.74233 |
| [5] | J. Fu, D. Xiao, D. Li, H R. Thomas, C. Li, Stochastic reconstruction of 3D microstructures from 2D cross-sectional images using machine learning-based characterization, Computer Methods in Applied Mechanics and Engineering, 390 (2022) 114532, Elsevier. · Zbl 1507.74565 |
| [6] | R. Fu, D. Xiao, I. M. Navon, F. Fangxin, L. Yang, A non-linear non-intrusive reduced order model of fluid flow by auto-encoder and self-attention deep learning methods, International Journal for Numerical Methods in Engineering, 2023, Wiley Online Library. |
| [7] | B. Bouriquet, J.-P. Argaud, R. Cugnart, Optimal design of measurement network for neu-tronic activity field reconstruction by data assimilation, Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equip-ment, 664 (1) (2012) 117-126, Elsevier. |
| [8] | M. Asch, M. Bocquet, M. Nodet, Data assimilation: Methods, algorithms, and applications, 2016, SIAM. |
| [9] | Y. Maday, T. Taddei, Adaptive PBDW approach to state estimation: noisy observations; user-defined update spaces, SIAM Journal on Scientific Computing, 41 (4) (2019), B669-B693, SIAM. · Zbl 1426.76551 |
| [10] | S. Cheng, C. Quilodrán-Casas, S. Ouala, A. Farchi, C. Liu, P. Tandeo, R. Fablet, D. Lucor, B. Iooss, J. Brajard, et al., Machine learning with data assimilation and uncertainty quantifica-tion for dynamical systems: a review, IEEE/CAA Journal of Automatica Sinica, 10 (6) (2023) 1361-1387, IEEE. |
| [11] | Y. Liu, D. Wang, X. Sun, N. Dinh, R. Hu, Uncertainty quantification for Multiphase-CFD simulations of bubbly flows: a machine learning-based Bayesian approach supported by high-resolution experiments, Reliability Engineering & System Safety, 212 (2021) 107636, Elsevier. |
| [12] | S. Riva, C. Introini, S. Lorenzi, A. Cammi, Hybrid data assimilation methods, Part I: Numer-ical comparison between GEIM and PBDW, Annals of Nuclear Energy, 190 (2023) 109864, Elsevier. |
| [13] | C. Introini, S. Riva, S. Lorenzi, S. Cavalleri, A. Cammi, Non-intrusive system state recon-struction from indirect measurements: A novel approach based on Hybrid Data Assimila-tion methods, Annals of Nuclear Energy, 182 (2023) 109538, Elsevier. |
| [14] | J.-P. Argaud, B. Bouriquet, F. De Caso, H. Gong, Y. Maday, O. Mula, Sensor placement in nuclear reactors based on the generalized empirical interpolation method, Journal of Com-putational Physics, 363 (2018) 354-370, Elsevier. · Zbl 1392.82075 |
| [15] | H. Gong, Z. Chen, Q. Li, Generalized empirical interpolation method with H1 regulariza-tion: Application to nuclear reactor physics, Frontiers in Energy Research, 9 (2022) 804018, Frontiers. |
| [16] | H. Gong, Z. Chen, Y. Maday, Q. Li, Optimal and fast field reconstruction with reduced basis and limited observations: Application to reactor core online monitoring, Nuclear Engineer-ing and Design, 377 (2021) 111113, Elsevier. |
| [17] | H. Gong, Y. Yingrui, Q. Li, Reactor power distribution detection and estimation via a sta-bilized gappy proper orthogonal decomposition method, Nuclear Engineering and Design, 370 (2020) 110833, Elsevier. |
| [18] | H. Gong, S. Cheng, Z. Chen, Q. Li, C. Quilodr’an-Casas, D. Xiao, R. Arcucci, An efficient digital twin based on machine learning SVD autoencoder and generalised latent assimilation for nuclear reactor physics, Annals of Nuclear Energy, 179 (2022) 109431, Elsevier. |
| [19] | Y. Liu, R. Hu, A. Kraus, P. Balaprakash, A. Obabko, Data-driven modeling of coarse mesh turbulence for reactor transient analysis using convolutional recurrent neural networks, Nu-clear Engineering and Design, 390 (2022) 111716, Elsevier. |
| [20] | K. Fukami, R. Maulik, N. Ramachandra, K. Fukagata, K. Taira, Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning, Nature Machine Intel-ligence, 3 (11) (2021) 945-951, Nature Publishing Group UK London. |
| [21] | T. Nakamura, K. Fukami, K. Hasegawa, Y. Nabae, K. Fukagata, Convolutional neural net-work and long short-term memory based reduced order surrogate for minimal turbulent channel flow, Physics of Fluids, 33 (2) (2021), AIP Publishing. |
| [22] | Y. Liu, R. Hu, A. Kraus, P. Balaprakash, A. Obabko, Data-driven modeling of coarse mesh turbulence for reactor transient analysis using convolutional recurrent neural networks, Nu-clear Engineering and Design, 390 (2022) 111716, Elsevier. |
| [23] | S. Hochreiter, J. Schmidhuber, Long short-term memory, Neural Computation, 9 (8) (1997) 1735-1780, MIT Press. |
| [24] | S. Cheng, Y. Guo, R. Arcucci, A generative model for surrogates of spatial-temporal wild-fire nowcasting, IEEE Transactions on Emerging Topics in Computational Intelligence, 2023, IEEE. |
| [25] | A. G”uemes, C. Sanmiguel Vila, S. Discetti, Super-resolution generative adversarial net-works of randomly-seeded fields, Nature Machine Intelligence, 4 (12) (2022) 1165-1173, Na-ture Publishing Group UK London. |
| [26] | Y. Yang, H. Gong, Q. Yang, Y. Deng, Q. He, S. Zhang, On the uncertainty analysis of the data-enabled physics-informed neural network for solving neutron diffusion eigenvalue prob-lem, arXiv preprint arXiv:2303.08455, (2023). |
| [27] | P. Vinai, H. Yi, C. Demaziere, A. Rouchon, A. Zoia, On the simulation of neutron noise induced by vibrations of fuel pins in a fuel assembly, Annals of Nuclear Energy, 181 (2023) 109521. |
| [28] | A. Nordio, C.-F. Chiasserini, E. Viterbo, Performance of linear field reconstruction tech-niques with noise and uncertain sensor locations, IEEE Transactions on Signal Processing, 56 (8) (2008) 3535-3547, IEEE. · Zbl 1390.94337 |
| [29] | K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2016) 770-778. |
| [30] | H. Yu, X. Miao, H. Wang, Bearing fault reconstruction diagnosis method based on ResNet-152 with multi-scale stacked receptive field, Sensors, 22 (5) (2022) 1705, MDPI. |
| [31] | M. Guo, H. Zhu, G. Zhou, Q. Wang, Dense light field reconstruction from sparse sampling using residual network, Computer Vision-ACCV 2018: 14th Asian Conference on Computer Vision, Perth, Australia, December 2-6, 2018,. |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
