Localization and size estimation for breaks in nuclear power plants

Abstract Several algorithms for nuclear power plant (NPP) break event detection, isolation, localization, and size estimation are proposed. A break event can be promptly detected and isolated after its occurrence by simultaneously monitoring changes in the sensing readings and by employing an interquartile range-based isolation scheme. By considering the multi-sensor data block of a break to be rank-one, it can be located as the position whose lead field vector is most orthogonal to the noise subspace of that data block using the Multiple Signal Classification (MUSIC) algorithm. Owing to the flexibility of deep neural networks in selecting the best regression model for the available data, we can estimate the break size using multiple-sensor recordings of the break regardless of the sensor types. The efficacy of the proposed algorithms was evaluated using the data generated by Maanshan NPP simulator. The experimental results demonstrated that the MUSIC method could distinguish two near breaks. However, if the two breaks were close and of small sizes, the MUSIC method might wrongly locate them. The break sizes estimated by the proposed deep learning model were close to their actual values, but relative errors of more than 8% were seen while estimating small breaks’ sizes.

[1]  Hyeonmin Kim,et al.  Smart support system for diagnosing severe accidents in nuclear power plants , 2018 .

[2]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[3]  B. Silverman.  Density estimation for statistics and data analysis , 1986 .

[4]  César Queral,et al.  Accident Management Actions in an Upper-Head Small-Break Loss-of-Coolant Accident with High-Pressure Safety Injection Failed , 2011 .

[5]  Young Do Koo,et al.  Identification of LOCA and Estimation of Its Break Size by Multiconnected Support Vector Machines , 2017, IEEE Transactions on Nuclear Science.

[6]  Waclaw Gudowski,et al.  Feasibility Study on Transient Identification in Nuclear Power Plants Using Support Vector Machines , 2006 .

[7]  Jaewhan Kim,et al.  Human Error Mode Identification for NPP Main Control Room Operations Using Soft Controls , 2011 .

[8]  Tara N. Sainath,et al.  Improving deep neural networks for LVCSR using rectified linear units and dropout , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[9]  A. Lee Swindlehurst,et al.  Projection Versus Prewhitening for EEG Interference Suppression , 2012, IEEE Transactions on Biomedical Engineering.

[10]  Nils Bausch,et al.  A study on the robustness of neural network models for predicting the break size in LOCA , 2018, Progress in Nuclear Energy.

[11]  Shun-Chi Wu,et al.  Multivariate algorithms for initiating event detection and identification in nuclear power plants , 2018 .

[12]  Jiawei Han,et al.  Data Mining: Concepts and Techniques , 2000 .

[13]  Douglas C. Montgomery,et al.  Applied Statistics and Probability for Engineers, Third edition , 1994 .

[14]  César Queral,et al.  Effects of delayed RCP trip during SBLOCA in PWR , 2014 .

[15]  V. Venkat Raj,et al.  Symptom based diagnostic system for nuclear power plant operations using artificial neural networks , 2003, Reliab. Eng. Syst. Saf..

[16]  Andrew Zisserman,et al.  Spatial Transformer Networks , 2015, NIPS.

[17]  Mark J. Embrechts,et al.  Hybrid identification of nuclear power plant transients with artificial neural networks , 2004, IEEE Transactions on Industrial Electronics.

[18]  B. Friedlander,et al.  Direction finding using spatial smoothing with interpolated arrays , 1992 .

[19]  K. Moshkbar-Bakhshayesh.  Development of a modular system for estimating attenuation coefficient of gamma radiation: comparative study of different learning algorithms of cascade feed-forward neural network , 2019, Journal of Instrumentation.

[20]  Tomoyoshi Shimobaba,et al.  Convolutional Neural Network-Based Regression for Depth Prediction in Digital Holography , 2018, 2018 IEEE 27th International Symposium on Industrial Electronics (ISIE).

[21]  Xiaoli Li,et al.  Deep Convolutional Neural Network Based Regression Approach for Estimation of Remaining Useful Life , 2016, DASFAA.

[22]  Man Gyun Na,et al.  Prediction of major transient scenarios for severe accidents of nuclear power plants , 2004 .

[23]  Gopika Vinod,et al.  Application of artificial neural networks to nuclear power plant transient diagnosis , 2007, Reliab. Eng. Syst. Saf..

[24]  Atul Srivastava,et al.  A diagnostic system for identifying accident conditions in a nuclear reactor , 2011 .

[25]  Robert A. McLaughlin,et al.  Convolutional neural network regression for short‐axis left ventricle segmentation in cardiac cine MR sequences , 2017, Medical Image Anal..

[26]  Man Gyun Na,et al.  MONITORING SEVERE ACCIDENTS USING AI TECHNIQUES , 2012 .

[27]  R. O. Schmidt,et al.  Multiple emitter location and signal Parameter estimation , 1986 .

[28]  T. Moon,et al.  Mathematical Methods and Algorithms for Signal Processing , 1999 .

[29]  Wen-Hsien Fang,et al.  FSF MUSIC for Joint DOA and Frequency Estimation and Its Performance Analysis , 2006, IEEE Transactions on Signal Processing.

[30]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[31]  Radu Horaud,et al.  A Comprehensive Analysis of Deep Regression , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  Man Gyun Na,et al.  Detection and Diagnostics of Loss of Coolant Accidents Using Support Vector Machines , 2008, IEEE Transactions on Nuclear Science.

[33]  Richard D. Braatz,et al.  Fault Detection and Diagnosis in Industrial Systems , 2001 .

[34]  Mohammad B. Ghofrani,et al.  Real-time estimation of break sizes during LOCA in nuclear power plants using NARX neural network , 2019 .

[35]  Barry M. Wise,et al.  The process chemometrics approach to process monitoring and fault detection , 1995 .

[36]  K. Moshkbar-Bakhshayesh.  Bayesian regularization of multilayer perceptron neural network for estimation of mass attenuation coefficient of gamma radiation in comparison with different supervised model-free methods , 2020, Journal of Instrumentation.