Application of cost-sensitive LSTM in water level prediction for nuclear reactor pressurizer

Abstract Applying an accurate parametric prediction model to identify abnormal or false pressurizer water levels (PWLs) is critical to the safe operation of marine pressurized water reactors (PWRs). Recently, deep-learning-based models have proved to be a powerful feature extractor to perform high-accuracy prediction. However, the effectiveness of models still suffers from two issues in PWL prediction: the correlations shifting over time between PWL and other feature parameters, and the example imbalance between fluctuation examples (minority) and stable examples (majority). To address these problems, we propose a cost-sensitive mechanism to facilitate the model to learn the feature representation of later examples and fluctuation examples. By weighting the standard mean square error loss with a cost-sensitive factor, we develop a Cost-Sensitive Long Short-Term Memory (CSLSTM) model to predict the PWL of PWRs. The overall performance of the CSLSTM is assessed by a variety of evaluation metrics with the experimental data collected from a marine PWR simulator. The comparisons with the Long Short-Term Memory (LSTM) model and the Support Vector Regression (SVR) model demonstrate the effectiveness of the CSLSTM.

[1]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[2]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups , 2012, IEEE Signal Processing Magazine.

[3]  Pierre Le Bot.  Human reliability data, human error and accident models - illustration through the Three Mile Island accident analysis , 2004, Reliab. Eng. Syst. Saf..

[4]  Piero Baraldi,et al.  Local Fusion of an Ensemble of Models for the Reconstruction of Faulty Signals , 2010, IEEE Transactions on Nuclear Science.

[5]  Yang Guo,et al.  A Weighted Deep Representation Learning Model for Imbalanced Fault Diagnosis in Cyber-Physical Systems , 2018, Sensors.

[6]  Haidong Shao,et al.  Electric Locomotive Bearing Fault Diagnosis Using a Novel Convolutional Deep Belief Network , 2018, IEEE Transactions on Industrial Electronics.

[7]  Enrico Zio,et al.  Neural network-based fault detections in a pressurized water reactor pressurizer , 1996 .

[8]  P. Balligand,et al.  Experience gained in France on heat recovery from nuclear plants for agriculture and pisciculture , 1978 .

[9]  Saeed Setayeshi,et al.  Prediction of critical heat flux using ANFIS , 2010 .

[10]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[11]  Jaemin Yang,et al.  An accident diagnosis algorithm using long short-term memory , 2018 .

[12]  C. Lombardi,et al.  Prediction of two-phase mixture density using artificial neural networks , 1997 .

[13]  Enrico Zio,et al.  A Novel Dynamic-Weighted Probabilistic Support Vector Regression-Based Ensemble for Prognostics of Time Series Data , 2015, IEEE Transactions on Reliability.

[14]  Nitesh V. Chawla,et al.  Editorial: special issue on learning from imbalanced data sets , 2004, SKDD.

[15]  Chen Yu-qing.  Study on Pressurizer Water Level Signal Reconstruction Based on Support Vector Regression , 2013 .

[16]  Hua Shen,et al.  A Time Series Forecasting Model Based on Deep Learning Integrated Algorithm with Stacked Autoencoders and SVR for FX Prediction , 2016, ICANN.

[17]  Enrico Zio,et al.  A randomized model ensemble approach for reconstructing signals from faulty sensors , 2011, Expert Syst. Appl..

[18]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[19]  Jianping Wu,et al.  Traffic Flow Prediction with Rainfall Impact Using a Deep Learning Method , 2017 .

[20]  Wei Wu,et al.  Convergence analysis of online gradient method for BP neural networks , 2011, Neural Networks.

[21]  Meng Wang,et al.  Hierarchical LSTM for Sign Language Translation , 2018, AAAI.

[22]  Wang Xiao-lon.  Prediction for Water Level of Steam Generator Based on Multi-signal Fusion by Support Vector Regression , 2013 .

[23]  Enrico Zio,et al.  A novel fault detection system taking into account uncertainties in the reconstructed signals , 2014 .

[24]  Stefanos D. Kollias,et al.  A Deep Learning Approach to Anomaly Detection in Nuclear Reactors , 2018, 2018 International Joint Conference on Neural Networks (IJCNN).

[25]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[26]  Stefanos D. Kollias,et al.  Towards a Deep Unified Framework for Nuclear Reactor Perturbation Analysis , 2018, 2018 IEEE Symposium Series on Computational Intelligence (SSCI).

[27]  Enrico Zio,et al.  An ensemble approach to sensor fault detection and signal reconstruction for nuclear system control , 2010 .

[28]  Enrico Zio,et al.  Fault Detection in Nuclear Power Plants Components by a Combination of Statistical Methods , 2013, IEEE Transactions on Reliability.

[29]  Jian-Hua Ye,et al.  Research on pressurizer water level control of nuclear reactor based on RBF neural network and PID controller , 2010, 2010 International Conference on Machine Learning and Cybernetics.

[30]  Yunchao Wei,et al.  Deep Learning with S-Shaped Rectified Linear Activation Units , 2015, AAAI.

[31]  Enrico Zio,et al.  Two novel procedures for aggregating randomized model ensemble outcomes for robust signal reconstruction in nuclear power plants monitoring systems , 2011 .

[32]  Wang Xiao-lon.  Abnormal Parameter Reconstruction for Marine Nuclear Power Plant Based on Multi-Signal Coupling , 2014 .