A continuous learning monitoring strategy for multi-condition of nuclear power plant

Abstract Safety is the most important feature in the operation of nuclear power plants. developing and perfecting energy markets lead to an unavoidable problem of adjusting the structure of the random forest model to adapt to new situations, such as switching to other steady state operating conditions of nuclear power plants. Another critical challenge is how to effectively learn new knowledge from continuously collected measurements and how to integrate new information into current random forest models. So, this paper proposes a continuous learning monitoring strategy for multi-Condition of nuclear power plant. Next, real data from nuclear power plants are used for modeling and the simulator is used to insert the fault test. Finally, simulation tests show that the model can effectively detect the typical faults of nuclear power plants under multiple operation conditions, and the model can effectively learn new knowledge.

[1]  Min Xie,et al.  A new approach for fault diagnosis with full-scope simulator based on state information imaging in nuclear power plant , 2020 .

[2]  Ahmet Palazoglu,et al.  Process pattern construction and multi-mode monitoring , 2012 .

[3]  Donghua Zhou,et al.  Multimode process monitoring based on fault dependent variable selection and moving window-negative log likelihood probability , 2020, Comput. Chem. Eng..

[4]  Li Peng,et al.  Process Monitoring Based on Recursive Probabilistic PCA for Multi-mode Process∗ , 2015 .

[5]  Shuai Li,et al.  Modeling and monitoring of nonlinear multi-mode processes , 2014 .

[6]  Seung Jun Lee,et al.  Abnormality diagnosis model for nuclear power plants using two-stage gated recurrent units , 2020 .

[7]  Tianyou Chai,et al.  Fast just-in-time-learning recursive multi-output LSSVR for quality prediction and control of multivariable dynamic systems , 2021, Eng. Appl. Artif. Intell..

[8]  Akio Gofuku.  INTEGRATED DIAGNOSTIC TECHNIQUE FOR NUCLEAR POWER PLANTS , 2014 .

[9]  S. Joe Qin,et al.  Joint diagnosis of process and sensor faults using principal component analysis , 1998 .

[10]  Guohua Wu,et al.  Diagnosis of operational failures and on-demand failures in nuclear power plants: An approach based on dynamic Bayesian networks , 2020 .

[11]  Heng Li,et al.  Design study of hydrogen monitoring equipment for severe accident in containment of nuclear power plant , 2020 .

[12]  Man Gyun Na,et al.  APPLICATION OF MONITORING, DIAGNOSIS, AND PROGNOSIS IN THERMAL PERFORMANCE ANALYSIS FOR NUCLEAR POWER PLANTS , 2014 .

[13]  Xuefeng Yan,et al.  Multimodal process monitoring based on transition-constrained Gaussian mixture model , 2020 .

[14]  Enrico Zio,et al.  Time-dependent reliability analysis of the reactor building of a nuclear power plant for accounting of its aging and degradation , 2021, Reliab. Eng. Syst. Saf..

[15]  Chi-Yong Park,et al.  Demonstration of the validity of the early warning in online monitoring system for nuclear power plants , 2019, Nuclear Engineering and Design.

[16]  Hao Wu,et al.  Self-adaptive deep learning for multimode process monitoring , 2020, Comput. Chem. Eng..

[17]  Tian Ran Lin,et al.  Just-in-time learning based probabilistic gradient boosting tree for valve failure prognostics , 2021, Mechanical Systems and Signal Processing.

[18]  Enrico Zio,et al.  A multi-branch deep neural network model for failure prognostics based on multimodal data , 2021 .

[19]  Bongsoo Lee,et al.  Fiber-optic humidity sensor system for the monitoring and detection of coolant leakage in nuclear power plants , 2020 .

[20]  Orestes Llanes-Santiago,et al.  Data-driven monitoring of multimode continuous processes: A review , 2019, Chemometrics and Intelligent Laboratory Systems.

[21]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[22]  Cheng Zhou,et al.  Chiller sensor fault detection using a self-Adaptive Principal Component Analysis method , 2012 .

[23]  Jin Wen,et al.  A model-based fault detection and diagnostic methodology based on PCA method and wavelet transform , 2014 .

[24]  Zuoyi Zhang,et al.  Adaptive state-observer for monitoring flexible nuclear reactors , 2019, Energy.

[25]  Seung-Hwan Seong,et al.  Providing support to operators for monitoring safety functions using reinforcement learning , 2020 .

[26]  Seung-Hwan Seong,et al.  Operator action log based monitoring and control and its verification of nuclear power plants , 2021 .

[27]  Xiaojun Zhang,et al.  Method to determine nuclear accident release category via environmental monitoring data based on a neural network , 2020 .

[28]  Aniruddha Datta,et al.  Industrial alarm systems: Challenges and opportunities , 2017 .

[29]  Minjun Peng,et al.  Online fault monitoring based on deep neural network & sliding window technique , 2020 .

[30]  Hang Wang,et al.  Improved PCA model for multiple fault detection, isolation and reconstruction of sensors in nuclear power plant , 2020 .

[31]  Jun Shang,et al.  Conditional random field for monitoring multimode processes with stochastic perturbations , 2020, J. Frankl. Inst..

[32]  Min-Sen Chiu,et al.  Nonlinear process monitoring using JITL-PCA , 2005 .

[33]  Wei Li,et al.  False alarm reducing in PCA method for sensor fault detection in a nuclear power plant , 2018, Annals of Nuclear Energy.

[34]  Xuefeng Yan,et al.  Monitoring multi-mode plant-wide processes by using mutual information-based multi-block PCA, joint probability, and Bayesian inference , 2014 .

[35]  Biao Huang,et al.  A deep learning just-in-time modeling approach for soft sensor based on variational autoencoder , 2020 .