Two neural network based strategies for the detection of a total instantaneous blockage of a sodium-cooled fast reactor

Martinez-Martinez, Sinuhé; Messai, Nadhir; Jeannot, Jean-Philippe; Nuzillard, Danielle

doi:10.1016/j.ress.2014.12.003

Cited by 11 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data fusion [9] and ML-based anomaly detection have been investigated for various processes. Data-driven ML approaches for NPP monitoring and anomaly detection include studies on detection of blockage in SFR [10,11], anomaly detection in reactor cores [12,13], predictive maintenance [14], accident classification [15], physics-informed neural networks [16,17], statistical anomaly detection enhanced with qualitative physics [18], and anomaly detection with Recurrent Neural Networks (RNNs) in imbalanced datasets from NPPs [19]. In particular, LSTM neural networks [20], a variant of RNNs, which have the potential advantages in transient data analysis due to their contextual information retention, have been explored in nuclear thermal hydraulics [21,22] and neutron flux [23] monitoring applications.…”

Section: Oveview Of Anomaly Detection In Nuclear Systemsmentioning

confidence: 99%

Anomaly Detection in Liquid Sodium Cold Trap Operation with Multisensory Data Fusion Using Long Short-Term Memory Autoencoder

Akins,

Kultgen,

Heifetz

2023

Energies

View full text Add to dashboard Cite

Sodium-cooled fast reactors (SFR), which use high temperature fluid near ambient pressure as coolant, are one of the most promising types of GEN IV reactors. One of the unique challenges of SFR operation is purification of high temperature liquid sodium with a cold trap to prevent corrosion and obstructing small orifices. We have developed a deep learning long short-term memory (LSTM) autoencoder for continuous monitoring of a cold trap and detection of operational anomaly. Transient data were obtained from the Mechanisms Engineering Test Loop (METL) liquid sodium facility at Argonne National Laboratory. The cold trap purification at METL is monitored with 31 variables, which are sensors measuring fluid temperatures, pressures and flow rates, and controller signals. Loss-of-coolant type anomaly in the cold trap operation was generated by temporarily choking one of the blowers, which resulted in temperature and flow rate spikes. The input layer of the autoencoder consisted of all the variables involved in monitoring the cold trap. The LSTM autoencoder was trained on the data corresponding to cold trap startup and normal operation regime, with the loss function calculated as the mean absolute error (MAE). The loss during training was determined to follow log-normal density distribution. During monitoring, we investigated a performance of the LSTM autoencoder for different loss threshold values, set at a progressively increasing number of standard deviations from the mean. The anomaly signal in the data was gradually attenuated, while preserving the noise of the original time series, so that the signal-to-noise ratio (SNR) averaged across all sensors decreased below unity. Results demonstrate detection of anomalies with sensor-averaged SNR < 1.

show abstract

Section: Oveview Of Anomaly Detection In Nuclear Systemsmentioning

confidence: 99%

Anomaly Detection in Liquid Sodium Cold Trap Operation with Multisensory Data Fusion Using Long Short-Term Memory Autoencoder

Akins,

Kultgen,

Heifetz

2023

Energies

View full text Add to dashboard Cite

show abstract

“…In the literature, a lot of fault diagnosis methods have been proposed; for example, Wang Hang applied the support vector machine (SVM) and improved particle swarm optimization (PSO) to perform further diagnosis in NPP on the basis of qualitative reasoning by knowledge-based preliminary diagnosis and sample data provided by an online simulation model [2]. Sinuhe adopted a time-lagged feed-forward neural network in the research of the total instantaneous blockage of an assembly in the core of a sodium-cooled fast reactor [3]. Principal component analysis (PCA) is applied for fault detection of sensors in a nuclear power plant by Li et al [4].…”

Section: Introductionmentioning

confidence: 99%

The Research of Fault Diagnosis of Nuclear Power Plant Based on ELM-AdaBoost.SAMME

2020

Science and Technology of Nuclear Installations

View full text Add to dashboard Cite

A fault diagnosis framework based on extreme learning machine (ELM) and AdaBoost.SAMME is proposed in a nuclear power plant (NPP) in this paper. After briefly describing the principles of ELM and AdaBoost.SAMME algorithm, the fault diagnosis framework sets ELM algorithm as the weak classifier and then integrates several weak classifiers into a strong one using the AdaBoost.SAMME algorithm. Furthermore, some experiments are put forward for the setting of two algorithms. The results of simulation experiments on the HPR1000 simulator show that the combined method has higher precision and faster speed by improving the performance of weak classifiers compared to the BP neural network and verify the feasibility and validity of the ensemble learning method for fault diagnosis. Meanwhile, the results also indicate that the proposed method can meet the requirements of a real-time diagnosis of the nuclear power plant.

show abstract

“…Because the inlet port blockage, the temperature measured above the subassembly with a TIB is not representative for the TIB detection. The early detection of an abnormal temperature rise provoked by a TIB has been previously considered in [5,6,7]. The recursive filtering based on the statistical estimation theory is used to reduce the outlet temperatures uncertainties in [5].…”

Section: Introductionmentioning

confidence: 99%

“…Next, the filtered TCs signals are used to detect a local temperature rise due to a TIB. The TIB detection algorithms based on the artificial neural network-based strategies are used in [6,7]. Nevertheless, some problems hold unsolved, especially, the calculation of the probabilities of missed detection and false alarm.…”

Section: Introductionmentioning

confidence: 99%

Sequential detection of a total instantaneous blockage occurred in a single subassembly of a sodium-cooled fast reactor

Harrou

Cogranne

Beauseroy

et al. 2020

Nuclear Engineering and Design

Self Cite

View full text Add to dashboard Cite

Two neural network based strategies for the detection of a total instantaneous blockage of a sodium-cooled fast reactor

Cited by 11 publications

References 22 publications

Anomaly Detection in Liquid Sodium Cold Trap Operation with Multisensory Data Fusion Using Long Short-Term Memory Autoencoder

Anomaly Detection in Liquid Sodium Cold Trap Operation with Multisensory Data Fusion Using Long Short-Term Memory Autoencoder

The Research of Fault Diagnosis of Nuclear Power Plant Based on ELM-AdaBoost.SAMME

Sequential detection of a total instantaneous blockage occurred in a single subassembly of a sodium-cooled fast reactor

Contact Info

Product

Resources

About