Nuclear Power Plant Diagnosis Research Articles

Enhancing accident diagnosis in nuclear power plants through knowledge Distillation: Bridging the gap between simulation and Real-World scenarios

Accident diagnosis is critical for ensuring the safety and reliability of nuclear power plants (NPPs). However, the scarcity of real-world data poses a significant challenge in the development of accurate, and robust, artificial intelligence (AI)-based diagnostic systems. This paper presents a novel approach for addressing this domain issue by leveraging knowledge-distillation techniques. We propose training a lightweight-student model that uses distilled knowledge from multiple teacher models, each of which captures different aspects of the problem, such as noise and time trends. Teacher models and student models were trained on CNS simulation data, and both models were evaluated on real-world proxy data(PCTRAN Simulation data).Through a series of experiments, we demonstrated the effectiveness of our approach in enhancing the performance and robustness of student models. The student model showed improvements in untrained target domain, when knowledge obtained from noisy, time-trend-information containing, and naive teacher models was used instead of a single teacher model. The incorporation of diverse knowledge from different teacher models aids the student model in handling noisy data, capturing temporal dependencies, and generalizing unseen scenarios better.Moreover, our analysis of the relative training time highlighted the computational benefits of using a lighter student model. The student model required significantly less training time than the teacher model, making it more efficient for deployment and online updation in real-world scenarios. This computational efficiency is particularly valuable in the context of NPPs where timely decision making and resource constraints are critical factors.Our findings will contribute to the development of effective, robust, and computationally efficient accident-diagnosis systems for NPPs. By bridging the gap between simulations and real-world scenarios through knowledge distillation, this study paves the way for further advancements in enhancing the safety, reliability, and efficiency of the nuclear power industry.

Fault diagnosis of nuclear power plant sliding bearing-rotor systems using deep convolutional generative adversarial networks

Sliding bearings are crucial rotating mechanical components in nuclear power plants, and their failures can result in severe economic losses and human casualties. Deep learning provides a new approach to bearing fault diagnosis, but there is currently a lack of a universal fault diagnosis model for studying bearing-rotor systems under various operating conditions, speeds and faults. Research on bearing-rotor systems supported by sliding bearings is limited, leading to insufficient fault data. To address these issues, this paper proposes a fault diagnosis model framework for bearing-rotor systems based on a deep convolutional generative adversarial network (TF-DLGAN). This model not only exhibits outstanding fault diagnosis performance but also addresses the issue of insufficient fault data. An experimental platform is constructed to conduct fault experiments under various operating conditions, speeds and faults, establishing a dataset for sliding bearing-rotor system faults. Finally, the model's effectiveness is validated using this dataset.

ECOC-based integrated learning method for fault diagnosis in nuclear power plants

Abstract The fault diagnosis system of nuclear power plants plays an important role in ensuring the safety and economy of nuclear power plant operations. This paper first analyzes typical faults of nuclear power plants and their phenomena, and fault samples are obtained. A comprehensive study of the structure of the nuclear power plant system, its working mode and the association between each subsystem is carried out to analyze the monitoring parameters and fault characteristics and establish the fault data set. Secondly, an IFWA (Improved Fireworks Algorithm - Integrated Learning) algorithm is proposed to assess the severity of faults in the first circuit of a nuclear power plant. Finally, the fault diagnosis module is divided into three units according to the functional logic, i.e., condition monitoring unit, fault identification unit, and fault severity assessment unit. The results show that the diagnostic accuracy of the IFWA algorithm is 94.25% for SGTR in the single-fault diagnosis experiment and 96.25% for SGTR-LOCA in the multiple-fault diagnosis experiment. It shows that the IFWA algorithm proposed in this paper has the optimal performance capability when applied to nuclear power plant fault diagnosis and effectively assists managers in diagnosing faults and giving maintenance recommendations.

Fault Diagnosis of Nuclear Power Plant Based on Sparrow Search Algorithm Optimized CNN-LSTM Neural Network

Nuclear power is a type of clean and green energy; however, there is a risk of radioactive material leakage when accidents occur. When radioactive material leaks from nuclear power plants, it has a great impact on the environment and personnel safety. In order to enhance the safety of nuclear power plants and support the operator’s decisions under accidental circumstances, this paper proposes a fault diagnosis method for nuclear power plants based on the sparrow search algorithm (SSA) optimized by the CNN-LSTM network. Firstly, the convolutional neural network (CNN) was used to extract features from the data before they were then combined with the long short-term memory (LSTM) neural network to process time series data and form a CNN-LSTM model. Some of the parameters in the LSTM neural network need to be manually tuned based on experience, and the settings of these parameters have a great impact on the overall model results. Therefore, this paper selected the sparrow search algorithm with a strong search capability and fast convergence to automatically search for the hand-tuned parameters in the CNN-LSTM model, and finally obtain the SSA-CNN-LSTM model. This model can classify the types of accidents that occur in nuclear power plants to reduce the nuclear safety hazards caused by human error. The experimental data are from a personal computer transient analyzer (PCTRAN). The results show that the classification accuracy of the SSA-CNN-LSTM model for the nuclear power plant fault classification problem is as high as 98.24%, which is 4.80% and 3.14% higher compared with the LSTM neural network and CNN-LSTM model, respectively. The superiority of the sparrow search algorithm for optimizing model parameters and the feasibility and accuracy of the SSA-CNN-LSTM model for nuclear power plant fault diagnosis were verified.

A fault diagnosis of nuclear power plant rotating machinery based on multi-sensor and deep residual neural network

Rotating machinery is a key component of nuclear power plants (NPPs). The integrity of rotating machine is related to the safety and economy of the entire NPPs. In order to achieve better and more robust diagnostic performance, this work proposes an intelligent fault diagnosis method based on multi-sensor and deep residual neural network. This method gives full play to the value of multi-sensor information, and utilizes the powerful learning ability of deep learning model to realize the identification of rotating machinery fault types. The effectiveness of the method is evaluated by using the motor dataset and the bearing dataset from fault simulation experiment bench. In addition, the anti-noise ability of the method is tested and compared with other methods. The results show that the proposed method has higher diagnosis accuracy and stronger robustness, demonstrating the potential application value in rotating machinery of NPPs.

Deep reinforcement learning for class imbalance fault diagnosis of equipment in nuclear power plants

In equipment fault diagnosis in nuclear power plants, there may be far more samples in one class (e.g., a health state) than in another class (e.g., a fault state). The distribution of data in each class is highly skewed. Most machine learning algorithms are suitable for balanced training datasets. When faced with imbalanced samples, these algorithms tend to provide good identification for the majority classes and bias for the minority classes. However, the misclassification of minority classes can lead to high costs. To address the above problem, this paper develops a deep reinforcement learning-based diagnosis method that models fault diagnosis as a sequential decision-making process. At each time step, the agent receives the state of the environment represented by the training samples and then takes a diagnosis action guided by a policy. If the action is correct/incorrect, the agent receives a positive/negative reward. The reward for minority classes is higher than that for majority classes. The agent’s goal is to obtain as many cumulative rewards as possible in the process, i.e., to identify the sample as correctly as possible. Six demonstration scenarios are constructed, depending on the selected fault datasets and the designed model structures. Experiments show that the proposed method achieves a higher weighted-averaged F1 score than the classical supervised learning method in most cases of class imbalance. The proposed method has potential applications in the field of class imbalance fault diagnosis of equipment in nuclear power plants.

A fault diagnosis methodology for nuclear power plants based on Kernel principle component analysis and quadratic support vector machine

The safety of nuclear power plant operation can be improved efficiently by developing the fault diagnosis applications. However, adopting single technique may restrict the flexibility and accuracy of the fault diagnosis module. This paper proposes a new fault diagnosis methodology for nuclear power plants based on Kernel Principle Component Analysis (KPCA) and Quadratic Support Vector Machine (QSVM). The nonlinearity between variables is analyzed and the importance of variables are quantified by standard deviations. Sensor faults are distinguished from system faults using contribution charts. In pre-process stage of classification, five normalization modes are compared to achieve better performance of classifiers. For fault identification, samples are transformed to QSVM classifier and the diagnosis results are compared with other classifiers. To further evaluate the performance, three typical case conditions are tested. QSVM outperforms other classifiers on all types of system faults. The findings are beneficial for fault diagnosis of nuclear power plant.

Combinatorial Techniques for Fault Diagnosis in Nuclear Power Plants Based on Bayesian Neural Network and Simplified Bayesian Network-Artificial Neural Network

Knowledge-driven and data-driven methods are the two representative categories of intelligent technologies used in fault diagnosis in nuclear power plants. Knowledge-driven methods have advantages in interpretability and robustness, while data-driven methods have better performance in ease of modeling and inference efficiency. Given the complementarity of the two methods, a combination of them is a worthwhile investigation. In this work, we introduce two new techniques based on Bayesian theory (knowledge-driven) and artificial neural network (data-driven) for fault diagnosis in nuclear power plants. The first approach exploits an integrated technique, Bayesian Neural Network (BNN), which introduces Bayesian theory into the neural network to provide confidence in diagnosis. The second approach, denoted as Simplified Bayesian Network-Artificial Neural Network (SBN-ANN), adopts a hierarchical diagnosis idea, which firstly uses a simplified Bayesian network to diagnose fault types and then a neural network to diagnose the severity of faults. The two new techniques are implemented and verified with simulated faults data of a typical pressurized water reactor. Compared with single-algorithmic diagnostic approaches such as Bayesian network and neural network, the new combinatorial techniques show better performance in diagnostic precision. The results suggest the feasibility to develop the data and knowledge dual-drive technologies for fault diagnosis.

Consistency check algorithm for validation and re-diagnosis to improve the accuracy of abnormality diagnosis in nuclear power plants

The diagnosis of abnormalities in a nuclear power plant is essential to maintain power plant safety. When an abnormal event occurs, the operator diagnoses the event and selects the appropriate abnormal operating procedures and sub-procedures to implement the necessary measures. To support this, abnormality diagnosis systems using data-driven methods such as artificial neural networks and convolutional neural networks have been developed. However, data-driven models cannot always guarantee an accurate diagnosis because they cannot simulate all possible abnormal events. Therefore, abnormality diagnosis systems should be able to detect their own potential misdiagnosis. This paper proposes a rule-based diagnostic validation algorithm using a previously developed two-stage diagnosis model in abnormal situations. We analyzed the diagnostic results of the sub-procedure stage when the first diagnostic results were inaccurate and derived a rule to filter the inconsistent sub-procedure diagnostic results, which may be inaccurate diagnoses. In a case study, two abnormality diagnosis models were built using gated recurrent units and long short-term memory cells, and consistency checks on the diagnostic results from both models were performed to detect any inconsistencies. Based on this, a re-diagnosis was performed to select the label of the second-best value in the first diagnosis, after which the diagnosis accuracy increased. That is, the model proposed in this study made it possible to detect diagnostic failures by the developed consistency check of the sub-procedure diagnostic results. The consistency check process has the advantage that the operator can review the results and increase the diagnosis success rate by performing additional re-diagnoses. The developed model is expected to have increased applicability as an operator support system in terms of selecting the appropriate AOPs and sub-procedures with re-diagnosis, thereby further increasing abnormal event diagnostic accuracy.

Graph neural network based multiple accident diagnosis in nuclear power plants: Data optimization to represent the system configuration

Because nuclear power plants (NPPs) are safety-critical infrastructure, it is essential to increase their safety and minimize risk. To reduce human error and support decision-making by operators, several artificial-intelligence-based diagnosis methods have been proposed. However, because of the nature of data-driven methods, conventional artificial intelligence requires large amount of measurement values to train and achieve enough diagnosis resolution.We propose a graph neural network (GNN) based accident diagnosis algorithm to achieve high diagnosis resolution with limited measurements. The proposed algorithm is trained with both the knowledge about physical correlation between components and measurement values. To validate the proposed methodology has a sufficiently high diagnostic resolution with limited measurement values, the diagnosis of multiple accidents was performed with limited measurement values and also, the performance was compared with convolution neural network (CNN). In case of the experiment that requires low diagnostic resolution, both CNN and GNN showed good results. However, for the tests that requires high diagnostic resolution, GNN greatly outperformed the CNN.

Model-Based Deep Transfer Learning Method to Fault Detection and Diagnosis in Nuclear Power Plants

Deep learning–based nuclear intelligent fault detection and diagnosis (FDD) methods have been widely developed and have achieved very competitive results with the progress of artificial intelligence technology. However, the pretrained model for diagnosis tasks is hard in achieving good performance when the reactor operation conditions are updated. On the other hand, retraining the model for a new data set will waste computing resources. This article proposes an FDD method for cross-condition and cross-facility tasks based on the optimized transferable convolutional neural network (CNN) model. First, by using the pretrained model's prior knowledge, the model's diagnosis performance to be transferred for source domain data sets is improved. Second, a model-based transfer learning strategy is adopted to freeze the feature extraction layer in a part of the training model. Third, the training data in target domain data sets are used to optimize the model layer by layer to find the optimization model with the transferred layer. Finally, the proposed comprehensive simulation platform provides source and target cross-condition and cross-facility data sets to support case studies. The designed model utilizes the strong nonlinear feature extraction performance of a deep network and applies the prior knowledge of pretrained models to improve the accuracy and timeliness of training. The results show that the proposed method is superior to achieving good generalization performance at less training epoch than the retraining benchmark deep CNN model.

An Unsupervised Mutual Information Feature Selection Method Based on SVM for Main Transformer Condition Diagnosis in Nuclear Power Plants

Dissolved gas in oil (DGA) is a common means of monitoring the condition of an oil-immersed transformer. The concentration of dissolved gas and the ratio of different gases are important indexes to judge the condition of power transformers. Monitoring devices for dissolved gas in oil are widely installed in main transformers, but there are few recorded fault data of main transformers. The special operation and maintenance modes of main transformers leads to the fault modes particularity of main transformers. In order to solve the problem of insufficient samples and the feature uncertainty, this paper puts forward an unsupervised mutual information method to select the feature verified by the optimized support vector machine (SVM) model of particle swarm optimization (PSO) method and tries to find the feature sequence with better performance. The methos is validated by data from nuclear power transformers.

Transfer learning with limited labeled data for fault diagnosis in nuclear power plants

Numerous achievements have been made in intelligent fault diagnosis of nuclear power plants, under the assumption that the labeled training data is sufficient and in the same distribution as the test data, which is always contrary to actual situations and limits their practical applications. Therefore, a novel transfer learning framework with diverse transfer strategies is proposed on basis of a pre-trained CNN model in this study, to deal with the problem of limited labeled data in target tasks. The pre-trained CNN is obtained by ample data in source task, then its weights are transferred to the target models and fine-tuned. The results show that with proper transfer strategy, the proposed transfer learning framework significantly boosts the diagnostic performances, compared with training a brand-new CNN model from scratch with insufficient labeled target data. Consequently, the feasibility and superiority of transfer learning in nuclear power plant fault diagnosis with limited labeled data are proven.

Unsupervised machine learning techniques for fault detection and diagnosis in nuclear power plants

Nuclear power plants have proved their importance in the energy sector by generating clean and uninterrupted energy over decades. Moreover, nuclear power plants (NPPs) are large-scale and complex systems with potential radioactive release risks. Hence, it is important to achieve the highest standards of safety by designing a reliable process monitoring system. Due to the massive amount of monitoring data that are collected and stored in modern NPPs, it is difficult to extract necessary information about the actual plant state in a timely and accurate manner. Machine learning techniques play a vital role as tools for data mining that help in decision-making and support the operators in the process industry. This paper presents an integrated framework for fault detection and diagnosis in NPPs using unsupervised machine learning techniques where there is no prior knowledge is required. In this framework, the faults are first detected using the principal component analysis (PCA) approach by different fault detection indices. Second, the multivariate contribution plots (MCPs) methods are used for fault diagnosis. The data collected from Personal Computer Transient Analyser (PCTRAN) simulation is utilized to demonstrate the efficiencies of all the discussed methods.

Data-Driven Machine Learning for Fault Detection and Diagnosis in Nuclear Power Plants: A Review

Data-driven machine learning (DDML) methods for the fault diagnosis and detection (FDD) in the nuclear power plant (NPP) are of emerging interest in the recent years. However, there still lacks research on comprehensive reviewing the state-of-the-art progress on the DDML for the FDD in the NPP. In this review, the classifications, principles, and characteristics of the DDML are firstly introduced, which include the supervised learning type, unsupervised learning type, and so on. Then, the latest applications of the DDML for the FDD, which consist of the reactor system, reactor component, and reactor condition monitoring are illustrated, which can better predict the NPP behaviors. Lastly, the future development of the DDML for the FDD in the NPP is concluded.

Ensemble learning with diversified base models for fault diagnosis in nuclear power plants

The performance and improvement of most currently proposed fault diagnosis models for nuclear power plants are limited due to their dependence on a single classification method. To solve this problem, this study proposes novel ensemble learning models (ELMs) obtained by integrating diversified base models through the plurality voting method and weighted voting method, respectively. Simulation data including one steady-state condition and 12 fault conditions are used to evaluate ELMs. The results show that ELMs achieve the best overall diagnostic performance and exhibit excellent performance for all faults. Compared with other common ensemble classification models, ELMs get better diagnostic performance at a dramatically lower time cost, and show significantly stronger robustness when diagnosing data with random noise. The universality of ELMs is illustrated by analyzing their performance under different input features. In summary, ensemble learning is a promising solution for fault diagnosis of nuclear power plants to improve safety and economy.

A Framework for Monitoring and Fault Diagnosis in Nuclear Power Plants Based on Signed Directed Graph Methods

When nuclear power plants (NPPs) are in a state of failure, they may release radioactive material into the environment. The safety of NPPs must thus be maintained at a high standard. Online monitoring and fault detection and diagnosis (FDD) are important in helping NPP operators understand the state of the system and provide online guidance in a timely manner. Here, to mitigate the shortcomings of process monitoring in NPPs, five-level threshold, qualitative trend analysis (QTA), and signed directed graph (SDG) inference are combined to improve the veracity and sensitivity of process monitoring and FDD. First, a three-level threshold is used for process monitoring to ensure the accuracy of an alarm signal, and candidate faults are determined based on SDG backward inference from the alarm parameters. According to the candidate faults, SDG forward inference is applied to obtain candidate parameters. Second, a five-level threshold and QTA are combined to determine the qualitative trend of candidate parameters to be utilized for FDD. Finally, real faults are identified by SDG forward inference on the basis of alarm parameters and the qualitative trend of candidate parameters. To verify the validity of the method, we have conducted simulation experiments, which comprise loss of coolant accident, steam generator tube rupture, loss of feed water, main steam line break, and station black-out. This case study shows that the proposed method is superior to the conventional SDG method and can diagnose faults more quickly and accurately.

Use of collaborative concept mapping in team diagnosis

AbstractTeamwork is necessary to accomplish challenging and information‐rich tasks in complex industrial systems, such as fault diagnosis in nuclear power plants. To improve team performance, assistive visualization tools are used to promote communication and reduce cognitive conflicts. As a shared visualization technology, collaborative concept mapping can effectively externalize one's thoughts into a visualized structure, thereby improving the efficiency of communication and information processing. This study accordingly investigates the effects of collaborative concept mapping on team diagnosis in two fault situations with different complexity levels in a simulated nuclear power plant: one caused by a single initiating event, and the other triggered by two initiating events. The dependent variables included fault analysis score, diagnostic result score, diagnosis time, workload, score of concept map content, and fixation time on a teammate's concept map. The findings revealed that collaborative concept mapping significantly improved the diagnostic result score and shortened diagnosis time, and marginally but significantly increased the fault analysis score. However, under the more complex fault situation triggered by two initiating events, this tool also significantly increased participants’ physical load and frustration level. Future work should focus on how collaborative concept mapping can improve operator performance while causing as little extra workload as possible, as well as explore its effects on experienced operators.

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

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.

Health diagnosis of nuclear power plant

At present, nuclear power plant is developing rapidly, and its application has been involved in many aspects including life, military, industry and many other important fields, bringing benefits to people’s life. However, the nuclear power plant has a relatively special structure. Once a safety accident occurs, the consequences will be unimaginable, and the cost of its operation and maintenance will be relatively high. Therefore, how to effectively diagnose the health status of the nuclear power plant is an urgent problem to be solved. On the above-mentioned research background, we need to study nuclear power plant health diagnosis method. Considering the characteristic of the nuclear power plant system and special failure mode, both the safety and economy, a health condition diagnosis method based on analytic hierarchy process and fuzzy comprehensive evaluation method is proposed for the structural characteristics and functional characteristics of nuclear power plants. According to the special failure mode and complex system structure of nuclear power plant, the evaluation index system based on failure mode is constructed by laying the system using the hierarchical analysis method, and the system is scored by fuzzy comprehensive evaluation method. The health status makes a coarse-grained diagnosis and provides a reference for the development of the operation and maintenance strategy.