Search

In nuclear power plants, the loss-of-coolant accident (LOCA) stands out as the most prevalent and consequential incident. Accurate breach size diagnosis is crucial for the mitigation of LOCAs, and identifying the cause of an accident can prevent catastrophic consequences. Traditional methods mostly focus on combining model algorithms and utilize intricate composite model neural network architectures. However, it is crucial to investigate whether greater complexity necessarily leads to better performance. In addition, the consideration of the impact of dataset construction and data preprocessing on model performance is also needed for model building. This paper proposes a framework named DeepLOCA-Lattice to experiment with different preprocessing approaches to fundamental deep learning models for a comprehensive analysis of the diagnosis of LOCA breach size. The DeepLOCA-Lattice involves data preprocessing via the lattice algorithm and equal-interval partitioning and deep-learning-based models, including the multi-layer perceptron (MLP), recurrent neural networks (RNNs), convolutional neural networks (CNNs), and the transformer model in LOCA breach size diagnosis. After conducting rigorous ablation experiments, we have discovered that even rudimentary foundational models can achieve accuracy rates that exceed 90%. This is a significant improvement when compared to the previous models, which yield an accuracy rate of lower than 50%. The results interestingly demonstrate the superior performance and efficacy of the fundamental deep learning model, with an effective dataset construction approach. It elucidates the presence of a complex interplay among diagnostic scales, sliding window size, and sliding stride. Furthermore, our investigation reveals that the model attains its highest accuracy within the discussed range when utilizing a smaller sliding stride size and a longer sliding window length. This study could furnish valuable insights for constructing models for LOCA breach size estimation. [ABSTRACT FROM AUTHOR]

The failure of wellbore sealing will cause leakage of greenhouse gases, such as carbon dioxide and methane, which will harm oil and gas recovery and environmental safety. Cementing is an important part of wellbore sealing. Only good cementing can keep the wellbore seal for a long time and improve the well life. In this study, we considered the construction of a horizontal shale oil well in eastern China as the background and analysed the rheological properties of the annulus fluid. We developed a displacement motion model and a calculation model for the annulus dynamic equivalent circulation density, and numerical simulations were used to study the impact of the dosage and injection sequence of the pad fluid on the displacement efficiency and annulus dynamic equivalent circulation density. The results show that when the pad fluid is composed completely of flushing fluid, the displacement performance is better than that of the spacer. By increasing the dosage of the flushing fluid from 0.3 times the annular volume to 1.0 times, the displacement efficiency can be increased by 3.3%, and the retention of the drilling fluid is also reduced by 3.6%. However, it can lead to a significant reduction in the annulus dynamic equivalent circulation density and increase in the risk of leakage. After adding the spacer, the structure of the flushing fluid–spacer provides the optimal injection sequence. Considering the application status in the field example well, it was shown that it can not only ensure the safety of cementing operations, but also improve the displacement efficiency. The results of this study have important theoretical significance and application value and can provide guidance for the optimisation design of the engineering scheme. [ABSTRACT FROM AUTHOR]

Fault diagnosis plays an important role in complex and safety-critical systems such as nuclear power plants (NPPs). With the development of artificial intelligence (AI), extensive research has been carried out for fast and efficient fault diagnosis based on intelligent methods. This paper presents a review of various AI-based system-level fault diagnosis methods for NPPs. We first discuss the development history of AI. Based on this exposition, AI-based fault diagnosis techniques are classified into knowledge-driven and data-driven approaches. For knowledge-driven methods, we discuss both the early if–then-based fault diagnosis techniques and the current new theory-based ones. The principles, application, and comparative analysis of the representative methods are systematically described. For data-driven strategies, we discuss single-algorithm-based techniques such as ANN, SVM, PCA, DT, and clustering, as well as hybrid techniques that combine algorithms together. The advantages and disadvantages of both knowledge-driven and data-driven methods are compared, illustrating the tendency to combine the two approaches. Finally, we provide some possible future research directions and suggestions. [ABSTRACT FROM AUTHOR]