Safety digital control system (DCS) cabinet, as a carrier for the electronic devices, plays a significant role in ensuring the normal operation of the nuclear power plant. In this work, a design idea of impact resista...
详细信息
system Availability, Rejection rate and Malfunction rate are vital technical indicators for safety class DCS when evaluating the reliability of the control system to meet technical requirements. This trend has attract...
详细信息
The radiation generated by nuclear reaction is harmful to human body and equipment,thus the radiation shielding materials that employ the shielding ability from neutron and gamma rays are the best candidates according...
详细信息
The radiation generated by nuclear reaction is harmful to human body and equipment,thus the radiation shielding materials that employ the shielding ability from neutron and gamma rays are the best candidates according to application situations and radiation *** this paper,the researches of metal-based neutron and gamma rays or multiple purpose shielding materials are systematically summarized,and the respective and principal problems of these materials with respect to shielding effectiveness and other performances,such as corrosion,mechanical properties,manufacture,etc.,are ***,the prospect of shielding materials is outlined,which suggests that the development of highly efficient and multiply functional radiation shielding materials with good environmental compatibility is one of the future development trends.
The lead-bismuth eutectic alloy (LBE) is a candidate coolant for the generation IV liquid metal reactors, and the plate-type fuel assemblies are widely used in the small or research reactors. However, the turbulent he...
详细信息
Prognostics and Health Management (PHM) is currently the mainstream solution for the condition monitoring and maintenance of industrial systems. In PHM, the system condition is monitored by monitoring the operational ...
详细信息
ISBN:
(数字)9798350354010
ISBN:
(纸本)9798350354027
Prognostics and Health Management (PHM) is currently the mainstream solution for the condition monitoring and maintenance of industrial systems. In PHM, the system condition is monitored by monitoring the operational status parameters of the system to diagnose equipment faults, predict the remaining useful life, etc. Utilizing sequential operational status parameters to complete prediction and classification tasks is usually modeled as a time series processing task. Therefore, a high-performance time series prediction model is crucial for PHM. This paper focuses on the use of time series prediction models to achieve the prediction of key state parameters of the nuclear power system. However, there are still some challenges when directly applying existing time series prediction models to industrial systems. First, obtaining operational data on the nuclear power system is relatively difficult, resulting in a small amount of training data, which causes many models to face the risk of insufficient training or overfitting. Second, most of the existing time series prediction models are composed of high- and low-frequency decoupling modules, while the operational data of nuclear power systems often have fewer high-frequency components, making it difficult for many existing SOTA models to achieve good results. In order to address these challenges, we have developed a Transformer-based time series prediction model with contrastive learning for monitoring the status of nuclear power systems. We evaluated the new model on three nuclear power simulation datasets and four power transformer datasets. The experimental results show that the new model's performance is superior to baseline models. We also proved the effectiveness of our improvement through ablation experiments.
Matrix multiplication (MM) is pivotal in fields from deep learning to scientific computing, driving the quest for improved computational efficiency. Accelerating MM encompasses strategies like complexity reduction, pa...
ISBN:
(纸本)9798331314385
Matrix multiplication (MM) is pivotal in fields from deep learning to scientific computing, driving the quest for improved computational efficiency. Accelerating MM encompasses strategies like complexity reduction, parallel and distributed computing, hardware acceleration, and approximate computing techniques, namely AMM algorithms. Amidst growing concerns over the resource demands of large language models (LLMs), AMM has garnered renewed focus. However, understanding the nuances that govern AMM's effectiveness remains incomplete. This study delves into AMM by examining algorithmic strategies, operational specifics, dataset characteristics, and their application in real-world tasks. Through comprehensive testing across diverse datasets and scenarios, we analyze how these factors affect AMM's performance, uncovering that the selection of AMM approaches significantly influences the balance between efficiency and accuracy, with factors like memory access playing a pivotal role. Additionally, dataset attributes are shown to be vital for the success of AMM in applications. Our results advocate for tailored algorithmic approaches and careful strategy selection to enhance AMM's effectiveness. To aid in the practical application and ongoing research of AMM, we introduce LibAMM —a toolkit offering a wide range of AMM algorithms, benchmarks, and tools for experiment management. LibAMM aims to facilitate research and application in AMM, guiding future developments towards more adaptive and context-aware computational solutions.
MTS (maintenance and test software), as an important human-computer interactive tool in DCS of nuclear power plant, plays a crucial role in configuration and management of the engineering applied data, engineering des...
详细信息
ARSAC is a reactorsystem analysis program independently developed in China. In this paper, a quench analysis module is developed based on ARSAC program. The boiling curve suitable for quench process is established an...
详细信息
This paper studies the influence of hybrid disorders on acoustic transmission characteristic in pipeline with periodic elastic HRs. Band gap structures (BGs) for infinite period are investigated by transfer matrix met...
详细信息
Melting and freezing model plays a crucial role in safety analysis for liquid metal fast reactors under core disruptive accidents. Thus, it’s necessary to establish suitable models for accurate prediction of molten m...
详细信息
暂无评论