Safety archetypes identification and behavior simulation for nuclear power plant operation human reliability improvement

Wu, Guanyin; Mao, Yuhe; He, Yifan; Lü, Yi; Fu, Shan

doi:10.1016/j.anucene.2022.109189

Cited by 3 publications

(1 citation statement)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wu, G. et al combined the theory of the Human Factors Analysis and Classification System (HFACS) framework, introduced the system dynamics method, and proposed a human factors reliability model. After practical analysis, the model can be used to assess the reliability of employee operations and provide support for management decisions [13]. Wang, W. et al proposed the basic concepts and functional positioning of intelligent remote terminal units (RTUs) and monitoring terminals, as well as the feasibility of utilizing the above concepts to achieve terminal monitoring in power stations.…”

Section: Introductionmentioning

confidence: 99%

Research on Electricity Operation Behaviour Recognition Strategy Combined with Intelligent Image Recognition and Its Key Technology

Feng,

Chen,

Zhou

et al. 2024

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

This paper builds a power operation target detection model based on the YOLOv4 algorithm in intelligent image recognition, and optimizes the YOLOv4 algorithm by combining with the loss function to improve the accuracy of power target operation detection. The kmeans++ algorithm was used to cluster the electric power operation behaviors to obtain a more accurate electric power operation behavior dataset. Three sets of tests were conducted after the model was constructed, targeting the behavioral set of electric power workers in a certain place and the behavior in VOC format, followed by the multi-target tracking effect test. The analysis based on the obtained data showed that the helmet placement detection confidence, fatigue detection confidence, smoking detection confidence, and fall detection confidence reached 0.97, 0.93, 0.89, and 0.93, respectively. The transmission speed got 53.58 fps, and the recall and precision of the multi-target tracking were also above 93%. The YOLOv4 detection model based on keans++ clustering algorithm can effectively detect and identify the variable power operation behavior images.

show abstract

Section: Introductionmentioning

confidence: 99%

Research on Electricity Operation Behaviour Recognition Strategy Combined with Intelligent Image Recognition and Its Key Technology

Feng,

Chen,

Zhou

et al. 2024

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

show abstract

Path to modeling dynamic performance shaping factors in nuclear power plants operation – A review

Xu,

Yang,

et al. 2023

Systems Engineering

View full text Add to dashboard Cite

The evolution of the mechanism of human behavior formation analysis has significantly influenced the development of human reliability analysis (HRA), which aims to calculate human error probability (HEP) with performance shaping factors (PSFs). This paper reviews the typical HRA methods in different generations, the role of PSFs, and their interrelation‐ships in human risk modeling, with the background of nuclear power plants (NPPs). In a retrospective of typical HRA methods, PSF plays a fundamental role in assessing human performance during task operation. However, the subjectivity in defining and evaluating PSFs often leads to a partial representation of human behavior characteristics and human risk evolution, resulting in the neglect of PSF inter‐relationships and conservative HEP estimation. Recent studies have emphasized employing simulation platforms to simulate the task process and obtain data relevant to PSFs that can enable the exploration of the mutual effects to support the calculation of HEP more accurately. Compared to certain previous methods involving over‐simplification and inappropriate assumptions resulting in inaccurate results, current HRA methods are prone to the construction of HEP models based on objective data acquisition and dynamic calculations with process models. This shift enables a better illustration of the intricate relationships among PSFs. Reflecting on the current trend of HRA methodology, this paper proposes a possible PSF quantification based on physiological measurement providing accessible and objective data. It improves the shortcomings in data scarcity and time‐invariance of HEP calculation, thus more accurately and realistically responds to the accumulation and fluctuation of human risks throughout a task.

show abstract

Deep Learning Model Based Behavioural Recognition Technology for Electricity Operators and Its Safety Guardianship Analysis

Ye,

Xu,

Zhu

et al. 2024

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

This study leverages the Openpose system to capture skeletal key points of electric power operators, simplifying network complexity by sharing convolutional layers during the ReLU activation phase. We introduce a graph convolutional network (GCN) to model these skeletal sequences, creating a spatio-temporal deep learning approach for behavior recognition. Tested on a relevant dataset, our Openpose-GCN network demonstrates stability with a training loss of 0.11 after 700 iterations, achieves over 90% accuracy in recognizing operator actions and behaviors, and maintains a recognition error below 0.003 for operations with varying risk levels. These findings underscore the potential of our approach to enhance electric power operation safety through real-time risk warning and control.

show abstract

Safety archetypes identification and behavior simulation for nuclear power plant operation human reliability improvement

Cited by 3 publications

References 47 publications

Research on Electricity Operation Behaviour Recognition Strategy Combined with Intelligent Image Recognition and Its Key Technology

Research on Electricity Operation Behaviour Recognition Strategy Combined with Intelligent Image Recognition and Its Key Technology

Path to modeling dynamic performance shaping factors in nuclear power plants operation – A review

Deep Learning Model Based Behavioural Recognition Technology for Electricity Operators and Its Safety Guardianship Analysis

Contact Info

Product

Resources

About