Use, Concerns, and Perspectives on AI in Health Care Among French Health Professionals and Students: Web-Based Cross-Sectional Survey.

Electrical work is a crucial foundation for ensuring the stable operation of the power system, directly impacting the safety of workers and national property. Currently, the factors threatening the safety of electrical workers are complex, encompassing multiple dimensions such as personnel operation, equipment status, site environment, and management mechanisms, posing significant challenges to the accuracy of risk identification and the effectiveness of prevention and control measures. Accurately identifying and deeply analyzing various risk factors affecting electrical work safety would provide more comprehensive protection for workers’ personal safety. However, existing studies mainly focus on the macro-level safety management and inherent risks of power systems. [–] Sadeghi-Yarandi et al. developed a novel Electrical Industry Safety Risk Index for the electricity power distribution industry based on fuzzy analytic hierarchy process and conducted comparative research []; Lee et al. proposed a safety autonomous platform for data-driven risk management based on an on-site AI engine in the electric power industry, and implemented the platform architecture and performed performance verification []; Efthymios Karangelos and Louis Wehenkel put forward an integrated cyber-physical risk management framework for electric power transmission grid security and carried out relevant optimization analysis []; Acakpovi and Dzamikumah adopted questionnaires and in-depth interviews to investigate the compliance of occupational health and safety management systems in a hydroelectric power plant in Ghana and sorted out safety influencing factors []; Shao Guangzheng constructed a scenario analysis model for large-scale blackout events, analyzed the evolution process of events from multiple dimensions and verified the model with field drills []; Sroka and Złotecka assessed the risk of large blackout failures and vulnerability of power systems using the bow tie model based on historical statistical data, and analyzed the impact of power reserve deficit []; Alhelou et al. presented a comprehensive survey on power system blackouts and cascading events over the past decade, summarized accident causes, analysis methods and existing problems, and proposed future research directions []. Wang et al. conducted a series of studies on risk and reliability assessment of overhead contact lines (OCLs). They first developed a data-driven lightning-related failure risk prediction method by integrating a Bayesian network with a spatiotemporal fragility model to characterize the relationship between lightning strikes and OCL failures and support predictive maintenance decisions []. Building upon this work, a dynamic Bayesian network-based predictive probabilistic risk analytics framework was proposed to identify critical risk factors and model the dynamic propagation of weather-driven risks, considering system failures, economic losses, and social impacts simultaneously []. To further enhance reliability assessment, the authors established a data-driven time-dependent reliability prediction framework that incorporates lightning strikes, imperfect maintenance, and common-cause failures, enabling dynamic reliability evaluation under evolving operational conditions []. More recently, an uncertainty-aware trustworthy weather-driven failure risk predictor based on probabilistic deep multitask learning and deep Gaussian processes was developed to simultaneously predict multiple weather-induced failures while quantifying epistemic and aleatory uncertainties, thereby improving the reliability and interpretability of risk prediction results []. From the above review, detailed research targeting workers’ personal safety and potential safety hazards in actual power operation scenarios remains insufficient. Few studies have conducted in-depth exploration of on-site safety issues faced by power operation personnel. Therefore, given that targeted studies on power workers’ safety and operational risk assessment are still inadequate, this paper centers on power personnel safety and develops a dedicated risk assessment method for power operation scenarios. This method innovatively combines scenario construction theories, Bayesian network (BN), Job Safety Analysis (JSA) and Grey Correlation Analysis (GCA) [,–]. It integrates qualitative analysis with quantitative calculation, as well as subjective judgment with objective evaluation, which makes it different from conventional assessment methods. On this basis, we establish typical live-line work scenarios and conduct quantitative calculations on risk factors at key links, so as to fully validate the feasibility of the newly developed method. illustrates the detailed procedures of power operation work. Power work advances through a sequence of stages: monthly, weekly, and daily planning phases; pre-operation preparation and site entry; the operational phase, consisting of various sub-phases; and ultimately, compl