RESUMEN
Dynamic processes in various fields exhibit risk coupling phenomena, but existing risk analysis studies tend to ignore the risk coupling effects of dynamic scenarios. Considering the principles of digitization, objective quantification, and the full process that should be adopted in the risk coupling analysis, an integrated risk coupling analysis framework is proposed. Specifically, the weighted Eclat algorithm is used to mine the risk association rules, then the key risk factors are extracted by social network analysis, and the stochastic Petri net is used to complete the construction, simulation, and evolution of accident scenarios. This universal framework can analyze the risk phenomena of accident scenario evolution in a process-oriented manner and decouple risks based on key risk factors and disconnect the chain of the accident scenario evolution process. Finally, the proposed framework is applied to the coupled analysis of fire risk in Chinese urban communities to verify its feasibility and scientific validity.
RESUMEN
To describe the safety rules of various industrial process data and explore the characteristics of unsafe behaviour, the association rules of unsafe behaviour based on pan-scene were proposed in this study. First, based on the scene data theory, unsafe behaviour was described by eight dimensions (time, location, behavioural individual, unsafe action, behavioural attribute, behavioural trace, professional category and risk level) to achieve scene data description and structural transformation. Second, the Apriori algorithm was used to explore the distribution rules of unsafe behaviour dimensions and the interaction between different dimensions from two perspectives: single-dimensional statistical analysis and multidimensional association rule mining. Finally, through SPSS Modeler software, an empirical analysis of pan-scene data for subway construction was conducted, and the association rules between type of work, construction stage, working time and unsafe action were identified. Some strong association rules were produced by the association analysis. For example, during the 13:00-17:00 of the excavation floor stage, the most frequent unsafe action of machine operators is the irregular binding of lifting objects. This result could explain why some unsafe actions are prone to occur in different construction stages and working times for workers of different types, which can be controlled and managed in a targeted manner, thus reducing the possibility of accidents.