Systemic and dynamic risk analysis of drilling construction based on bayesian network and system dynamics model.

Drilling construction is a key means to obtain underground resources and information, and construction risk also directly affects the safety, economy and sustainability of engineering projects. Aiming at the limitations of traditional risk assessment methods in the dynamic and systematic aspects, this paper proposes a comprehensive analysis method combining Bayesian network (BN) and system dynamics (SD). First, through expert interviews and field investigations, an evaluation system consisting of 5 dimensions and 20 indicators was established, and the combination of entropy weight method and expert score was used to empower the system. Then the three-layer Bayesian network was constructed by GeNIe, and the system dynamics model with 5 feedback loops was established by Vensim-PLE to realize the static and dynamic coupling analysis of risk factors. The study found that equipment integrity (59%), geological conditions (55%) and operational skills (51%) were the leading risk factors. Finally, the model is applied to the actual scene, and the results are in agreement with the actual situation. This study provides a theoretical framework of probability prediction and process optimization for the systematic analysis of complex drilling construction, and provides a more comprehensive risk analysis for drilling safety under complex geological conditions.