Research on human error analysis of high-speed railway traffic dispatchers based on an improved weighted BN-CREAM model

High-speed railway traffic dispatchers occupy a pivotal role in ensuring the safe and efficient operation of high-speed railway systems. Errors committed by these dispatchers can precipitate severe operational consequences, underscoring the necessity for robust methodologies to mitigate human-induced failures. This study introduces an advanced approach for analyzing human errors among high-speed railway traffic dispatchers, leveraging an enhanced weighted Bayesian Network (BN) integrated with the Cognitive Reliability and Error Analysis Method (CREAM), termed the improved weighted BN-CREAM. The proposed methodology synthesizes the strengths of the CREAM model and Bayesian Networks, augmented by an innovative weighted algorithm, to construct a comprehensive human error analysis framework tailored for high-speed railway traffic dispatchers. The efficacy of the model is empirically validated through a detailed case study, demonstrating its capability to identify and quantify human error probabilities with high precision. Based on the findings, targeted preventive measures are proposed to enhance the reliability and safety of high-speed railway operations. This research contributes to the field by providing a systematic and quantifiable tool for human error analysis, thereby supporting the development of more resilient railway dispatching systems.