Characteristics analysis and situation prediction of production safety accidents in non-coal mining

Safety accident prediction is the prerequisite for accident prevention and the basis for safety management decision-making. To realize the accurate prediction of non-coal mine safety production situation, the evolution characteristics of non-coal mine safety production situation are analyzed from two perspectives of system characteristics and temporal characteristics, and the complexity of non-coal mine safety production system is elaborated from several perspectives, and its predictability is revealed. For the non-stationary non-coal mine safety production situation, CEEMDAN is used to progressively refine the non-coal mine safety production situation into several high-frequency trend components and low-frequency disturbance components by telescoping translation operations. Aiming at the correlation between the multi-modal components, the multi-modal components are reconstructed according to the distribution characteristics of the fuzzy entropy of the multi-modal components, and the detail, random, trend and residual components are obtained to characterize the composition of the non-coal mine safety production situation. Finally, by assuming the existence of unobservable hidden state sequences and their corresponding observable sequences, the relationship between the hidden states, and the observed states individually and between them is studied, and the HMM prediction model is constructed to achieve accurate prediction of the reconstructed multi-modal components. The results show that the accuracy evaluation indexes such as MAE, MSE and RMSE of the multimodal HMM prediction model for non-coal mine safety production situation prediction is better than those of the comparison model, and the prediction effect under different prediction steps is better than that of the comparison model, and the prediction accuracy is higher. The research is helpful for safety decision-makers to accurately grasp the changes in mine safety production and make correct safety decisions, which can provide theoretical guidance for the safety planning of noncoal mines.

Automated summary

Safety accident prediction is crucial for accident prevention and safety management decision-making. This study analyzes the evolution characteristics and complexity of non-coal mine safety production situation, and proposes a multi-modal HMM prediction model using the CEEMDAN method. The results demonstrate that the model achieves higher accuracy in predicting the non-coal mine safety production situation. This research provides valuable insights for decision-makers to accurately understand the changes in mine safety production and make informed decisions.