Longwall face roof disaster prediction algorithm based on data model driving

Abstract Hydraulic support is the primary equipment used for surrounding rock control at fully mechanized mining faces. The load, location, and attitude of hydraulic are important sets basis data to predict roof disasters. This paper summarized analyzed status coal mine safety accidents influencing factors work also proposed monitoring characteristic parameters disasters based on posture-load changes, such as location posture. feature decomposition method additive model was with load in Yanghuopan effectively extract trend, cycle period, residuals, which provided period weighting characteristics longwall face. autoregressive, long-short term memory, vector regression algorithms were analyze realize single-point predictions. seasonal autoregressive integrated moving average (SARIMA) (ARIMA) models adopted support. SARIMA shown be better than ARIMA predictions one cycle, but prediction effect these two over a fracture poor. Therefore, we multiple cutting template library. constructed technical framework disaster intelligent platform this perform early warnings posture information from