摘要:Coal mine belt conveyor can guarantee the coal mine production stable and efficient. On how to effectively predict abnormal accident occurrence time, this paper puts forward a method to predict the abnormal accident occurrence time based on Hidden Markov Model and Hidden Semi-Markov Model. Large amount of time series is collected through belt conveyor protection sensors. The corresponding HMM or HSMM model could be built after feature extraction. At last the accident occurrence time is able to be predicted based on the HMM model or the HSMM model. Experiments carried on the actual production data set illustrate that HMM and HSMM model can effectively predict specific event occurrence time.