The equipment monitoring of the merging unit relies on on-site staff records， practical experience and preset alarm threshold， and the lack of analysis and mining of the system monitoring data makes it impossible to realize the device state prediction. In view of this， according to the timing characteristics of the level data of the monitoring merge unit， a combined model of the traditional timing model of autoregressive integrated moving average （ARIMA） and long short-term memory（LSTM） is constructed and optimized by using shuffled frog leaping algorithm（SFLA）. The optimized model is applied to the level data prediction analysis of the combined unit laser monitoring. The comparison of the ARIMA-LSTM optimized combination model with the single model verifies that the former has higher accuracy than the latter. Further comparison experimental results show that the combined model is superior to the other combined models after the SFLA algorithm optimization， which can better mine the hidden information and trend in the data， improving the accuracy of time series data prediction and the efficiency of fault troubleshooting. By comparing the combined ARIMA-SVM model and the proposed ARIMA-LSTM model， experimental results show that the proposed ARIMA-LSTM model is superior to the ARIMA-SVM model， and it can better analyze and grasp the device state information， and realize the level data prediction of the merging unit equipment.