As the key link to realize the function drive of mechanical equipment and its control system, the engine needs to have good operation and fault diagnosis and maintenance capability. Based on digital twin technology and long and short term memory recurrent neural network, the article proposes an engine fatigue monitoring method and life prediction model. The method uses digital twin technology to establish an engine control system simulation model to obtain the engine state parameters and fatigue value life related data set according to the engine composition structure and working principle; the obtained data set is trained by LSTM neural network to determine the engine life prediction model, and the real-time data of DT model is used as the test data set of LSTM network to complete the testing work, so as to achieve the prediction of the remaining engine life results. Finally, we select the Turbofan Engine Degradation dataset and compare and analyze the prediction results of BP and RNN networks through simulation results to prove the effectiveness of the proposed method.