Digital twin-driven aero-engine intelligent predictive maintenance

Aero-engine is one of the most important components of an aircraft. The development of maintenance has undergone the transition from post-event maintenance and preventive maintenance to predictive maintenance, and the future development direction is precise maintenance, which aims to achieve the collaborative optimization goal of ensuring operational safety and reducing operating costs. To improve the effect of predictive engine maintenance, the aero-engine predictive maintenance framework driven by digital twin (DT) is studied, and the implicit digital twin (IDT) model is mined. The validity of the model is verified by the consistency evaluation of virtual and real data assets. Combining the data-driven with LSTM model of deep learning method and taking an aero-engine as an example can show that the method is effective. Experimental results show that when the data set used for model training is 80%, the model prediction has high accuracy, and the RMSE predicted by aero-engine RUL is 13.12, which is better than other experimental schemes.

Automated summary

The maintenance of aircraft engines has evolved towards predictive and precise maintenance, and the use of digital twin technology and deep learning methods can improve the effectiveness of predictive maintenance. Experimental results demonstrate that this method achieves high accuracy in model prediction.