Prediction of remaining useful life using deep learning models with regularization

Nowadays the use of modern technologies leads to an increase in the complexity of equipment. Failures of equipment lead to enterprises shutdowns or breakdowns not at enterprises. In this regard, there is a need to predict the remaining useful life of equipment with great accuracy in order to replace its parts at a time close to the time of its failures. This increase safety and reliability and reducing maintenance costs. Predictive maintenance of equipment is replacing corrective and preventive maintenance. In this study to improve prediction accuracy of remaining useful life of equipment it is proposed deep learning models using convolutional and long short-term memory neural networks. To solve the problem of overfitting of the neural networks during the training process, the regularization entered into their structures. Experimental results on real data show that the proposed methods can achieve higher stability and accuracy, which are useful for prediction of remaining useful life of aero engines and have high efficiency.