In real industrial applications, intelligent methods are recently emerging for remaining useful life (RUL) prediction. However, their development is hindered by two obstacles. First, it is hard for an ordinary edge client to achieve RUL prediction owing to its weak computing capacity and limited data volume. Second, as for all edge clients, it is unrealistic to share data with each other due to the potential conflict of interests. Therefore, a federated learning-based RUL prediction method namely FedRUL is proposed to solve these problems. In this method, multiple edge clients and a cloud server are applied to train a global encoder and an RUL predictor without data sharing. Each client includes a convolutional autoencoder (CAE) comprised of an encoder and a decoder while the server includes a same encoder and an RUL predictor. During each epoch, CAEs are trained in all clients through their corresponding local training datasets first. Then, all local encoders are uploaded to the server and aggregated to a global encoder through assigning weights for all clients according to their performance on a validation dataset in the server. At last, this global encoder is sent back to all clients for extracting low-level features from their datasets and uploading these features to train the RUL predictor for each client one by one. Two experiments suggest FedRUL offers a promising solution on confidential decentralized learning for RUL prediction.

Digital twin is an important technology for grasping states of mechanical systems in real time. However, there are few studies on how to establish life-cycle digital twin models of bearings. In order to accurately estimate the condition of bearings, a digital twin model of bearing life cycle (BLDT) is proposed to achieve equivalent information on the virtual entity (VE) model and physical entity (PE) model. First, a dynamic model of rolling bearings and defect evolution model are established to simulate the dynamic response of the bearing performance degradation process. Then, the physical characteristics and degradation information of the PE model are exchanged with the VE model to evaluate the time-varying defect size and the equivalent comprehensive stiffness. The evolution law of the life-cycle is obtained through a neural network. Finally, the network parameters are introduced into the VE model to obtain dynamic response results of the life-cycle bearing dynamic model of other datasets under the same working conditions. By comparing the obtained digital twin results with experiment signals in the time and frequency domains, the accuracy and effectiveness of the BLDT model are verified.

The main gearbox is very important for the operation safety of helicopters, and the oil temperature reflects the health degree of the gearbox; therefore establishing an accurate oil temperature forecasting model is an important step for reliable fault detection. Firstly, in order to achieve accurate gearbox oil temperature forecasting, an improved deep deterministic policy gradient algorithm with a CNN–LSTM basic learner is proposed, which can excavate the complex relationship between oil temperature and working condition. Secondly, a reward incentive function is designed to accelerate the training time costs and to stabilize the model. Further, a variable variance exploration strategy is proposed to enable the agents of the model to fully explore the state space in the early training stage and to gradually converge in the training later stage. Thirdly, a multi-critics network structure is adopted to solve the problem of inaccurate Q-value estimation, which is the key to improving the prediction accuracy of the model. Finally, KDE is introduced to determine the fault threshold to judge whether the residual error is abnormal after EWMA processing. The experimental results show that the proposed model achieves higher prediction accuracy and shorter fault detection time costs.