With the rapid development of deep learning (DL) techniques, data-driven models have been increasingly used in remaining useful life (RUL) prediction, in which convolution neural network (CNN)-based RUL prognostics models have received special attention. However, there are still two main issues that need to be addressed: 1) traditional CNN is not suitable to extract the time-sequence characteristics from the long-term historical signals and 2) the receptive field range of convolution operation is fixed, thus only learning the feature information at a specific scale, which is insufficient for complex feature extraction. To address these two issues, a multiscale temporal convolutional network (MsTCN) that has powerful time-sequence characteristics is proposed for RUL prediction in this article. The MsTCN adopts the temporal convolutional network (TCN) framework, which is good at extracting time-sequence information. Based on this, a new multiscale dilated causal convolution residual block (MsDCCRB) is developed to constitute the RUL prognostics model, where multiple dilated convolutions (DCs) are based on different dilation factors that are put on each layer in parallel. Furthermore, the squeeze-and-excitation (SE) unit is embedded into the MsDCCRB to adaptively recalibrate the sequence feature responses and enhance the representation learning ability. Through stacking multiple MsDCCRBs, the historical condition monitoring data can be fed directly into the proposed model to realize the high-level representations of RUL estimation. Finally, the proposed approach is validated with the accelerated whole-life degradation dataset of rolling element bearings (REBs). The experimental results exhibit that the proposed MsTCN achieves a higher RUL prediction accuracy, which is superior to some state-of-the-art data-driven prognostics methods.

With the increasing speed of trains, the lateral vibration of the car body becomes violent and the ride comfort becomes worse. This study adopts semi-active control techniques to reduce the excessive vibration of the car body. A novel control strategy and its extended control strategy, Displacement-Velocity (DV) and Sky-hook (SH)-DV, are presented and applied to the magnetorheological (MR) dampers. The semi-active suspension system of MR dampers is integrated into a quarter model and a 17 degrees of freedom (DOF) train model instead of the passive suspension, respectively. The theoretical simulations are performed and compared with the SH control strategy. Furthermore, the hardware in the loop (HIL) test based on MR dampers is built and experimental research is carried out. In the theoretical simulations and experimental research, multiple service conditions are adopted, and the dynamic performance of highspeed trains is evaluated. Theoretical and experimental results indicate that the new control strategies can significantly suppress the vibration of the car body, and they can ensure the safety and stability of the high-speed train. Moreover, their control and robust performance (about time delay) are better than that of the SH, especially the DV. Therefore, this paper provides an additional choice for the methods of vibration control.

A sensible maintenance strategy must take into account the remaining usable life (RUL) estimation to maximize equipment utilization and avoid costly unexpected breakdowns. In view of some inherent drawbacks of traditional CNN and LSTM-based RUL prognostics models, a novel combination model of the ConvLSTM and the Transformer, which is based on the idea of “Extracting spatiotemporal features and applying them to RUL prediction”, is proposed for RUL prediction. The ConvLSTM network can directly extract low-dimensional spatiotemporal features from long-time degradation signals. The Transformer, based entirely on attention mechanisms, can deeply explore the mapping law between deep-level nonlinear spatiotemporal feature information and equipment service performance degradation. The proposed approach is validated with the whole-life degradation dataset of bearings from the PHM 2012 Challenge dataset and the XJTU-SY public dataset. The detailed comparative analysis shows that the proposed method has higher RUL prediction accuracy and outstanding comprehensive prediction performance.