Data imbalance and large data probability distribution discrepancies are major factors that reduce the accuracy of remaining useful life (RUL) prediction of high-reliability rotating machinery. In feature extraction, most deep transfer learning models consider the overall features but rarely attend to the local target features that are useful for RUL prediction; insufficient attention paid to local features reduces the accuracy and reliability of prediction. By considering the contribution of input data to the modeling output, a deep learning model that incorporates the attention mechanism in feature selection and extraction is proposed in our work; an unsupervised clustering method for classification of rotating machinery performance state evolution is put forward, and a similarity function is used to calculate the expected attention of input data to build an input data extraction attention module; the module is then fused with a gated recurrent unit (GRU), a variant of a recurrent neural network, to construct an attention-GRU model that combines prediction calculation and weight calculation for RUL prediction. Tests on public datasets show that the attention-GRU model outperforms traditional GRU and LSTM in RUL prediction, achieves less prediction error, and improves the performance and stability of the model.

The structured light projection (SLP) method occupies a crucial position in three-dimensional (3D) imaging technology. Different working wavelengths of structured light can be employed depending on the situation. However, there are few structured lights that can be modulated based on wavelength at present. Therefore, we have comprehensively investigated and designed a Dammann grating (DG) based on metasurface, which can be controlled through multi-beam interference (MBI) to achieve a change of the working wavelength. In this work, we can convert the straight waveguide to the helical waveguide by fine-tuning the related parameters of the incident lights and generate 5 × 5 diffraction spot arrays in the wavelength range of 480–510 nm and 950–1020 nm, respectively. Furthermore, the metasurfaces exhibit good performance. For example, their spread angles can be up to 44° × 44° and they can reach a conversion efficiency of over ≥50% while maintaining a contrast ratio of roughly 40%. Compared with traditional structured light, it can be used in different working wavelengths and has a broader application range in 3D sensing systems.

Given the challenges of rotating equipment fault diagnosis under variable working conditions, including the unbalanced transmission of information during feature extraction, difficulty in capturing both global and local features, and limited generalization across different working conditions, a Chebyshev graph convolutional neural network (ChebyNet) method is proposed to address these issues. First, a symmetry processing mechanism is incorporated into the framework of the ChebyNet to balance the transfer of information between nodes in the graph to ensure the fair and efficient integration of information. Secondly, the wide-area feature extraction capabilities of the ChebyNet and the adaptive nodes of the graph attention network (GAT) are integrated to achieve the comprehensive mining of fault characteristics and accurate characterization of complex interactive relationships. Finally, the node reconstruction task of self-supervised learning and collaborative node classification tasks are used to enhance the model’s ability to capture complex changes in variable working conditions data, significantly improving the generalizability of working conditions. In comparative and cross-validation experiments, the proposed method achieved an average diagnostic accuracy of 99.72%, representing an improvement of up to 17.96% compared to other graph neural network (GNN) models. It significantly enhances the accuracy, stability, and generalization of fault diagnosis. Ablation experiments further validate the effectiveness of the proposed method in improving fault diagnosis performance under variable working conditions.

The Stream of Variation (SoV) model and control chart are combined to study the fault diagnosis method of flexible materials R2R manufacturing system. Based on the analysis of the correlation between the fault source and product quality in the manufacturing process and also the statistical distribution rule of the processing quality characteristic vector Li and the fault source fi, SoV model under controlled or uncontrolled states and the mathematical model of the probability distribution of the statistic Ti,m2 of the quality characteristic variable Li are deduced. And the calculation equation of the centerline, the upper limit, and the lower limit of the control chart are deduced. The experimental results show that, under controlled or uncontrolled condition, when the program runs to 500 steps, the Average Run Length (ARL) of the performance parameters tends to be stable; and when program reaches 1000 steps, the actual ARL value is almost the same as the theoretical value. The fault diagnosis experiment shows that, under the condition when the fault source is strongly correlated or the fault source correlation coefficient is the same, using the control chart established in this paper can simply and quickly determine the fault location in the system.

The rotating parts of large and complex equipment are key components that ensure the normal operation of the equipment. Accurate fault diagnosis is crucial for the safe operation of these systems. To simultaneously extract both local and global valuable fault feature information from key components of complex equipment, this study proposes a fault diagnosis network model, named MultiDilatedFormer, which is based on the fusion of transformer and multi-head dilated convolution. The newly designed multi-head dilated convolution module is sequentially integrated into the transformer-encoder architecture, constructing a feature extraction module where the complementary advantages of both components enhance overall performance. Firstly, the sample is expanded into a two-dimensional feature map and then input into the newly designed feature extraction module. Finally, the diagnostic output is performed by the designed patch feature fusion module and classifier module. Additionally, interpretability research is conducted on the proposed model, aiming to understand the decision-making mechanism of the model through visual analysis of the entire decision process. The experimental results on three different datasets indicate that the proposed model achieved high accuracy in fault diagnosis with relatively short data windows. The highest accuracy reached 97.95%, which was up to 10.97% higher than other models. Furthermore, the feasibility of the model is also verified in the actual dataset of the rotating parts of the injection molding machine. The excellent performance of the model on different datasets demonstrates its effectiveness in extracting comprehensive fault feature information and also proves its great potential in practical industrial applications.