Xueping Song

Modern aero-engine bearings operate under demanding rotational and thermal conditions, where inaccurate prediction of thermal behavior and an incomplete understanding of heat-transfer mechanisms may increase the risk of thermal failure. This study develops a thermal–fluid–solid coupling method to investigate heat generation and heat transfer in aero-engine bearings. The frictional power consumption analysis evaluates rolling friction, sliding friction, seal friction, and oil-churning power consumption. In the conjugate thermal–fluid calculation, only the contact-related rolling and sliding friction contributions are transferred to the raceway surfaces through the prescribed heat-flux boundary conditions. Thermo-elastohydrodynamic lubrication (TEHL) theory is introduced to describe the physical relationships among bearing contact conditions, lubricant-film behavior, and thermal effects, rather than as an independently solved full-field TEHL model. A hybrid heat-flux density distribution model combining a Gaussian distribution in the contact zone with exponential decay in the oil-film zone is proposed. The prescribed raceway thermal loads are incorporated into a three-dimensional conjugate thermal–fluid model to investigate the bearing temperature and lubricant flow responses. With prescribed reference heat-flux density amplitudes for the inner and outer raceways, the model describes their distinct spatial distributions, with stronger local concentration on the inner raceway. Numerical simulations and bearing temperature-rise tests are conducted to assess the thermal response predicted by the model. The prescribed inner- and outer-raceway thermal loads produce distinct local thermal responses, with stronger local heat-flux concentration on the inner raceway and different heat-transfer characteristics in the surrounding lubricant flow field. The numerical results show that the thermal and dynamic responses vary non-monotonically with oil supply rate, indicating a strong dependence on lubricant distribution and local heat-transfer conditions. Within the investigated conditions, the principal stiffness and damping reach their maximum values at an oil supply rate of 0.6 L/min. The proposed framework captures the main thermal response trends of the bearing and provides a theoretical basis for lubrication parameter optimization and bearing thermal management.

A key challenge in federated remaining useful life (RUL) prediction arises from the entanglement between degradation dynamics and client-specific temporal scaling under heterogeneous operating conditions. In such settings, standard federated aggregation mixes trajectories with different degradation rates, leading to systematic bias in the learned latent evolution and consequently distorted RUL estimates. We observe that this issue is fundamentally caused by the lack of identifiability between shared degradation evolution and client-dependent temporal rate variations in conventional federated optimisation. To address this limitation, we propose FedMDR, a federated latent dynamics framework that explicitly separates the shared degradation field, client-specific temporal scaling, and condition-dependent drift within a unified continuous-time formulation. Its identifiability-aware design keeps degradation-rate information largely out of the shared representation during aggregation, while a rate-drift diagnostic down-weights unstable client updates. Across five seeds (mean ± 90% CI), FedMDR attained a C-index of 0.776 ± 0.011 and RMSE of 16.3 ± 0.8 cycles on C-MAPSS; on CALCE, it achieved a mean C-index of 0.789 ± 0.014 and Brier score of 0.133 ± 0.010 . Together, the results indicate strong predictive discrimination and reliable uncertainty estimates across mechanical and electrochemical degradation domains.

Due to the low stiffness characteristics, thin-walled parts are prone to force-induced deformation during the peripheral milling process, which severely restricts machining accuracy and efficiency. In existing studies, for curved thin-walled parts, the Finite Element Method (FEM) is usually adopted for deformation prediction. However, the traditional FEM usually requires a considerable amount of computing time, owing to the high model complexity and batch parameter evaluations. Therefore, this study proposes a method of constructing a surrogate model based on a small amount of FEM simulation data. Firstly, a peripheral milling cutting force model is established to obtain the instantaneous milling force. Secondly, a finite element model considering the material removal effect is constructed, and an iterative solution strategy is introduced to calculate the force-induced deformation. Finally, an Enhanced Latin Hypercube Sampling (ELHS) method is used to generate training samples, and the Elliptic Basis Function Neural Network (EBFNN) is selected as the surrogate model to establish a nonlinear mapping relationship between machining parameter combinations and force-induced deformation. This method enables rapid prediction of deformation at any machining position on curved thin-walled parts, reducing the computation time from hours to seconds while maintaining prediction accuracy.

To address the shortage of public datasets for customs X-ray images of contraband and the difficulties in deploying trained models in engineering applications, a method has been proposed that employs the Extract-Transform-Load (ETL) approach to create an X-ray dataset of contraband items. Initially, X-ray scatter image data is collected and cleaned. Using Kafka message queues and the Elasticsearch (ES) distributed search engine, the data is transmitted in real-time to cloud servers. Subsequently, contraband data is annotated using a combination of neural networks and manual methods to improve annotation efficiency and implemented mean hash algorithm for quick image retrieval. The method of integrating targets with backgrounds has enhanced the X-ray contraband image data, increasing the number of positive samples. Finally, an Airport Customs X-ray dataset (ACXray) compatible with customs business scenarios has been constructed, featuring an increased number of positive contraband samples. Experimental tests using three datasets to train the Mask Region-based Convolutional Neural Network (Mask R-CNN) algorithm and tested on 400 real customs images revealed that the recognition accuracy of algorithms trained with Security Inspection X-ray (SIXray) and Occluded Prohibited Items X-ray (OPIXray) decreased by 16.3% and 15.1%, respectively, while the ACXray dataset trained algorithm’s accuracy was almost unaffected. This indicates that the ACXray dataset-trained algorithm possesses strong generalization capabilities and is more suitable for customs detection scenarios.

Many security detectors do not have the ability to output individual luggage package images and are not compatible with deep learning algorithms. In this paper, a luggage package extraction of X-ray images based on the ES-MBD (Edge Sensitive Multi-channel Background Difference Algorithm) method is proposed, which is aiming at the problem that background difference binarization is insensitive to texture features and edge detection binarization is insensitive to smooth areas. In this method, X-ray luggage package images from complex original video images are used as a key target, the RGB three-channel background difference is calculated from the original X-ray image, the edge detection of the grayscale map is performed using the Sobel operator optimized by local gradient enhancement, and the morphological expansion process is performed on the combined results to obtain the complete wrapping target. The Suzuki algorithm is used to detect the outline of the binarized package image, match the package frame area and determine the key target. The ES-MBD method solves the problem of information loss in the traditional binarization method, and retains the information of insensitive regions while reducing noise. Through experimental comparison, the accuracy of ES-MBD binarization method reaches 97.3%, the recall rate reaches 96.5%, and ES-MBD method has obvious advantages in key target extraction of X-ray images.

Due to the advantages of high transmission accuracy and high impact resistance, cycloid-pin gear drives are widely used in precision machinery. In the actual manufacturing and use process, a suitable clearance must be left between the cycloid gear and the pin teeth to meet the requirements of assembly lubrication, so the cycloid gear needs to be modified. In order to improve the performance of the cycloid-pin gear drive, this paper proposes a multi-objective optimization modification method which takes into account the maximum transmission error of the cycloid drive on the basis of the compound modification. Firstly, a compound modification function is constructed based on the equations of the cycloid gear. Tooth contact analysis is carried out on the cycloid gear to obtain the equations for calculating the transmission error and return error of the cycloid pinion drive and to solve for the transmission error and return error of a single cycle with different modification coefficients. Then, a multi-objective optimization model is constructed, and the optimum coefficients are solved by genetic algorithm. By analyzing the forces on the cycloid gear under load, the range, the number and the contact force of meshing teeth are calculated for different modification methods. At the end, the cycloid gear is modeled and finite element analyzed after multi-objective optimization modification and compound modification according to the optimal modification coefficients. By finite element analysis, the correctness of the theoretical calculation of the contact force of the modified cycloid gear and the loading transmission error is solved. The contact forces and transmission error of the multi-objective optimization modification are less than the compound modification. The theoretical calculation and finite element analysis indicate that the cycloid profile with the multi-objective optimization modification is better than the profile with the compound modification.

Social network analysis has important research significance in sociology, business analysis, public security, and other fields. The traditional Louvain algorithm is a fast community detection algorithm with reliable results. The scale of complex networks is expanding larger all the time, and the efficiency of the Louvain algorithm will become lower. To improve the detection efficiency of large-scale networks, an improved Fast Louvain algorithm is proposed. The algorithm optimizes the iterative logic from the cyclic iteration to dynamic iteration, which speeds up the convergence speed and splits the local tree structure in the network. The split network is divided iteratively, then the tree structure is added to the partition results, and the results are optimized to reduce the computation. It has higher community aggregation, and the effect of community detection is improved. Through the experimental test of several groups of data, the Fast Louvain algorithm is superior to the traditional Louvain algorithm in partition effect and operation efficiency.

It is an important part of security inspection to carry out security and safety screening with X-ray scanners. Computer vision plays an important role in detection, recognition, and location analysis in intelligent manufacturing. The object detection algorithm is an important part of the intelligent X-ray machine. Existing threat object detection algorithms in X-ray images have low detection precision and are prone to missed and false detection. In order to increase the precision, a new improved Mask R-CNN algorithm is proposed in this paper. In the feature extraction network, an enhancement path is added to fuse the features of the lower layer into the higher layer, which reduces the loss of feature information. By adding an edge detection module, the training effect of the sample model can be improved without accurate labeling. The distance, overlap rate, and scale difference between objects and region proposals are solved using DIoU to improve the stability of the region proposal’s regression, thus improving the accuracy of object detection; SoftNMS algorithm is used to overcome the problem of missed detection when the objects to be detected overlap each other. The experimental results indicate that the mean Average Precision (mAP) of the improved algorithm is 9.32% higher than that of the Mask R-CNN algorithm, especially for knife and portable batteries, which are small in size, simple in shape, and easy to be mistakenly detected, and the Average Precision (AP) is increased by 13.41% and 15.92%, respectively. The results of the study have important implications for the practical application of threat object detection in X-ray images.