In response to the visualization requirements of the models and analysis results necessary for the development of simulation analysis software for spiral bevel gear transmission systems, based on the structural characteristics of the bevel gear transmission system, the topological structure of the transmission system and the complete expression of the interrelationships among components were achieved by applying graph theory and object-oriented data structures.

The generation method of regularized point sets on the geometric surfaces of key heterogeneous components in the transmission system was investigated, and the precise construction and rapid assembly of the geometric models of bevel gears, transmission shafts, and bearings were accomplished using the open-source 3D computer graphics tool VTK. On this basis, the mapping between the geometric model of the transmission system and the mechanical model of loading contact analysis was established, and the visualization methods for the analysis results such as system deformation under loading and tooth surface meshing state were studied. Finally, the visualization effects of modeling and simulation analysis results of the bevel gear transmission system were verified through examples.

Research has shown that the comprehensive application of graph theory and object-oriented data structures can achieve a complete expression of the topological configuration and geometric correlation properties of bevel gear transmission systems. By applying the parameter expression modeling, sweep modeling, and triangulation modeling methods of the VTK library, accurate modeling of heterogeneous components can be achieved. Based on this, a mapping between the system geometry model and the mechanical analysis model can be established to complete the loading contact analysis of the bevel gear transmission system, and visualize the analysis results. The above research results provide technical support for the development of modeling and simulation analysis software for bevel gear transmission systems.

A health state assessment method combining deep residual shrinkage network (DRSN) and adversarial domain adaptation (ADA) was proposed to address the problems of vibration signal noise interference and inconsistent data distribution under different working conditions in the remaining useful life (RUL) prediction of rolling bearings, so as to improve the accuracy and generalization ability of RUL prediction.

Firstly, a health state assessment model combining deep residual shrinkage network and adversarial domain adaptation was constructed. The performance of DRSN in avoiding noise in vibration signals and adaptively extracting bearing degradation features was utilized to build the health indicator curve. Then, ADA was used to align the distribution of health indicators between the test set and the training set, so as to eliminate the difference in data distribution under different working conditions. Finally, the health indicators output by the DRSN-ADA model were input into the convolutional long short-term memory (ConvLSTM) network model, and the accurate RUL prediction of rolling bearings was realized.

In the XJTU-SY dataset and engineering tests, the health indicators constructed by DRSN-ADA are superior to the comparison methods in monotonicity, robustness and correlation, with their mean values reaching 0.61, 0.97 and 0.98 respectively. The mean values of mean squared error (MSE) and mean absolute error (MAE) of the RUL prediction results are 2.52% and 2.19% respectively, and the average score is 0.86, which is significantly better than the DRN, principal component analysis and root mean square (RMS) methods. These results verify the effectiveness of the proposed method in noise suppression and cross-working condition prediction.