Search

Extracting and transforming shape features has been an important research domain in wheel hub design. The study of wheel hub design based on shape semantics, brand planning, and structural optimization requires regression analysis by using shape features and the corresponding variables to guide wheel hub design through the correlation model. The practical role of feature transformation in design is determined by its effectiveness, accuracy, and convenience. This process, however, has generally been handled manually in previous studies, limiting the universality and comprehensiveness of research outcomes. With the development of artificial intelligence, the automation of this process has become possible, ushering in the era of big data research for feature extraction and transformation. Hence, this study proposes a wheel hub feature transformation method based on target detection and geometric analysis. This method implements feature transformation in the following automation steps: (1) wheel hub feature point detection based on the YOLO model; (2) wheel hub feature grouping based on morphological parameters and position parameters; (3) feature point grooming based on geometric relations; and (4) parameter construction and transformation based on morphological features. Thus, an automatic, bidirectional, and morphological mechanism for transforming the parameters of a wheel hub shape can be developed. With the proposed transformation model, parameters related to the wheel hub shape and features can be transformed quickly, and the generative design of the wheel hub can be conducted based on big data. [ABSTRACT FROM AUTHOR]

For ensuring vehicle safety, the impact performance of wheels during wheel development must be ensured through a wheel impact test. However, manufacturing and testing a real wheel requires a significant time and money because developing an optimal wheel design requires numerous iterative processes to modify the wheel design and verify the safety performance. Accordingly, wheel impact tests have been replaced by computer simulations such as finite element analysis (FEA); however, it still incurs high computational costs for modeling and analysis, and requires FEA experts. In this study, we present an aluminum road wheel impact performance prediction model based on deep learning that replaces computationally expensive and time-consuming 3D FEA. For this purpose, 2D disk-view wheel image data, 3D wheel voxel data, and barrier mass values used for the wheel impact test were utilized as the inputs to predict the magnitude of the maximum von Mises stress, corresponding location, and the stress distribution of the 2D disk-view. The input data were first compressed into a latent space with a 3D convolutional variational autoencoder (cVAE) and 2D convolutional autoencoder (cAE). Subsequently, the fully connected layers were used to predict the impact performance, and a decoder was used to predict the stress distribution heatmap of the 2D disk-view. The proposed model can replace the impact test in the early wheel-development stage by predicting the impact performance in real-time and can be used without domain knowledge. The time required for the wheel development process can be reduced using this mechanism. [ABSTRACT FROM AUTHOR]