Feature Transformation Method for Wheel Hub Shape Based on Target Detection and Geometric Analysis

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.