To address the challenges in industrial precision component detection posed by existing point cloud datasets, this research endeavors to amass and construct a point cloud dataset comprising 1101 models of miniature gears. The data collection and processing procedures are elaborated upon in detail. In response to the segmentation issues encountered in point clouds of small industrial components, a novel Point Transformer network incorporating a multiscale feature fusion strategy is proposed. This network extends the original Point Transformer architecture by integrating multiple global feature extraction modules and employing an upsampling module for contextual information fusion, thereby enhancing its modeling capabilities for intricate point cloud structures. The network is trained and tested on the self-constructed gear dataset, yielding promising results. Comparative analysis with the baseline Point Transformer network indicates a notable improvement of 1.1% in mean Intersection over Union (mIoU), substantiating the efficacy of the proposed approach. To further assess the method’s effectiveness, several ablation experiments are designed, demonstrating that the introduced modules contribute to varying degrees of segmentation accuracy enhancement. Additionally, a comparative evaluation is conducted against various state-of-the-art point cloud segmentation networks, revealing the superior performance of the proposed methodology. This research not only aids in quality control, structural detection, and optimization of precision industrial components but also provides a scalable network architecture design paradigm for related point cloud processing tasks.