Yuzhe Guo
Research Subjects
Yuzhe Guo has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Liang Chang
Shanghai Aircraft Manufacturing Co., Ltd., Shanghai 201324, China
2 shared publications - Qinghua Song
Shanghai Aircraft Manufacturing Co., Ltd., Shanghai 201324, China
2 shared publications - Tiancheng Zhao
Shanghai Aircraft Manufacturing Co., Ltd., Shanghai 201324, China
2 shared publications - Chao Gu
Hangzhou Aimeiyi Aviation Manufacturing Equipment Co., Ltd., Hangzhou 311225, China
1 shared publication - Yu Zhang
Hangzhou Aimeyi Aviation Manufacturing Equipment Co., Ltd., Hangzhou 310000, China
1 shared publication - Yuxin Wei
Hangzhou Aimeiyi Aviation Manufacturing Equipment Co., Ltd., Hangzhou 311225, China
1 shared publication
Latest Publications
- Open Access
- 16 October 2026
- Published by MDPI AG in Journal of Composites Science
- Vol. 10 (10) , 547
Gradient-Enhanced Deformation-Aware Defect Detection for Automated Fiber Placement with Synthetic Sample Expansion
Existing learning-based AFP inspection methods predominantly rely on grayscale/depth-like representations or directly learned appearance features, while the directional relationship between laser-profile height variation and defect boundaries remains insufficiently exploited. This limitation is particularly relevant to low-contrast and slender AFP defects, for which periodic tow textures can interfere with boundary localization and only limited real defect samples are typically available. To address these issues, this study develops an AFP-specific instance-segmentation framework that coordinates geometry-informed input representation, deformation-aware feature processing, and training-distribution expansion. After outlier correction, RANSAC reference-surface fitting, and residual enhancement, the residual height field and its signed horizontal and vertical gradients are used as a three-channel input to explicitly represent local surface amplitude and directional boundary variation. C2f_DCNv2 and CBAM are incorporated into YOLOv8n-Seg for complementary purposes: adaptive sampling along elongated or irregular defect geometry and suppression of less relevant tow-texture responses, respectively. ConSinGAN-generated samples are screened, manually annotated, and used only for training to expand the represented defect morphology. Three-seed experiments show that the gradient-enhanced representation improves mask P, mask R, mask mAP@50, and mask mAP@50:95 by 2.56, 1.67, 2.85, and 1.22 percentage points over the depth-enhanced input. The architecture modification provides additional gains of 1.32 and 1.52 points in mAP@50 and mAP@50:95, and ConSinGAN augmentation adds 1.19 and 1.51 points. The complete method achieves 94.36% mask P, 91.93% mask R, 94.71% mask mAP@50, and 60.17% mask mAP@50:95. The complete post-acquisition dual-window processing pipeline requires 26.8 ± 0.9 ms per synchronized pair, compared with a 409.6 ms acquisition interval at 30 m/min. These results demonstrate the effectiveness of coordinating AFP-specific geometric representation, morphology-adaptive feature processing, and controlled training-set expansion for online defect segmentation under the evaluated conditions.
- 16 October 2026
- Published by MDPI AG in Journal of Composites Science
- Vol. 10 (10) , 547
Open AccessGradient-Enhanced Deformation-Aware Defect Detection for Automated Fiber Placement with Synthetic Sample Expansion
Existing learning-based AFP inspection methods predominantly rely on grayscale/depth-like representations or directly learned appearance features, while the directional relationship between laser-profile height variation and defect boundaries remains insufficiently exploited. This limitation is particularly relevant to low-contrast and slender AFP defects, for which periodic tow textures can interfere with boundary localization and only limited real defect samples are typically available. To address these issues, this study develops an AFP-specific instance-segmentation framework that coordinates geometry-informed input representation, deformation-aware feature processing, and training-distribution expansion. After outlier correction, RANSAC reference-surface fitting, and residual enhancement, the residual height field and its signed horizontal and vertical gradients are used as a three-channel input to explicitly represent local surface amplitude and directional boundary variation. C2f_DCNv2 and CBAM are incorporated into YOLOv8n-Seg for complementary purposes: adaptive sampling along elongated or irregular defect geometry and suppression of less relevant tow-texture responses, respectively. ConSinGAN-generated samples are screened, manually annotated, and used only for training to expand the represented defect morphology. Three-seed experiments show that the gradient-enhanced representation improves mask P, mask R, mask mAP@50, and mask mAP@50:95 by 2.56, 1.67, 2.85, and 1.22 percentage points over the depth-enhanced input. The architecture modification provides additional gains of 1.32 and 1.52 points in mAP@50 and mAP@50:95, and ConSinGAN augmentation adds 1.19 and 1.51 points. The complete method achieves 94.36% mask P, 91.93% mask R, 94.71% mask mAP@50, and 60.17% mask mAP@50:95. The complete post-acquisition dual-window processing pipeline requires 26.8 ± 0.9 ms per synchronized pair, compared with a 409.6 ms acquisition interval at 30 m/min. These results demonstrate the effectiveness of coordinating AFP-specific geometric representation, morphology-adaptive feature processing, and controlled training-set expansion for online defect segmentation under the evaluated conditions.
- Open Access
- 8 October 2026
- Published by MDPI AG in Journal of Composites Science
- Vol. 10 (10) , 530
Classification and Identification of Overlap and Gap Regions in Path-Planning for Automated Fiber Placement Technology
Automated Fiber Placement (AFP) of carbon-fiber composite materials constitutes a core digital manufacturing technology for large-scale aerospace composite components with double-curved surfaces. Gap and overlap defects induced during path planning degrade the fatigue performance of composite parts and threaten aircraft structural safety. Aiming at the limitation that conventional post-forming non-destructive testing cannot predict lay-up defects at the design stage, this work analyzes the generation mechanisms of gaps and overlaps from differential-geometric constraints of non-developable surfaces. A defect classification framework and geometric identification method oriented to the path-planning phase are established. According to geometric formation causes, lay-up defects are categorized into boundary overlap–gaps induced by tow-cutting operations and internal gaps originating from trajectory divergence over curved surfaces. Twenty boundary working conditions are defined for triangular boundary defects, and internal gaps are further subdivided into tape-type gaps and rectangular gaps. A triangular-patch approximation algorithm is adopted to compute the area of gap–overlap regions and quantitatively evaluate lay-up coverage. The simulation results reveal an inherent trade-off between allowable fiber-angle deviation and lay-up coverage on double-curved mold surfaces.
- 8 October 2026
- Published by MDPI AG in Journal of Composites Science
- Vol. 10 (10) , 530
Open AccessClassification and Identification of Overlap and Gap Regions in Path-Planning for Automated Fiber Placement Technology
Automated Fiber Placement (AFP) of carbon-fiber composite materials constitutes a core digital manufacturing technology for large-scale aerospace composite components with double-curved surfaces. Gap and overlap defects induced during path planning degrade the fatigue performance of composite parts and threaten aircraft structural safety. Aiming at the limitation that conventional post-forming non-destructive testing cannot predict lay-up defects at the design stage, this work analyzes the generation mechanisms of gaps and overlaps from differential-geometric constraints of non-developable surfaces. A defect classification framework and geometric identification method oriented to the path-planning phase are established. According to geometric formation causes, lay-up defects are categorized into boundary overlap–gaps induced by tow-cutting operations and internal gaps originating from trajectory divergence over curved surfaces. Twenty boundary working conditions are defined for triangular boundary defects, and internal gaps are further subdivided into tape-type gaps and rectangular gaps. A triangular-patch approximation algorithm is adopted to compute the area of gap–overlap regions and quantitatively evaluate lay-up coverage. The simulation results reveal an inherent trade-off between allowable fiber-angle deviation and lay-up coverage on double-curved mold surfaces.