Liang Chang

Dr. Liang Chang


Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 October 2026 in Journal of Composites Science
Verified
Journal Article
Open access
PDF file
YGYuzhe Guo
Yuzhe Guo
QSQinghua Song
Qinghua Song
LCLiang Chang
Liang Chang
TZTiancheng Zhao
Tiancheng Zhao
朱朱朱帅辉 朱帅辉
朱帅辉 朱帅辉
Automated fiber placement (AFP) of advanced polymer composites requires timely monitoring of process conditions that influence gaps, overlaps, wrinkles, and inter-ply bonding. This study develops an end–edge–cloud decision-support framework that links read-only sensing, low-latency prediction, risk grading, operator confirmation, and traceable cloud optimization while retaining the numerical-control hard-interlock chain. The edge uses 18 temporal-statistical features for anomaly classification (TF-MLP-C) and temperature–pressure forecasting (TF-MLP-TP), while a separate nine-feature Cutter-RUL MLP estimates cutter life. In 90 days of single-machine operation, the pipeline processed 2.87 × 108 records at 36.9 records/s, supported 80 concurrent users, and achieved 99.6% availability. On fixed-seed parametric simulations, classification accuracy and macro F1 were 91.67% and 90.28%, respectively; mean warning lead time was 5.83 ± 2.54 s. The temperature and pressure MAEs were 0.713 °C and 26.96 N, and cutter-life MAE was 139.52 cuts (R2 = 0.9819). The 90-day field records establish pipeline operation and operator-facing logging, not independent predictive-model accuracy; all reported model scores are simulation-based proof-of-concept estimates, with no evaluation on a held-out labeled AFP production test set. The contribution is a deployable and auditable monitoring workflow that turns heterogeneous AFP data into bounded decision support and provides a reproducible basis for future multi-machine and quality-linked validation.

16 October 2026 in Journal of Composites Science
Verified
Journal Article
Open access
PDF file
LCLiang Chang
Liang Chang
QSQinghua Song
Qinghua Song
TZTiancheng Zhao
Tiancheng Zhao
YGYuzhe Guo
Yuzhe Guo
YWYuxin Wei
Yuxin Wei
CGChao Gu
Chao Gu
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.

29 September 2026 in Journal of Composites Science
Verified
Journal Article
Open access
PDF file
QSQinghua Song
Qinghua Song
LCLiang Chang
Liang Chang
TZTiancheng Zhao
Tiancheng Zhao
YGYuze Guo
Yuze Guo
JZJing Zhu
Jing Zhu
Automated fibre placement (AFP) is a key process for manufacturing advanced polymer–matrix composite aerostructures; however, an uneven compaction-pressure distribution of tows during lay-up reduces the inter-laminar bonding strength and induces processing defects such as bridging and wrinkles. In this study, a pressure regulation strategy coordinating simulation-based feed-forward planning with closed-loop feedback control is proposed as a modified processing route for improving the manufacturing quality of polymer composites. The strategy adopts a two-layer “planning–execution” architecture. In the planning layer, process parameters and placement trajectories are optimized in advance based on a compaction-roller pressure simulation model and a compaction-uniformity index. In the execution layer, closed-loop pressure control suppresses on-site disturbances in real time to ensure that the simulation objectives are realized, thereby achieving uniform control of the compaction-pressure field. Finally, multi-angle lay-up experiments were carried out on a convex-surface mould, and the pressure field was measured using pressure-sensitive films. The results show that the proposed regulation strategy improves pressure distribution uniformity by more than 6%, effectively enhancing curved-surface lay-up quality and the consolidation quality of advanced polymer composite components. This work provides an intelligent design-and-manufacturing route that links process simulation with real-time control for high-quality automated composite processing.

8 October 2026 in Journal of Composites Science
Verified
Journal Article
Open access
PDF file
TZTiancheng Zhao
Tiancheng Zhao
QSQinghua Song
Qinghua Song
LCLiang Chang
Liang Chang
YGYuzhe Guo
Yuzhe Guo
YZYu Zhang
Yu Zhang
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.