Wei-Wei Xu

Dr. Wei-Wei Xu


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
23 September 2025 in Nanomaterials
Verified
Journal Article
Open access
PDF file
YLYu-Xin Liu
Yu-Xin Liu
WGWei Gong
Wei Gong
FBFan-Gao Bu
Fan-Gao Bu
XZXin-Jing Zhao
Xin-Jing Zhao
SLSong Li
Song Li
BGBingrong Gao
Bingrong Gao
Artificial intelligence (AI), particularly machine learning (ML), is equipping laser micro/nano processing with significant intelligent capabilities, demonstrating exceptional performance in areas such as manufacturing process modeling, process parameter optimization, and real-time anomaly detection. This transformative potential is driving the development of next-generation laser micro/nano processing technologies. The key challenges confronting traditional laser manufacturing stem from the complexity of laser–matter interactions, resulting in difficult-to-control processing outcomes and the accumulation of micro/nano defects across multi-step processes, ultimately triggering catastrophic process failures. This review provides an in-depth exploration of how machine learning effectively addresses these challenges through the integration of data-driven modeling with physics-driven modeling, coupled with intelligent in situ monitoring and adaptive control techniques. Systematically, we summarize current representative breakthroughs and frontier advances at the intersection of machine learning and laser micro/nano processing research. Furthermore, we outline potential future research directions and promising application prospects within this interdisciplinary field.

4 December 2023 in Biomimetics
Verified
Journal Article
Open access
PDF file
RLRui-Zhe Leng
Rui-Zhe Leng
BYBi Yun
Bi Yun
ZCZhi-Hao Chen
Zhi-Hao Chen
CCChen Chai
Chen Chai
WXWei-Wei Xu
Wei-Wei Xu
Lei WangLei Wang
Lei Wang
Inspired by periodically aligned micro/nanostructures on biological surfaces, researchers have been fabricating biomimetic structures with superior performance. As a promising and versatile tool, an ultrafast laser combined with other forms of processing technology has been utilized to manufacture functional structures, e.g., the biomimetic subwavelength structures to restrain the surface Fresnel reflectance. In this review paper, we interpret the biomimetic mechanism of antireflective subwavelength structures (ARSSs) for high-transmission windows. Recent advances in the fabrication of ARSSs with an ultrafast laser are summarized and introduced. The limitations and challenges of laser processing technology are discussed, and the future prospects for advancement are outlined, too.

8 February 2024 in Optics Letters
Verified
Journal Article
Closed access
XZXu Zhang
Xu Zhang
Lei WangLei Wang
Lei Wang
XCXiao-Wen Cao
Xiao-Wen Cao
SJShu Jiang
Shu Jiang
YYYan-Hao Yu
Yan-Hao Yu
Qidai ChenQidai Chen
Qidai Chen
In this Letter, a method for the fabrication of bifocal lenses is presented by combining surface ablation and bulk modification in a single laser exposure followed by the wet etching processing step. The intensity of a single femtosecond laser pulse was modulated axially into two foci with a designed computer-generated hologram (CGH). Such pulse simultaneously induced an ablation region on the surface and a modified volume inside the fused silica. After etching in hydrofluoric acid (HF), the two exposed regions evolved into a bifocal lens. The area ratio (diameter) of the two lenses can be flexibly adjusted via control of the pulse energy distribution through the CGH. Besides, bifocal lenses with a center offset as well as convex lenses were obtained by a replication technique. This method simplifies the fabrication of micro-optical elements and opens a highly efficient and simple pathway for complex optical surfaces and integrated imaging systems.

8 December 2025 in Frontiers in Plant Science
Verified
Journal Article
Open access
PDF file
DZDejia Zhang
Dejia Zhang
SSShaozhong Song
Shaozhong Song
JLJia Liu
Jia Liu
WXWei-Wei Xu
Wei-Wei Xu
NXNurdila Xiayidan
Nurdila Xiayidan
Introduction: The real-time, accurate detection and classification of rice seeds are crucial for improving agricultural productivity, ensuring grain quality, and promoting smart agriculture. Although significant progress has been made using deep learning, particularly convolutional neural networks (CNNs) and attention-based models, earlier methods such as threshold segmentation and single-grain classification faced challenges related to computational efficiency and latency, especially in high-density seed agglutination scenarios. This study addresses these limitations by proposing an integrated intelligent analysis model that combines object detection, real-time tracking, precise classification, and high-accuracy phenotypic measurement. Methods: The proposed model utilizes the lightweight YOLOv11-LA for real-time grain segmentation, which builds upon the YOLOv11 architecture. YOLOv11-LA incorporates several enhancements over YOLOv11, including separable convolutions, CBAM (Convolutional Block Attention Module) attention mechanisms, and module pruning strategies. These modifications not only improve detection accuracy but also significantly reduce the number of parameters by 63.2% and decrease computational complexity by 51.6%. For classification, the model employs a custom-designed, lightweight RiceLCNN classifier. Additionally, the DeepSORT algorithm is employed for real-time multi-object tracking, and sub-pixel edge detection along with dynamic scale calibration mechanisms are applied for precise phenotypic feature measurement. Results: Compared to YOLOv11, the YOLOv11-LA model increases the mAP@0.5:0.95 score by 1.9%, showcasing its superior detection performance while maintaining lower computational overhead. The RiceLCNN classifier achieved classification accuracies of 89.78% on private datasets and 96.32% on public benchmark datasets. The system demonstrated high accuracy in measuring phenotypic features such as seed size and roundness, with measurement errors kept within 0.1 millimeters. The DeepSORT algorithm effectively managed multi-object tracking, reducing duplicate identifications and frame loss in real-time. Discussion: Experimental validation confirmed that the YOLOv11-LA model outperforms the original YOLOv11 in terms of both detection speed and accuracy, while also maintaining low computational complexity. The integration of the YOLOv11-LA, RiceLCNN, and DeepSORT algorithms, combined with advanced measurement techniques, underscores the model's potential for industrial applications, particularly in enhancing smart agricultural practices.

17 October 2025 in Materials
Verified
Journal Article
Open access
PDF file
QWQinxin Wang
Qinxin Wang
WXWei-Wei Xu
Wei-Wei Xu
XWXue Wang
Xue Wang
DSDandan Shi
Dandan Shi
JWJingyuan Wang
Jingyuan Wang
ZHZhan Hu
Zhan Hu
A glow discharge polymer (GDP) has unique physical properties—transparency, brittleness, and hardness—that pose challenges for traditional mechanical machining techniques. We have investigated the microhole fabrication of GDP films using shaped femtosecond laser pulses to study the influence of pulse shape, delay between subpulses, and focusing position on processing precision and efficiency. By precisely controlling pulse characteristics, such as duration, energy, and subpulse intervals, the efficiency, hole morphology, and processing quality were significantly improved. The experimental results demonstrated that femtosecond lasers with subpulses produce smaller and more uniform microholes compared to transform-limited pulses. Furthermore, both the pulse shape and focusing position of the laser were found to further influence ablation efficiency. This study establishes, for the first time, the critical role of temporal pulse shaping in optimizing the femtosecond laser drilling of GDP films, which provides valuable information on optimizing femtosecond laser parameters for precision processing of polymer films and advances the potential for microhole fabrication in industrial applications.