WWWeilin Wu

Weilin Wu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Weilin Wu has a total of 18 co-authors. Here are the top co-authors by number of shared publications:

  • Zhongjian Xie

    School of Physics and Electronic Information, Guangxi Minzu University, Nanning, China

    3 shared publications
  • Wei Xie

    School of Automation Science and Engineering, South China University of Technology, Guangzhou 510640, China

    2 shared publications
  • Weiqi Chen

    Affiliation College of Physics and Electronic Information, Guangxi Minzu University, Nanning, China

    2 shared publications
  • Xinwei Chen

    Affiliation College of Physics and Electronic Information, Guangxi Minzu University, Nanning, China

    2 shared publications
  • Yao Xiao

    Affiliation College of Physics and Electronic Information, Guangxi Minzu University, Nanning, China

    2 shared publications
  • Yaya Zhang

    Affiliation College of Physics and Electronic Information, Guangxi Minzu University, Nanning, China

    2 shared publications

Latest Publications

  • Open Access

    A lightweight trichosanthes kirilowii maxim detection algorithm in complex mountain environments based on improved YOLOv7-tiny

    by Zhongjian Xie, Xinwei Chen, Weilin Wu, Yao Xiao, Yuanhang Li, Yaya Zhang, ZhuXuan Wan, Weiqi Chen

    Detecting Trichosanthes Kirilowii Maxim (Cucurbitaceae) in complex mountain environments is critical for developing automated harvesting systems. However, the environmental characteristics of brightness variation, inter-plant occlusion, and motion-induced blurring during harvesting operations, detection algorithms face excessive parameters and high computational intensity. Accordingly, this study proposes a lightweight T.Kirilowii detection algorithm for complex mountainous environments based on YOLOv7-tiny, named KPD-YOLOv7-GD. Firstly, improve the multi-scale feature layer and reduce the complexity of the model. Secondly, a lightweight convolutional module is introduced to replace the standard convolutions in the Efficient Long-range Aggregation Network (ELAN-A) module, and the channel pruning techniques are applied to further decrease the model’s complexity. Finally, the experiment significantly enhanced the efficiency of feature extraction and the detection accuracy of the model algorithm through the integration of the Dynamic Head (DyHead) module, the Content-Aware Re-Assembly of Features (CARAFE) module, and the incorporation of knowledge distillation techniques. The experimental results showed that the mean average precision of the improved network KPD-YOLOv7-GD reached 93.2%. Benchmarked against mainstream single-stage algorithms (YOLOv3-tiny, YOLOv5s, YOLOv6s, YOLOv7-tiny, and YOLOv8), KPD-YOLOv7-GD demonstrated mean average precision improvements of 4.8%, 0.6%, 3.0%, 0.6%, and 0.2% with corresponding model compression rates of 81.6%, 68.8%, 88.9%, 63.4%, and 27.4%, respectively. Compared with similar studies, KPD-YOLOv7-GD exhibits lower complexity and higher recognition speed accuracy, making it more suitable for resource-constrained T.kirilowii harvesting robots.

  • Multiobjective Optimization Control for Nonideal Single-Inductor Dual-Output Buck Converter

    by Lin Yang, Jiarong Wu, Liping Luo, Weilin Wu, Hailong Ma

    Single-inductor dual-output (SIDO) buck converter has been widely applied in fields of portable electronic products and smart homes due to their advantages of small size and multiple outputs. However, cross regulation seriously deteriorates the stability of the converter. In addition, parasitic parameters of circuit components reduce the conversion efficiency of the converter and have a significant impact on cross regulation. To suppress the cross regulation and improve the conversion efficiency of the nonideal SIDO buck converter, a multiobjective optimization control strategy is proposed. Considering the parasitic parameters of circuit components, a large signal model of the converter is established, and a predictive equation is constructed based on the model predictive control theory. Furthermore, an objective function for optimizing output error is established based on weighting the output voltage error and inductor current error. Then, a method is proposed to achieve real-time correction of the state variable reference values. The power loss of the system is analyzed and weighted onto the objective function to improve the conversion efficiency. Compared with the common mode voltage-differential mode voltage control method, simulation and experimental results show that the proposed strategy provides smaller cross regulation and better dynamic performance. The conversion efficiency is improved by 6.6%.


  • Open Access

    Hydroponic Chinese flowering cabbage detection and localization algorithm based on improved YOLOv5s

    by Zhongjian Xie, Yaya Zhang, Weilin Wu, Yao Xiao, Xinwei Chen, Weiqi Chen, ZhuXuan Wan, Chunhua Lin

    To achieve automated harvesting of hydroponic Chinese flowering cabbage, the detection and localization of the cabbage are crucial. This study proposes a two stages detection and localization algorithm for hydroponic Chinese flowering cabbage, which includes macro-detection and micro-localization. The macro-detection algorithm is named P-YOLOv5s-GRNF. Its improvement strategies include adopting pruning techniques, the GSConv, receptive field attention convolution (RFAConv), normalization-based attention module (NAM), and the Focal-EIOU Loss module. The micro-localization algorithm is named YOLOv5s-SBC. Its improvement strategies include adding a 160×160 detection layer, removing a 20×20 detection layer, introducing a weighted bidirectional feature pyramid network (BiFPN) structure, and utilizing the coordinate attention (CA) mechanism. The experimental results showed that P-YOLOv5s-GRNF increased the mAP(mean average precision) by 0.8%, 4.3%, 3.2%, 0.7%, 19.3%, 9.8%, 3.1% compared to mainstream object detection algorithms YOLOv5s, YOLOv6s, YOLOv7-tiny, YOLOv8s, YOLOv5s-Shufflenetv2, YOLOv5s-Mobilenetv3, YOLOv5s-Ghost, respectively. Compared to the original model, P-YOLOv5s-GRNF decreased parameters by 18%, decreased model size to 11.9MB, decreased FLOPs to 14.5G, and increased FPS by 4.3. YOLOv5s-SBC also increased mAP by 4.0% compared to the original YOLOv5s, with parameters decreased by 65%, model size decreased by 60%, and FLOPs decreased to 15.3G. Combined with a depth camera, the improved models construct a positioning system that can provide technical support for the automated and intelligent harvesting of Chinese flowering cabbage.


  • Open Access

    Switching Linear Parameter-Varying Controller Design With H∞ Performance Based on Youla Parameterization

    by Weilin Wu, Wei Xie, Liejun Li

    This paper utilizes the Youla parameterization method to design a switching linear parameter-varying (LPV) output-feedback controller. The switching controller consists of several LPV controllers designed in advance and independently with corresponding H∞ performance. Based on the Youla parameterization idea, the controller design procedure is decomposed into two steps. First, a central controller is designed to ensure global H∞ performance. Second, a switching controller is constructed to achieve the H∞ performance in each subset under arbitrary switching. This scheme is designed to develop state-space realizations of Youla parameters from the central controller. The realizations not only ensure that the closed-loop system satisfies the H∞ performance under arbitrary switching but also guarantees the corresponding H∞ performance for local subsystem at each fixed point. The simulation results show the effectiveness of the proposed method.


  • Open Access

    Switching controller design for linear time-invariant plant with H2 performance criterion

    by Weilin Wu, Wei Xie, Wei He, Langwen Zhang

    This paper deals with the problem of designing a switching controller, which includes several linear time-invariant (LTI) controllers designed beforehand and independently for a specific LTI plant with corresponding H2 control performance criteria. It is possible to find suitable state space realizations for any given family of controller transfer matrices, which guarantee not only certain H2 performance of the overall closed-loop system under arbitrary switching but also the corresponding H2 performance of local subsystems at each switching point. The effectiveness of the proposed method is demonstrated with a numerical example.