XCXiaokang Chen

Xiaokang Chen

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xiaokang Chen has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Microstructural Organization and Mechanical Properties of 5356 Aluminum Alloy Wire Arc Additive Manufacturing Under Low Heat Input Conditions

    by Xiaogang Zuo, Zhimin Lv, Yuejie Wang, Xiaokang Chen, Wenjun Qi

    This study examines the microstructure and mechanical properties of 5356 aluminum alloy under low heat input conditions during arc additive manufacturing, focusing on the challenges posed by excessive heat input, which hinders specimen formation and affects dimensional accuracy. The study analyzes the characteristics of single-pass multilayer straight-walled specimens fabricated under varying low heat input conditions, along with evaluations of their mechanical properties, including their microstructure, microhardness, and tensile strength. This study demonstrates that as the heat input increases from 87.5 J/mm to 190.0 J/mm, the width of the vertical wall specimens increases significantly, whereas the change in single-layer height remains minimal. The specimen width increases from 5.22 mm to 8.87 mm, representing a change of 3.65 mm, while the single-layer height increases by only 0.16 mm. The microstructure primarily consists of the α(Al) matrix and the skeletal β(Al3Mg2) phase. As heat input increases, some of the β(Al3Mg2) phase dissolves, resulting in a decrease in its distribution density, a reduction in its quantity, and an increase in its size. The average hardness increases from 69.40 HV at 87.5 J/mm to 77.89 HV at 154.2 J/mm, before decreasing to 73.56 HV at 190.0 J/mm. As the heat input increases, the tensile strength and elongation of both horizontal and vertical specimens initially increase and then decrease. The tensile strength and elongation of the horizontal specimens are slightly greater than those of the vertical specimens. The microstructure and mechanical properties vary across different regions. In the upper region, the β(Al3Mg2) phase is uniformly distributed, with high density and small size. The fracture surface exhibits fine, uniform dimples, displaying the best microhardness and mechanical properties, with a tensile strength of 245.88 MPa. In the middle region, the distribution density of the β phase decreases, the size increases, and the dimples become slightly coarser. Consequently, the microhardness and mechanical properties decline. At the bottom, due to the higher cooling rates, the β phase does not dissolve significantly. The distribution density is high, the dimples are large and uneven, and the microhardness and mechanical properties are the lowest, with a tensile strength of 236.00 MPa.


  • Open Access

    New Plum Detection in Complex Environments Based on Improved YOLOv8n

    by Xiaokang Chen, Genggeng Dong, Xiangpeng Fan, Yan Xu, Xiangjun Zou, Jianping Zhou, Hong Jiang

    To address the challenge of accurately detecting new plums amidst trunk and leaf occlusion and fruit overlap, this study presents a novel target detection model, YOLOv8n-CRS. A specialized dataset, specifically designed for new plums, was created under real orchard conditions, with the advanced YOLOv8n model serving as the base network. Initially, the CA attention mechanism was introduced to the backbone network to improve the model’s ability to extract crucial features of new plums. Subsequently, the RFB module was incorporated into the neck layer to leverage multiscale information, mitigating inaccuracies caused by fruit overlap and thereby enhancing detection performance. Finally, the original CIOU loss function was replaced with the SIOU loss function to further enhance the model’s detection accuracy. Test results show that the YOLOv8n-CRS model achieved a recall rate of 88.9%, with average precision scores of mAP@0.5 and mAP@0.5:0.95 recorded at 96.1% and 87.1%, respectively. The model’s F1 score reached 90.0%, and it delivered a real-time detection speed of 88.5 frames per second. Compared to the YOLOv8n model, the YOLOv8n-CRS exhibited a 2.2-percentage-point improvement in recall rate, alongside increases of 0.7 percentage points and 1.2 percentage points in mAP@0.5 and mAP@0.5:0.95, respectively. In comparison to the Faster R-CNN, YOLOv4, YOLOv5s, and YOLOv7 models, the YOLOv8n-CRS model features the smallest size of 6.9 MB. This streamlined design meets the demands for real-time identification of new plums in intricate orchard settings, providing strong technical backing for the visual perception systems of advanced plum-picking robots.


  • Open Access

    Fruit Stalk Recognition and Picking Point Localization of New Plums Based on Improved DeepLabv3+

    by Xiaokang Chen, Genggeng Dong, Xiangpeng Fan, Yan Xu, Tongshe Liu, Jianping Zhou, Hong Jiang

    Among the challenges posed by real orchard environments, where the slender new plum fruit stalks exhibit varying postures and share similar coloration with surrounding leaves and branches, the significant obscuration caused by leaves leads to inaccurate segmentation of the fruit stalks, thereby complicating the precise localization of picking points and other related issues. This paper proposes a method for new plum fruit stalk recognition and picking point localization based on the improved DeepLabv3+ model. Firstly, it employs the lightweight MobileNetv2 as the backbone feature extraction network. Secondly, the Convolutional Block Attention Module (CBAM) is integrated into the decoder to enhance the model’s ability to extract key features of the fruit stalks. Moreover, dense atrous spatial pyramid pooling (DenseASPP) is utilized to replace the original ASPP module, thereby reducing segmentation leakage. Finally, a picking point localization method is designed based on a refinement algorithm and an endpoint detection algorithm to meet the specific picking demands of new plum, identifying the endpoints along the skeletal line of the fruit stalks as the optimal picking points. The experimental results demonstrate that the mean intersection over union (MIoU) and mean pixel accuracy (MPA) of the enhanced DeepLabv3+ model are 86.13% and 92.92%, respectively, with a model size of only 59.6 MB. In comparison to PSPNet, U-Net, and the original DeepLabv3+ model, the MIoU improves by 13.78, 0.34, and 1.31 percentage points, while the MPA shows enhancements of 15.35, 1.72, and 1.38 percentage points, respectively. Notably, with the endpoint of the fruit stalk’s skeletal structure designated as the picking point for new plums, the localization success rate reaches 88.8%, thereby meeting the requirements for precise segmentation and picking point localization in actual orchard environments. Furthermore, this advancement offers substantial technical support for the research and development of new plum harvesting robots.