Junyong Xia

Junyong Xia

Auto-generated profile, based on publicly available information

Junyong Xia

School of Mechanical Engineering, Hubei University of Technology, Wuhan 430068, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
1 February 2022 in Automation in Construction
Verified
Journal Article
Closed access
LZLiang Zeng
Liang Zeng
WSWenqiang Shu
Wenqiang Shu
ZLZhe Liu
Zhe Liu
XZXinyi Zou
Xinyi Zou
SWShanshan Wang
Shanshan Wang
ZYZhao Yang
Zhao Yang

26 April 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YCYijie Cai
Yijie Cai
MHMing He
Ming He
QTQi Tao
Qi Tao
JXJunyong Xia
Junyong Xia
FZfei zhong
fei zhong
HZHongdi Zhou
Hongdi Zhou
Fastener screws are critical components of rail fasteners. For the fastener screw maintenance robot, an image-based fast fastener screw detection method is urgently needed. In this paper, we propose a light-weight model named FSS-YOLO based on YOLOv5n for rail fastener screw detection. The C3Fast module is presented to replace the C3 module in the backbone and neck to reduce Params and FLOPs. Then, the SIoU loss is introduced to enhance the convergence speed and recognition accuracy. Finally, for the enhancement of the screw detail feature fusion, the shuffle attention (SA) is incorporated into the bottom-up process in the neck part. Experiment results concerning CIoU and DIoU for loss, MobileNetv3 and GhostNet for light-weight improvement, simple attention mechanism (SimAM), and squeeze-and-excitation (SE) attention for the attention module, and YOLO series methods for performance comparison are listed, demonstrating that the proposed FSS-YOLO significantly improves the performance, with higher accuracy and lower computation cost. It is demonstrated that the FSS-YOLO is 7.3% faster than the baseline model in FPS, 17.4% and 19.5% lower in Params and FLOPs, respectively, and the P, mAP@50, Recall, and F1 scores are increased by 10.6% and 6.4, 13.4%, and 12.2%, respectively.

1 February 2024 in IEEE Sensors Journal
Verified
Journal Article
Closed access
HZHongdi Zhou
Hongdi Zhou
THTao Huang
Tao Huang
FZFei Zhong
Fei Zhong
JDJian Duan
Jian Duan
Xixing LiXixing Li
Xixing Li
JXJunyong Xia
Junyong Xia
Transfer learning has been widely applied in bearing defect diagnosis across various working conditions. However, some existing methods overlook the local and discriminative manifold structures hidden in samples with different distributions, which may degrade model diagnostic performance. In this study, a local manifold discriminant domain adaptation (LMDDA) transfer learning method is proposed for bearing fault diagnosis. The source and target domains are firstly converted in manifold feature subspace to obtain robust feature representations. Then, an intermediate domain with similar distribution to target domain is generated from the source domain in the potential common subspace to reduce the distribution difference between source and target domains. Meanwhile, the local generated discrepancy metric is used to evaluate the discriminability of data, preserve the local manifold structure of the generated data, and align the local data. The intermediate and target domains are aligned by the maximum mean discrepancy metric to enhance the consistency of the local and global structure of data. On this basis, the low-rank constraint is introduced to guarantee the correlation between source and target data in virtue of the block diagonal property, which can improve the generalization ability and performance stability of the model. Finally, the least squares method is utilized to achieve bearing fault diagnosis. A series of cross-domain fault diagnosis experiments were carried out to verify the effectiveness and superiority of the proposed method, and the results illustrate that LMDDA can accurately detect diverse fault types and handle intricate cross-domain adaptive scenarios.

10 November 2024 in Symmetry
Verified
Journal Article
Open access
PDF file
JXJunyong Xia
Junyong Xia
BLBiwei Li
Biwei Li
ZXZhiqiang Xu
Zhiqiang Xu
FZFei Zhong
Fei Zhong
XHXiaotao Hei
Xiaotao Hei
When using point cloud technology to measure the dimension and geometric error of aircraft landing gear components, the point cloud data obtained after scanning may have certain differences because of the sophistication and diversity of the components that make up the landing gear. However, when using traditional point cloud registration algorithms, if the initial pose between point clouds is poor, it can lead to significant errors in the final registration results or even registration failure. Furthermore, the significant difference in registration results between point clouds can affect the final measurement results. Adopting Teaching-Learning-Based Optimization (TLBO) to solve some optimization problems has unique advantages such as high accuracy and good stability. This study integrates TLBO with point cloud registration. To increase the probability of using TLBO for point cloud registration to search for the global optimal solution, adaptive learning weights are first introduced during the learner phase of the basic TLBO. Secondly, an additional tutoring phase has been designed based on the symmetry and unimodality of the normal distribution to improve the accuracy of the solution results. In order to evaluate the performance of the proposed algorithm, it was first used to solve the CEC2017 test function. The comparison results with other metaheuristics showed that the improved TLBO has excellent comprehensive performance. Then, registration experiments were conducted using the open point cloud dataset and the landing gear point cloud dataset, respectively. The registration results showed that the point cloud registration method proposed in this paper has strong competitiveness.

25 November 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JXJunyong Xia
Junyong Xia
HCHan Chen
Han Chen
HZHongdi Zhou
Hongdi Zhou
FZFei Zhong
Fei Zhong
To address the demand for high-precision multi-object real-time detection in factory safety production scenarios, this paper proposes an improved real-time visual detection model. The model is built upon YOLOv8 and introduces the MAStar module to replace part of the C2f structure, enhancing feature reuse and gradient flow. A small-object detection layer is added to improve the perception of small-scale targets, while a lightweight shared detection head is adopted to reduce the number of parameters. Furthermore, a High-Efficiency Up-sampling Convolution (HEUC) module is designed to achieve more accurate feature reconstruction. Experimental results show that, on the self-built dataset, the proposed model improves mAP@50 and mAP@50:95 by 3.8 percentage points compared with the original model, and by 6.6 percentage points on the public VisDrone2019 dataset. The proposed method achieves a favorable balance between detection accuracy and computational efficiency, providing an effective solution for multi-object real-time detection in industrial safety monitoring.