| 江敏,李志星,高雨晴,杨啸龙.轻量化YOLO-SGLS电梯钢丝绳损伤检测算法[J].电子测量与仪器学报,2025,39(10):153-164 |
| 轻量化YOLO-SGLS电梯钢丝绳损伤检测算法 |
| Lightweight YOLO-SGLS Elevator Wire Rope Damage Detection Algorithm |
| |
| DOI： |
| 中文关键词: 钢丝绳 损伤检测 YOLO11 轻量化 StarNet |
| 英文关键词:wire rope defect detection YOLO11 lightweight StarNet |
| 基金项目:国家自然科学基金青年基金（51805275）、北京市属高校基本科研业务费项目（X21053）资助 |
|
|
| Author | Institution |
| Jiang Min | School of Mechanical, Electrical and Vehicle Engineering, Beijing University of
Civil Engineering and Architecture, Beijing 100000, China |
| Li Zhixing | School of Mechanical, Electrical and Vehicle Engineering, Beijing University of
Civil Engineering and Architecture, Beijing 100000, China |
| Gao Yuqing | School of Mechanical, Electrical and Vehicle Engineering, Beijing University of
Civil Engineering and Architecture, Beijing 100000, China |
| Yang Xiaolong | School of Mechanical, Electrical and Vehicle Engineering, Beijing University of
Civil Engineering and Architecture, Beijing 100000, China |
|
| 摘要点击次数: 650 |
| 全文下载次数: 494 |
| 中文摘要: |
| 针对现有电梯钢丝绳表面损伤检测方法所存在的精度不足、计算量过大等缺陷，基于YOLO11算法提出一种轻量化YOLO-SGLS模型。首先采用StarNet替代YOLO11的主干网络，以星型运算提升特征提取和计算性能。同时，引入大核分离注意力（LSKA）模块与空间金字塔池化快速（SPPF）模块融合，利用深度卷积增强模型的特征表达与感知。此外，用动态卷积（DynamicConv）改进Ghost模块得到GDC（ghost-dynamic-Conv）模块，并将其于C3K2结合，减少计算负担。最后设计轻量级共享卷积检没头（LSCD）提高推理速度。实验使用Cable Damage数据集，分训练、验证、测试集，在特定实验环境下，进行消融实验、泛化实验和对比实验。实验表明YOLO-SGLS模型相比原始基础网络YOLO11n的浮点计算量和参数量分别降低了40%、36%，准确率提升了5.5%，平均精度和召回率只下降了0.3%、1.9%，在泛化能力测试中，100张新数据集，YOLO-SGLS正确识别的图像数为77张。证明了算法的轻量化程度、准确率和鲁棒性均满足电梯钢丝绳损伤检测在实际应用场景中的需求，尤其适用于资源受限的嵌入式设备。 |
| 英文摘要: |
| A lightweight YOLO-SGLS model is proposed based on the YOLO11 algorithm to address the shortcomings of existing elevator wire rope surface damage detection methods, such as insufficient accuracy and excessive computational complexity. Firstly, StarNet is used to replace the backbone network of YOLO11, and the star operation is used to improve feature extraction and computational performance. Meanwhile, the LSKA module is integrated with SPPF to enhance the feature expression and perception of the model through deep convolution. In addition, the Ghost module is improved using DynamicConv to obtain the Ghost Dynamic Conv （GDC) module, which is combined with C3K2 to reduce computational burden. Finally, an LSCD detection head is designed to improve inference speed. The experiment uses the Cable Damage dataset, which is divided into training, validation, and testing sets. In a specific experimental environment, ablation experiments, generalization experiments, and comparative experiments are conducted. The experiment shows that the YOLO-SGLS model reduces GFLOPs and parameter count by 40% and 36% respectively compared to the original base network YOLO11, improves accuracy by 5.5%, and only decreases average accuracy and recall by 0.3% and 1.9%. In the generalization ability test, the YOLO-SGLS model correctly recognizes 77 images out of 100 new datasets. It has been proven that the lightweight, accuracy, and robustness of the algorithm meet the requirements of elevator wire rope damage detection in practical application scenarios, especially for embedded devices with limited resources. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
