基于改进Deeplabv3+算法的滚珠丝杠驱动表面点蚀缺陷检测
Detection of Pitting Defects on the Surface of Ball Screw Drive Based on Improved Deeplabv3+Algorithm
郎朗 1陈晓琴 1刘莎 2周强3
作者信息
- 1. 重庆三峡职业学院智能制造学院 重庆 404155
- 2. 电子科技大学无线通信国家重点实验室 成都 611731
- 3. 重庆邮电大学计算机科学与技术学院 重庆 400065
- 折叠
摘要
针对滚珠丝杠驱动表面背景环境复杂、点蚀缺陷目标小因而难以检测的问题,提出改进的Deeplabv3+滚珠丝杠驱动表面缺陷分割算法.本算法采用Re2Net-50替换Deeplabv3+的主干网络,显著提升了对小尺寸缺陷目标的识别能力.此外,通过在主干网络中融合特征金字塔网络FPN,能够加强多尺度信息的提取,从而增强了对缺陷目标的精确定位.最后,本研究在Deeplabv3+网络的ASPP模块之后引入了Coordinate Attention机制,能够增强模型对图像中空间和维度的关注,有效地捕获了图像中的长距离空间依赖关系.实验结果表明,与原始的Deeplabv3+相比,所提算法在平均交并比MIoU指标上提高了4.38％,准确率Accuracy提高了5.52％,F1-score提高了2.74％.同时,与其他经典的语义分割算法相比,所提算法也展现出了一定的优越性.
Abstract
Aiming at the problems of complex background environments,small pitting defect targets,and difficulty in detection on the surface of ball screw drives,an improved Deeplabv3+algorithm for segmenting surface defects of ball screw drives is pro-posed.This algorithm adopts Re2Net-50 to replace the backbone network of Deeplabv3+,significantly enhances the ability to recognize small-sized defect targets.Additionally,by integrating feature pyramid networks(FPN)into the backbone network,the algorithm effectively extracts multi-scale information,thereby improving the precise localization of defect targets.Finally,the coordinate attention mechanism is introduced after the ASPP module of the Deeplabv3+network,enhancing the model's focus on spatial dimensions within the image and effectively capturing long-range spatial dependencies.Experimental results demon-strate that,compared to the original Deeplabv3+,the proposed algorithm shows a 4.38％improvement in the mean intersection over union(MIoU)metric,a 5.52％increase in accuracy,and a 2.74％rise in F1-score.Furthermore,when compared with other classic semantic segmentation algorithms,the proposedalgorithm also exhibits certain superiority.
关键词
滚珠丝杠驱动/缺陷检测/Deeplabv3+/多尺度特征/注意力机制Key words
Ball screw drive/Defect detection/Deeplabv3+/Multi-scale features/Attention mechanism引用本文复制引用
基金项目
重庆市教委科学技术研究计划(KJQN202103509)
重庆市教学改革研究项目(GZ223108)
重庆市教学改革研究项目(GZ223113)
出版年
2024
NETL
NSTL
万方数据