基于列向语义分割的悬浮间隙视觉检测方法研究  

Research on the visual detection method of levitation gap based on column-oriented semantic segmentation

作　　者：靖永志[1,2,3] 倪胜 贾兴科 刘治辛 刘国清 Jing Yongzhi;Ni Sheng;Jia Xingke;Liu Zhixin;Liu Guoqing(Key Laboratory of Maglev Technology and Maglev Train,Ministry of Education,Southwest Jiaotong University,Chengdu 611756,China;College of Electrical Engineering,Southwest Jiaotong University,Chengdu 611756,China;Tangshan Institute,Southwest Jiaotong University,Tangshan 063000,China)

机构地区：[1]西南交通大学磁浮技术与磁浮列车教育部重点实验室,成都611756 [2]西南交通大学电气工程学院,成都611756 [3]西南交通大学唐山研究院,唐山063000

出　　处：《仪器仪表学报》2024年第9期67-76,共10页Chinese Journal of Scientific Instrument

摘　　要：针对传统语义分割网络存在参数量大、实时性低以及抗干扰能力差的问题,提出了一种基于列向语义分割的悬浮间隙视觉检测方法。该方法将间隙检测定义为寻找间隙在图像中部分列位置的集合,简化分类问题以缩减计算复杂度。首先,设计了基于视觉间隙检测悬浮系统结构,基于列方向上的位置选择和分类设计了一种间隙检测语义分割网络(GMSSNet),并采用1×1卷积加列向亚像素卷积层模块代替全连接层进一步减少模型参数量;然后,构建了悬浮间隙样本集并配置训练环境,对所设计的GMSSNet模型分别进行了抗干扰能力测试、消融实验和闭环悬浮实验。实验结果表明,GMSSNet模型具有较高的检测精度,正常悬浮间隙检测样本时的最大检测误差为±0.1 mm,线性度为0.5%F.S,存在偏移或特定遮挡情况下,网络最大检测误差为±0.15 mm,线性度为0.75%F.S,闭环悬浮实验表明基于GMSSNet模型的悬浮间隙检测精度和速度均满足悬浮系统要求。To address the problems of a large number of parameters,low real-time performance,and poor anti-interference ability of traditional semantic segmentation networks,a visual detection method of suspension gap based on column-oriented semantic segmentation is proposed.The method defines gap detection as finding the set of disaggregated locations of gaps in the middle of the image and simplifies the classification problem to reduce the computational complexity.Firstly,the structure of the visual gap detection-based suspension system is designed.A gap detection semantic segmentation network(GMSSNet)is designed based on position selection and classification in the column direction.The number of model parameters is further reduced by using a 1×1 convolution plus column-wise sub-pixel convolution layer module instead of a fully connected layer.Then,the suspension gap sample set is constructed and the training environment is configured.The designed GMSSNet model is tested for anti-jamming ability,ablation experiments,and closed-loop suspension experiments,respectively.The experimental results show that the GMSSNet model has high detection accuracy,the maximum detection error is±0.1 mm and the linearity is 0.5%F.S for normal levitation gap detection samples.The maximum detection error of the network is±0.15 mm and the linearity is 0.75%F.S in the presence of offset or specific occlusion.The closed-loop levitation experiments show that the levitation gap detection accuracy and speed of the GMSSNet model meet the requirements of the suspension system.Aiming at the problems of large number of parameters,low real-time performance and poor anti-interference ability of traditional semantic segmentation network,a visual detection method of suspension gap based on column-oriented semantic segmentation is proposed.The method defines gap detection as finding the set of disaggregated locations of gaps in the middle of the image,and simplifies the classification problem to reduce the computational complexity.Firstly,the structure o

关 键 词：语义分割 悬浮间隙检测 深度学习 超分辨率 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TH702[自动化与计算机技术—控制科学与工程]