多级解码神经网络用于滚珠丝杠点蚀检测  

Multi-level decoding neural network for pitting detection of ball screw

作　　者：赵慧锋 李铁军[1] Zhao Huifeng;Li Tiejun(Equipment Reliability Institute,Shenyang University of Chemical Technology,Shenyang 110142,China;School of Mechanical and Power Engineering,Shenyang University of Chemical Technology,Shenyang 110142,China)

机构地区：[1]沈阳化工大学装备可靠性研究所,沈阳110142 [2]沈阳化工大学机械与动力工程学院,沈阳110142

出　　处：《电子测量技术》2024年第1期125-129,共5页Electronic Measurement Technology

基　　金：国家自然科学基金(52275156);辽宁省重点(一般)项目教育部(LJKZ0435)项目资助。

摘　　要：由于滚珠丝杠点蚀区域小,环境干扰严重,缺陷难以及时检测。所以提出了一种多级解码神经网络,实现滚珠丝杠点蚀缺陷的分割。该网络由编码器、多级解码器和多尺度注意力模块组成。编码器由Resnet34组成,并引入Ghost模块构建了轻量化的多级解码器。为了融合多尺度特征并过滤冗余信息,设计了多尺度注意力模块。采用二值交叉熵函数,IOU和SSIM函数组成的混合损失函数训练网络。在滚珠丝杠缺陷数据集上做了实验,多级解码神经网络在maxF_(β)指标上达到了0.7703,与其他方法相比,该网络取得了更好的分割结果,并且单张图片处理时间为26 ms。为滚珠丝杠点蚀缺陷实时分割提供了一种新的方法。Due to the small pitting area of the ball screw and the serious environmental interference,defects are difficult to detect in time.Therefore,a Multi-level decoding neural network is proposed to realize the segmentation of pitting defects in ball screws.The network consists of an encoder,a multi-level decoder and a Multi-scale Attention module.The encoder is composed of Resnet34,and the Ghost module is introduced to build a lightweight multi-level decoder.In order to fuse multi-scale features and filter redundant information,the Multi-scale Attention module is designed.A hybrid loss function composed of BCE function,IOU and SSIM function is used to train the network.Experiments on the ball screw defect dataset show that Multi-level decoding neural network achieves 0.7703 in the maxF_(β) metrics,compared with other methods,which achieves better segmentation results,and the processing time of a single image is 26 ms.It provides a new method for real-time segmentation of ball screw pitting defects.

关 键 词：滚珠丝杠 缺陷检测 神经网络 图像分割 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]