小样本问题下的铣削表面粗糙度测量  

Milling Surface Roughness Measurement Under Few-Shot Problem

作　　者：易怀安 方润基 舒爱华 路恩会 Yi Huaian;Fang Runji;Shu Aihua;Lu Enhui(School of Mechanical and Control Engineering,Guilin University of Technology,Guilin 541006,Guangxi,China;School of Foreign Languages,Guilin University of Technology,Guilin 541006,Guangxi,China;School of Mechanical Engineering,Yangzhou University,Yangzhou 225009,Jiangsu,China)

机构地区：[1]桂林理工大学机械与控制工程学院,广西桂林541006 [2]桂林理工大学外国语学院,广西桂林541006 [3]扬州大学机械工程学院,江苏扬州225009

出　　处：《激光与光电子学进展》2022年第23期255-261,共7页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(52065016);2021广西研究生创新项目(YCSW2021204);桂林理工大学博士启动基金(GLUTQD2017060)。

摘　　要：基于机器视觉的粗糙度测量方法大多是根据粗糙度关联指标建立预测模型,或者利用深度学习网络建立无指标预测模型,而这两类方法均存在着不足。一方面,人工设计指标的计算过程复杂,不利于在线检测。另一方面,深度学习模型则严重依赖大数据,数据量不足难以训练出有效的模型。针对以上问题,本文提出一种基于图神经网络的铣削表面粗糙度测量方法。该方法在训练阶段获取了自主学习的能力,而后仅需要少量铣削样本就能够完成铣削工件的粗糙度测量。试验结果表明,本文方法在铣削工件的粗糙度测量上不仅能够自动提取特征,而且表现出了较高的精度和良好的光照环境鲁棒性。Most machine vision-based roughness measurement methods either build a prediction model based on roughness correlation indices or build an index-free prediction model using deep learning networks.However,both these models have disadvantages.The artificial designed index has a complicated calculation process,which is not conducive to inline detection.In comparison,deep learning models rely heavily on big data.It is difficult to train an effective model when the amount of data is insufficient.To address the above problems,this study proposes a graph neural network-based method for measuring the roughness of milling surfaces.This proposed approach acquired the ability to learn autonomously during the training phase.Thus,only a few milling samples were required to measure the roughness of the milling workpieces.The experimental results show that the proposed method can automatically extract features on roughness measurement of milling workpieces with high accuracy and good robustness of lighting environment.

关 键 词：表面粗糙度测量 图神经网络 小样本问题 特征自提取 光照环境 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]