燃料电池陶瓷电芯表面缺陷自动检测装置设计  

Design of Automatic Detection Device for Surface Defects of Fuel Cell Ceramic Cells

作　　者：张金星 周瑾 李炳熹 张建锋[1] 吴剑[2] ZHANG Jinxing;ZHOU Jin;LI Bingxi;ZHANG Jianfeng;WU Jian(College of Optical,Mechanical and Electrical Engineering,Zhejiang A&F University,Hangzhou,Zhejiang 311300,China;College of Mathematics and Computer Science,Zhejiang A&F University,Hangzhou,Zhejiang 311300,China)

机构地区：[1]浙江农林大学光机电工程学院,浙江杭州311300 [2]浙江农林大学数学与计算机科学学院,浙江杭州311300

出　　处：《自动化应用》2025年第6期228-232,235,共6页Automation Application

基　　金：浙江省科技计划重点项目(2021C01100);浙江农林大学校级学生科研创新训练项目(S202210341233)。

摘　　要：针对固体氧化物燃料电池陶瓷电芯表面缺陷人工目检法存在的劳动强度大、误判率高等问题,搭建了基于PLC的陶瓷电芯表面缺陷自动检测装置。装置基于Visual C++和Halcon机器视觉库开发陶瓷电芯表面缺陷的识别算法,以PLC作为下位机主控制器,使用DOP-07BV触摸屏作为人机交互界面,灵活分配PLC控制系统的I/O地址以实现对系统主要软硬件的调控,并以检出率、误检率、漏检率和精确率等作为评价指标进行试验验证。结果表明,所开发装置响应速度块、工作平稳效率高,表面缺陷检测准确率保持在93%以上,基本满足陶瓷电芯表面检测的工作需求;与人工检测相比,整体检测准确率提升了2.43个百分点以上,在检出率、误检率和漏检率等方面也有明显提升。A PLC based automatic detection device for surface defects of ceramic cells in solid oxide fuel cells has been developed to address the issues of high labor intensity and high misjudgment rate in manual visual inspection methods.The device is based on Visual C++and Halcon machine vision library to develop a recognition algorithm for surface defects of ceramic cells.The PLC is used as the main controller of the lower computer,and the DOP-07BV touch screen is used as the humancomputer interaction interface.The I/O addresses of the PLC control system are flexibly allocated to achieve control of the main software and hardware of the system.The detection rate,false detection rate,missed detection rate,and accuracy rate are used as evaluation indicators for experimental verification.The results show that the developed device has high response speed,smooth operation,and high efficiency.The accuracy of surface defect detection remains above 93%,which basically meets the work requirements of ceramic cell surface detection.Compared with manual detection,the overall detection accuracy has increased by more than 2.43 percentage points,and there have also been significant improvements in detection rate,false detection rate,and missed detection rate.

关 键 词：陶瓷电芯 表面缺陷 可编程逻辑控制器 机器视觉 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]