| Enameled wire is one of the important raw materials for modern industrial production.Its quality determines the comprehensive performance of downstream products.Traditional manual detection methods can no longer meet the needs of industrial production.With the advancement of science and technology,machine vision is becoming more and more mature.In this paper,machine vision detection technology is applied to enameled wire diameter measurement and paint film continuity inspection,and a mobile enameled wire online inspection system based on machine vision is designed to realize non-contact inspection.The system has the characteristics of fast detection speed,high measurement accuracy,and a wide application range.The research results help to improve the quality of enameled wire and provide a reference for the improvement and optimization of the enameled wire production process.The main contents of this paper are as follows:(1)Through enterprise research,combined with the existing enameled wire production process,the overall framework of the detection system was designed.First,the UG NX10.0 software was used to build a three-dimensional model of the system;then,the static analysis was carried out on the Y-axis slider with a large force and the beam assembly with a large bending moment,and the feasibility of the structure was theoretically verified;Finally,combined with the needs of enterprise applications,choose appropriate industrial cameras,lenses,light sources,PLC controllers and industrial control all-in-one computers to build a hardware system.(2)Aiming at the problem that the vibration amplitude of the enameled wire is too large,from the perspective of the system hardware,a movable enameled wire hooking mechanism is designed,which can automatically hook the enameled wire to the fixed wheelset during detection,which is convenient for the camera to collect images.Experimental results It is shown that the mechanism effectively reduces the amplitude of the enameled wire to within 0.1mm;the calibration principle of the camera is analyzed,and the needle gauge with an accuracy of ±0.001 mm is used as the calibration object of the system,and the calibration experiment of the system is completed;by comparing the machine vision The commonly used image preprocessing and Blob analysis methods in the paper,ROI extraction,threshold segmentation,median filtering,and eigenvalue calculation algorithms are applied to the enameled wire image,and the identification and localization of the enameled wire image are completed.(3)The existing sub-pixel edge detection algorithms are analyzed.According to the design idea of "first coarse and then fine",the interpolation method based on the Canny operator and the least square method are used to complete the measurement of the wire diameter of the enameled wire;through the analysis For the problem of discontinuous paint film on the surface of enameled wire,a combination of sub-pixel edge detection algorithm and the curve-fitting algorithm is used to realize the continuous detection of the enameled wire paint film.(4)Analyze the mainstream machine vision software in the market,choose Visual Studio 2022 development platform,design inspection software in combination with HALCON 18.05 image processing toolkit,choose TIA Portal V15.1 software,and design inspection software in combination with Win CC V7.4 system;adopt Siemens The PLC controller controls the positioning motor and the wire hooking motor and realizes the real-time communication between the upper computer and the lower computer through the S7 protocol,to achieve the effect of automatic inspection of 36 enameled wire stations;through the design of software and hardware,the system prototype is assembled.,and completed the stability test,single enameled wire test,and online ability test.The test results show that the absolute error of the system prototype detection is 0.02μm,and the relative error is 0.008%,which meets the production requirements of the enterprise. |
PDF Full Text Request