Image processing and feature extracting of welding seam misalignment for highfrequency welded pipe
1.School of Mechanical and Power Engineering, Nanjing University of Technology, Nanjing, Jiangsu 210009, China; 2.Post Doctorate Work Station, Zhejiang Kingland Pipeline Science and Technology Limited Company, Huzhou, Zhejiang 313000, China; 3.Key Laboratory of Nonferrous Metal Alloys and Processing of Ministry of Education, Lanzhou University of Technology, Lanzhou, Gansu 730050, China
Abstract：To obtain real time detection of unfitness defect in highfrequency weld(HFW) pipe, a CCD visual measurement system was developed. The characteristic of the unfitness defect in captured image was analyzed. The image processing of misalignment was conducted by morphology method to extract edge image and the width and brightness of welding seam. The results show that the width and brightness of welding seam can be used as characteristic parameters to detect the unfitness defect in HFW pipe and to establish a visual system for inspecting welding unfitness. At the LabVIEW virtual instrument, the controlled temperature system of HFW pipe was established by colorimetric temperature measurement to realize controlled temperature test. The test results show that the influences of dust, moisture and other interference factors on temperature measurement can be better reduced by colorimetry temperature measurement mode to improve the stability and precision of temperature. At the basis of stable and accurate temperature measurement, the effective temperature control system can be realized.
2012, Vol. 33 
