Transactions of Materials and Heat Treatment

Title：On-line detection method for wrinkling defect of conical spinning parts based on machine vision

Authors： Li Yongting Xia Qinxiang Xiao Gangfeng Cheng Xiuquan

Unit： South China University of Technology Guangzhou Civil Aviation College

KeyWords： conical parts shear spinning wrinkling defect machine vision on-line detection

ClassificationCode：TP391.4

year,vol(issue):pagenumber：2019,44(1):134-141

Abstract：

Fast and accurate online detection method of forming defects is the basis to realize intelligence of spinning. Based on machine vision, an on-line detection method of wrinkling defect was proposed by studying the wrinkling characteristics and image detection process, and the method was applied to on-line detection of wrinkling defect during shear spinning process of conical parts. Then, the on-line image acquisition system of spinning was constructed, and the real-time images of spinning parts during forming were acquired. Furthermore, the images were pre-processed by Halcon software, including ROI extraction and histogram equalization, and high-contrast and clear images were obtained. Finally, the traditional Canny edge detection algorithm was improved by Otsu method, the high and low thresholds of images were determined automatically according to image gradient, and the image contours of conical parts were extracted accurately. According to the number and size of ripples at the outline of mouth after wrinkling of conical spinning parts, the detection algorithm of wrinkling defect was designed, and the wrinkling defects of conical parts were detected successfully. Meanwhile, the reliability of wrinkling detection algorithm was verified by shear spinning experiment. The results show that the wrinkling defect can be detected accurately and fast by the proposed method, and the whole detection process takes 0.225 s on average, which can satisfy the demand of online detection.

Funds：

广东省自然科学基金博士启动纵向协同项目(2017BQ019)；国家自然科学基金青年科学基金项目(51705159)；中国博士后科学基金项目(2017M622678)

李永婷(1994-)，女，硕士研究生，E-mail：1072690167@qq.com；通讯作者：夏琴香(1964-)，女，博士，教授，E-mail:meqxxia@scut.edu.cn

Reference：

[1]夏琴香.特种旋压成形技术[M].北京：科学出版社，2017.

Xia Q X.Special Spinning Forming Technology [M].Beijing：Science Press，2017.

[2]Xia Q X，Xiao G F，Long H，et al.A review of process advancement of novel metal spinning [J].International Journal of Machine Tools & Manufacture，2014，85：100-121.

[3]夏琴香，周立奎，肖刚锋，等.工艺参数对高强钢锥形件剪切旋压成形质量的影响[J].锻压技术，2017，42(2)：77-81.

Xia Q X，Zhou L K，Xiao G F，et al.Influence of process parameters on shear spinning quality for high strength steel conical parts[J].Forging & Stamping Technology，2017，42(2)：77-81.

[4]Wong C C，Dean T A，Lin J.A review of spinning shear forming and flow forming processes [J]. International Journal of Machine tools and Manufacturing，2003，43（14）：1419-1435.

[5]郭静，罗华，张涛.机器视觉与应用[J]. 电子科技，2014，27(7)：185-188.

Guo J，Luo H，Zhang T.Machine vision and applications[J].Electronic Science and Technology，2014，27(7)：185-188.

[6]陈英.机器视觉检测技术在工业检测中的应用[J].电子测试，2015，(18)：79-80.

Chen Y.Machine vision inspection technology in industrial applications detection[J].Electronic Test，2015，(18)：79-80.

[7]Shen H，Li S X，Gu D Y，et al.Bearing defect inspection based on machine vision[J]. Measurement，2012，45 (4)：719-733.

[8]Liu Y，Yu F.Automatic inspection system of surface defects on optical IRCUT filter based on machine vision[J].Optics & Lasers in Engineering，2014，55(7)：243-257.

[9]Arjun P，Mirnalinee T T.Machine parts recognition and defect detection in automated assembly systems using computer vision techniques[J].Revista Tecnica de la Facultad de Ingenieria Universidad del Zulia，2016，39(1)：71-80.

[10]周江，任锟，帅英琦，等.基于机器视觉的磁钢片缺陷检测研究[J].机电工程，2014，31(12)：1541-1546.

Zhou J，Ren K，Shuai Y Q，et al.Machine vision based defect detection on magnetic steel sheet[J].Journal of Mechanical & Electrical Engineering，2014，31(12)：1541-1546.

[11]Han B A，Xiang H Y，Li Z，et al.Feature size measurement of multihole sheet metal part based on HALCON[J].Applied Mechanics and Materials，2013，302：546-549.

[12]袁源，樊万梅.基于背景统计的ROI提取方法[J].重庆理工大学学报：自然科学，2012，26(3)：89-92.

Yuan Y，Fan W M.A method for ROI extraction based on background statistics[J].Journal of Chongqing University of Technology：Natural Science，2012，26(3)：89-92.

[13]Jafar I，Ying H.New algorithms for contrast enhancement in grayscale images based on the variational definition of histogram equalization [J].Integrated ComputerAided Engineering，2008，15(2)：131-147.

[14]Gonzalez R C, Woods R E. 数字图像处理[M].阮秋琦，阮宇智，等译.第3版.北京：电子工业出版社，2011.

Gonzalez R C,Woods R E. Digital Image Processing [M].Translated by Ruan Q Q，Ruan Y Z，et al.The Third Edition. Beijing：Publishing House of Electronics Industry，2011.

[15]Bao P，Zhang D，Wu X.Canny edge detection enhancement by scale multiplication[J].Pattern Analysis and Machine，2005，27(9)：957-961.

[16]Otsu N.Threshold selection method from graylevel histogram[J].IEEE Transactions on Systems,Man,and Cybernetics，1979，9(1)：62-66.

[17]唐路路，张启灿，胡松.一种自适应阈值的Canny边缘检测算法[J].光电工程，2011，38(5)：127-132.

Tang L L，Zhang Q C，Hu S.An improved algorithm for Canny edge detection with adaptive threshold[J].OptoElectronic Engineering，2011，38(5)：127-132.

[18]翟俊海，赵文秀，王熙照.图像特征提取研究[J].河北大学学报：自然科学版，2009，29(1)：106-112.

Zhai J H，Zhao W X，Wang X Z.Research on the image feature extraction[J].Journal of Hebei University：Natural Science，2009，29(1)：106-112.

Service：

【This site has not yet opened Download Service】【Add Favorite】