Abstract The appearance of defects in cylindrical metal pipe fittings during the production process is random, and it is difficult for traditional mono- and binocular machine vision systems to acquire the full-surface information of the pipe fittings, an on-line image acquisition scheme for the full surface of the pipe fittings is proposed to realize high-quality and all-round imaging information collection. Firstly, by acquiring the two-dimensional image captured by a single camera, establishing the correspondence between the two-dimensional image and the surface covered by the column, calculating the actual pipe surface coverage angle corresponding to the two-dimensional image, and judging the number of cameras required to acquire the full-surface information of pipe fittings, we adopt multi-camera coordination with the real-time acquisition of the image in the clockwise direction of the disk. Secondly, a multi-factor experimental program is established based on the response surface design method to evaluate the effects of aperture value, exposure time and gain of the camera lens on image quality. The optimal camera parameters of cylindrical side camera and cylindrical ends camera are determined at the acceptable maximum speed to reduce the influence of motion blur and improve the efficiency of shooting. Finally, based on the optimal parameters, the images of metal pipe fittings are acquired and evaluated on-line in real-time to retain better quality images of pipe fittings. The experimental results meet the requirements of high-quality, fine defects clear metal surface defect detection data, and lay a foundation for the subsequent study of real-time defect detection of cylindrical metal pipe fittings.
TAO Guohao,LIU Zihao,XU Xiaomeng, et al. Construction of On-line Image Acquisition Device for Cylindrical Metal Pipe Fittings and Control Optimization of Key Parameters[J]. Acta Metrologica Sinica, 2024, 45(10): 1494-1501.
BAO Y D, WU L K, DAI Y, et al. Research on surface image acquisition system of train bearing cylindrical roller［J］. Journal of Mechanical Science and Technology, 2022, 36(8): 4353-4361.
［6］
WEN S, CHEN Z, LI C. Vision-Based Surface Inspection System for Bearing Rollers Using Convolutional Neural Networks［J］. Applied Sciences, 2018, 8(12): 2565-2565.
［7］
TAO J, ZHU Y, JIANG F, et al. Rolling Surface Defect Inspection for Drum-Shaped Rollers Based on Deep Learning［J］. IEEE Sensors Journal, 2022, 22(9): 8693-8700.
ZHANG S W, ZHONG Z Y , ZHU D H. Surface defect detection method of metal gear based on improved YOLOx network［J］. Advances in laser and optoelectronics, 2023, 60(22): 280-290.
［9］
XU L M, YANG Z Q, JIANG Z H, et al. Light source optimization for automatic visual inspection of piston surface defects［J］. The International Journal of Advanced Manufacturing Technology,2017, 91(5): 2245-2256.
MENG Y D, TANG S L, FU Y H. Design of Valve Offset Detection Device based on photoelectric Signal ［J］. Automotive Parts, 2022, 17(4): 79-81.
［13］
田海东. 铝合金薄壁结构件铣削变形预测与工艺参数优化［D］. 济南: 山东大学, 2020.
YU F C, ZHANG D, FAN X, et al. Research and Application of Machine Vision in Assembly Process of Pump Body mouth Ring ［J］. Modern Manufacturing Engineering, 2022, 45(3): 133-139.
JIN K, CHEN X R. Research on Measurement of Geometric Parameters of Optical Fiber Endface Based on Machine Vision［J］. Acta Metrologica Sinica, 2023, 44(2): 165-170.
SUN Y C. Design and Simulation of intelligent classification Stereoscopic Garage based on PLC ［J］. Science and Technology Innovation and Productivity, 2022, 43(10): 50-52.
JU B. High precision vision measuring instrument based on Telecentric lens ［J］. Ornological Industry Automation, 2014, 33(8): 82-86.
［20］
TAHERI A, YENTZER B A, FELDMAN S R. Focusing and depth of field in photography: application in dermatology practice［J］. Skin Research and Technology, 2013, 19(4): 394-397.
XIONG X M, WANG X X, REN X X. Application research of Laser Displacement Sensor in Wafer Detection ［J］. Automation & Instrumentation, 2022, 42(8): 7-12.
CAI R, LI Y, LIU Z S, et al. Analytical calculation formula of electromagnetic field quantity of external inspection type electromagnetic ultrasonic guided wave transducer for metal pipe fittings［J］. Chinese Journal of applied Mechanics, 2021, 38(2): 538-544.
SU L, WANG L J, QI Y, et al. Metal surface defect detection based on IADSA deep migration network［J］. Journal of Mechanical Engineering, 2023, 71(23): 1-10.
［10］
FEYZA C, SERAP K, MUHAMMED A O, et al. Online metallic surface defect detection using deep learning［J］. Emerging Materials Research, 2020, 9(4): 1266-1273.
ZHOU W B. Discussion on the Application of Intelligent Industrial Camera ［J］. Electronic Testing, 2018, 25(22): 135-136.
ZHANG D D, ZHAO Y H. Review of natural image quality evaluation methods ［J］. Computer Knowledge and Technology, 2019, 16(9): 203-205.
［8］
TIAN H, WANG D, LIN J, et al.Surface Defects Detection of Stamping and Grinding Flat Parts Based on Machine Vision［J］.Sensors,2020,20(16):4531-4531.
HAN X C, PAN Y, XIE Y D, et al. Study on evaluation of appearance quality of exposed concrete by UAV image acquisition ［J］. Materials Review, 2019, 35(S2): 205-212.
LI Y F, CHEN N N, ZHANG J C. A fast and highly sensitive focusing evaluation function［J］. Application Research of Computers, 2010, 27(4): 1534-1536.
2024, Vol. 45 
