رویکرد بینایی ماشین به‌عنوان یک سامانه ضدخطا در ایستگاه هم‌بندی یاتاقان متحرک خط تولید موتور

نوع مقاله : مقاله پژوهشی

نویسنده

عضو هیئت علمی، گروه مهندسی کشاورزی، دانشگاه فنی و حرفه ای، تهران، ایران

چکیده

این مقاله به ارائه یک روش بینایی ماشین برای تشخیص خطای نصب یاتاقان شاتون (متحرک) در موتورهای چهار سیلندر می­ پردازد. از آنجایی که همواره خطاهای انسانی در خطوط تولید موتور وجود دارد که باعث کاهش کیفیت محصول نهایی می ­شود، راه اندازی سیستم ­های بینایی ماشین هوشمند به منظور رصد فرایند همبندی قطعات و جلوگیری از خطاهای نصب بسیار لازم است. روش پیشنهادی به این صورت است که با گرفتن تصویر بدنه موتور، یک تصویر دودویی ایجاد می ­کند که کل تصویر سیاه بوده و فقط محل­ هایی که یاتاقان ­های متحرک وجود دارد سفید است، و همچنین اعلام می کند که کدام یاتاقان­ ها وجود دارند و کدام ­ها نصب نشده ­اند. بدین منظور ابتدا تصاویر 16 حالت مختلف از نصب یاتاقان توسط دوربین گرفته شد. سپس تمام تصاویر با ترکیبی از روش‌های پردازش تصویر شامل فیلتر گاوسی، آستانه‌گذاری و بخش‌بندی تصویر، و تکنیک‌های ریخت ­شناسی از جمله فرسایش و گسترش تجزیه و تحلیل شدند. در نهایت، با اعمال قواعد اگر-آنگاه در مورد ویژگی­ های اشیاء ایجاد شده در تصویر، وضعیت آن تصمیم ­گیری شد. نتایج نشان داد که بهترین محدوده آستانه برای جداسازی یاتاقان از سایر قسمت‌های تصویر بین 110 تا 245 است. همچنین یک المان ساختاری دیسکی شکل با شعاع 60، بهترین ابزار ریخت شناسی برای تشخیص یاتاقان‌ها را ارائه داد. علاوه بر این، نتایج نشان داد که نواحی متعلق به یاتاقان‌های متحرک مساحتی بین 30  تا حدود 80 هزار پیکسل داشتند. با استفاده از قواعد اگر-آنگاه، حالات مختلف نصب یاتاقان در تمام تصاویر، به طور موفقیت آمیز با دقت 100 درصد تشخیص داده شد. کل زمان تجزیه و تحلیل هر تصویر حدود 1 ثانیه بود. بنابراین نتایج نشان داد که سامانه بینایی ماشین پیشنهادی، ابزاری بدون خطا و سریع برای تشخیص وجود یاتاقان‌های متحرک را فراهم می‌کند که می‌تواند به عنوان یک سامانه ضدخطا در خط تولید موتور مورد استفاده قرار گیرد.
 

کلیدواژه‌ها


عنوان مقاله [English]

The Machine Vision Approach as a Poka-Yoke System in Conrod Bearing Assembly Station of Engine Production Line

نویسنده [English]

  • Ashkan Moosavian
Assistant Professor, Department of Agricultural Engineering, Technical and Vocational University (TVU), Tehran, Iran
چکیده [English]

This paper presents a machine vision approach to detect the installation error of conrod bearing in four-cylinder engines. Since there are always human errors in engine production lines that would reduce the quality of the final product, it is vital to establish the intelligent machine vision systems in order to track the process of assembling parts and prevent installation errors. The proposed method is such that by taking an engine block image, it produces a binary image that the whole image is black and only the places where conrod bearings exist are white, and also it announces which bearings are present and which ones are not installed. To this end, firstly the images of 16 different bearing installation cases were captured by camera. Then, all images were analyzed with a combination of image processing methods including Gaussian filtering, image thresholding and segmentation, and morphological techniques including erosion and dilation. Finally, with applying if-then rules on the characteristics of the objects created in the image, its condition was decided. The results showed that the best threshold range for separating the bearing from other parts of image was between 110 and 245. Also a disk-shaped structuring element with the radius of 60 provided the best morphological tool to detect the bearings. In addition, the results demonstrated that the regions belonged to conrod bearings had an area between 30,000 and about 80,000 pixels. With using if-then rule, the different bearing installation cases in all images were successfully detected with 100% accuracy. The total time for analyzing each image was about 1 s. So the results showed that the proposed machine vision system provided a non-error and fast tool for detecting the existence of conrod bearings which can be served as a Poka-Yoke system in the engine production line.
 

کلیدواژه‌ها [English]

  • Machine vision
  • IC Engine
  • Conrod Bearing
  • Image Segmentation
  • Morphology
[1] Y. Le, S. Qiang, S. Liangfa, A novel method of analyzing quality defects due to human errors in engine assembly line,  2012 International Conference on Information Management, Innovation Management and Industrial Engineering, IEEE, pp. 154-157, 2012.
[2] H. Robinson, Using Poka-Yoke techniques for early defect detection, Sixth International Conference on Software Testing Analysis and Review, pp. 134-145, 1997.
[3] N. Belu, L. Ionescu, A. Misztal, and A. Mazăre, Poka yoke system based on image analysis and object recognition, in IOP Conference Series: Materials Science and Engineering, IOP Publishing, Vol. 95, No. Issue, pp. 012138, 2015.
[4] S. Widjajanto, H.H. Purba and S.C. Jaqin, Novel poka-yoke approaching toward industry-4.0: A literature review, Operational Research in Engineering Sciences: Theory and Applications, Vol. 3, No. 3, pp. 65-83, 2020.
[5] T.A. Saurin, J.L.D. Ribeiro and G. Vidor, A framework for assessing poka-yoke devices, Journal of Manufacturing Systems,  Vol. 31, No. 3, pp. 358-366, 2012.
[6] R. Kashyapa, Machine vision guide for automotive process automation, Auto Tech Review,  Vol. 5, No. 8, pp. 14-15, 2016.
[7] B.G. Batchelor, Machine vision handbook, Springer, 2012.
[8] H. Golnabi, A. Asadpour, Design and application of industrial machine vision systems, Robotics and Computer-Integrated Manufacturing, Vol. 23, pp. 630-637, 2007.
[9] X. Wang, W. Zhang, X. Wu, L. Xiao, Y. Qian, Z. Fang, Real-time vehicle type classification with deep convolutional neural networks, Journal of Real-Time Image Processing, Vol. 16, pp. 5-14, 2019.
[10] A.J. Malekabadi, M. Khojastehpour, B. Emadi, M.R. Golzarian, Development of a machine vision system for determination of mechanical properties of onions, Computers and Electronics in Agriculture, Vol. 141, pp. 131-139, 2017.
[11] M. Abdollahpour, M.R. Golzarian, A. Rohani, H.A. Zarchi, Development of a machine vision dual-axis solar tracking system, Solar Energy, Vol. 169, pp. 136-143, 2018.
[12] C. Beltrán-González, M. Bustreo, A. Del Bue, External and internal quality inspection of aerospace components, 2020 IEEE 7th International Workshop on Metrology for AeroSpace (MetroAeroSpace), IEEE, pp. 351-355, 2020.
[13] A. Esteva, K. Chou, S. Yeung, N. Naik, A. Madani, A. Mottaghi, Y. Liu, E. Topol, J. Dean, R. Socher, Deep learning-enabled medical computer vision, NPJ digital medicine, Vol. 4, pp. 1-9, 2021.
[14] A. Solana-Altabella, M. Sánchez-Iranzo, J. Bueso-Bordils, L. Lahuerta-Zamora, A.M. Mellado-Romero, Computer vision-based analytical chemistry applied to determining iron in commercial pharmaceutical formulations, Talanta, Vol. 188, pp. 349-355, 2018.
[15] L. Deepak, R. Balakrishnan, An accurate and robust method for the honing angle evaluation of cylinder liner surface using machine vision, The International Journal of Advanced Manufacture Technology, Vol. 55, pp. 611-621, 2011.
[16] R. Kanna, M. Saravana, Intelligent vision inspection system for IC engine head: an ANN approach, Advanced Materials Research, Trans Tech Publ, pp. 2242-2245, 2012.
[17] K.D. Lawrence, R. Shanmugamani and B. Ramamoorthy,  Evaluation of image based abbott–firestone curve parameters using machine vision for the characterization of cylinder liner surface topography, Measurement,  Vol. 55, pp. 318-334, 2014.
[18] M. Costa, D. Piazzullo, U. Sorge, S. Merola, A. Irimescu, V. Rocco, Image processing for early flame characterization and initialization of flamelet models of combustion in a gdi engine, SAE Technical Paper, 2015.
[19] H. Chen, Y. Hou, X. Wang, Z. Pan, H. Xu, Characterization of in-cylinder combustion temperature based on a flame-image processing technique, Energies, Vol. 12, pp. 2386, 2019.
[20] F. Xuyun, L. Hui, S. Zhong, and L. Lin, Aircraft engine fault detection based on grouped convolutional denoising autoencoders, Chinese Journal of Aeronautics, Vol. 32, No. 2, pp. 296-307, 2019.
[21] S. Capela, R. Silva, S.R. Khanal, A.T. Campaniço, J. Barroso, V. Filipe, Engine labels detection for vehicle quality verification in the assembly line: a machine vision approach, Portuguese Conference on Automatic Control, Springer, pp. 740-751, 2020.
[22] C. Angermann, S. Jónsson, M. Haltmeier, A. Moravová, C. Laubichler, C. Kiesling, M. Kober, W. Fimml, Machine Learning for Nondestructive Wear Assessment in Large Internal Combustion Engines, arXiv preprint arXiv:2103.08482, 2021.
[23] A. Moosavian, A. Hosseini, S.M. Jafari, I. Chitsaz, and S. Baradaran Shokouhi, Machine vision–based measurement approach for engine accessory belt transverse vibration based on deep learning method, Automotive Science and Engineering,  Vol. 12, No. 2, pp. 3838-3846, 2022.
[24] M. Sonka, V. Hlavac, R. Boyle, Image processing, analysis, and machine vision, Fourth ed., Cengage Learning, 2014.
[25] R.C. Gonzalez, R.E. Woods, Digital Image Processing, Pearson Education, 2018
[26] M.R. Golzarian, F. Kazemi, Z. Hajiabolhasani, Digital image processing from principles to implementation using matlab, Ferdowsi University of Mashhad, Mashhad, 2014.