نوع مقاله : مقاله پژوهشی
نویسندگان
1 ادارة مهندسی محصول، شرکت تحقیق، طراحی و تولید موتور ایران خودرو (ایپکو)، تهران، ایران
2 گروه مهندسی کشاورزی، دانشگاه فنی و حرفه ای، تهران، ایران
چکیده
کلیدواژهها
موضوعات
عنوان مقاله [English]
نویسندگان [English]
The adaption of main bearings with crankshaft grades is an important consideration in bearing installation task. If operator is not careful, it will cause a significant decrease in quality of the final assembled engine and also make some defects on it. Machine vision systems have the potential to implement autonomous error detection that can significantly reduce inspection time and lead to more frequent, precise and objective inspections. Herein, an inspection system was developed, capable of automatically detecting crankshaft grades from crankshaft images. A specific lighting condition was designed to obtain proper images of the crankshafts. An efficient diagnostic approach based on semantic segmentation method, was presented in this regard. Two different convolutional neural network (CNN) architectures, including: MobileNet and VGG19 were trained and evaluated. MobileNet revealed to be the best compromise between accuracy, with an IoU-Score of 85%, and validation time, with 0.2 ms for discovering the characters engraved on the crankshaft. According to the obtained results, the proposed approach could be used as efficient, accurate and fast tool for automatic detection of crankshaft grades in bearing assembly station.
کلیدواژهها [English]