این سایت در حال حاضر پشتیبانی نمی شود و امکان دارد داده های نشریات بروز نباشند
Iranian Journal of Mechanical Engineering Transactions of the ISME، جلد ۲۶، شماره ۲، صفحات ۶-۳۴
عنوان فارسی
چکیده فارسی مقاله
کلیدواژه‌های فارسی مقاله
عنوان انگلیسی Integrating Adaptive Sliding Mode Control and Deep Learning for Autonomous Vision-driven Fruit Sorting robot
چکیده انگلیسی مقاله This article presents a novel application of deep learning in automated fruit-sorting robotics, improving real-time object recognition and handling. By integrating advanced neural networks, the robot achieves higher accuracy in identifying various fruits, addressing fruit variability and enhancing sorting precision. This innovation, combining deep learning and visual servoing, represents a significant advancement in automated fruit-sorting technology, with promising benefits for agricultural processes. The project aims to control a fruit-sorting robot using image processing data, merging sliding mode control and NN-based (neural network-based) techniques for automation. Utilizing the latest YOLO (You Only Look Once) model, the system classifies and positions fruits rapidly and accurately, making it suitable for real-time applications. After identifying fruit types and positions, a controller is designed for the pick-and-place process. Sliding mode control manages uncertainties and guides manipulator movements precisely, while a neural network controls joint angles for smooth and accurate fruit manipulation. Comparative tests on a simulated robot revealed that the NN-based controller excels in accuracy and speed, adapting to different fruit configurations effectively. The sliding mode controller, though robust and stable, is sensitive to uncertainties, affecting sorting precision. The hybrid system, integrating both controllers, enhances adaptability by combining the NN-based approach's precision with the stability of sliding mode control, optimizing fruit-sorting performance across diverse scenarios. Results emphasize selecting the appropriate controller to balance precision and speed based on specific application needs.
کلیدواژه‌های انگلیسی مقاله Fruit detection,NN-based control,Adaptive sliding mode control,Visual servoing
نویسندگان مقاله Hassan Sayyaadi |
Professor, Department of Mechanical Engineering, Sharif University of Technology, Tehran, Iran

Sara Adeli |
M.Sc., Student, Department of Mechanical Engineering, Sharif University of Technology, Tehran, Iran

نشانی اینترنتی https://jmee.isme.ir/article_723291_e0f8a6e566ae12d46ba682fb3c7b775c.pdf
فایل مقاله فایلی برای مقاله ذخیره نشده است
کد مقاله (doi)
زبان مقاله منتشر شده en
موضوعات مقاله منتشر شده
نوع مقاله منتشر شده
برگشت به: صفحه اول پایگاه   |   نسخه مرتبط   |   نشریه مرتبط   |   فهرست نشریات