2014 | OriginalPaper | Chapter
An Novel Quality Classification for Ring Die Pellet
Authors : Kun Zhang, Minrui Fei, Jianguo Wu, Peijian Zhang
Published in: Life System Modeling and Simulation
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Ring die granulator is a high energy consumption and complex system. Conventional method for improvement the quality of pellets is detected by human sense offline. Aimed to lowness of efficiency and bigness of error, a novel strategy is present for the intelligence quality classification. By means of machine vision, after extract the feature, the pellet edge images are captured based canny algorithm, and the quality classification can be accuracy got by FSVM. Real pellet images are conducted to prove the effect. Compared with other methods by the simulation, the present approach has apparent advantages. The result of the present work implied that, the present method can be applied to auto quality detection and the classification results can be used as the feedback signals in controller to update the parameters to control the ring die granulator well.