Quality Analysis of high-density polyethylene based on Intelligent Vision Detection

Abstract

High-density polyethylene (HDPE) are colorless and transparent particles, which are critical raw materials of many plastic products. HDPE particles with defects would affect the quality of final products and the economic benefits of enterprises. At present, there is lack of methods to identify defective HDPE particles quickly and efficiently. To address above problems, intelligent vision detection is introduced into the quality analysis of HDPE, and a set of quality analysis and detection schemes of HDPE are designed in this paper. Firstly, for obtaining better imaging quality, analysis and selection of the background color of the detection scenario is conducted. Secondly, particle conveying and photographing sensing strategy is designed for upgrading production line. Thirdly, intelligent detection of defective particles based on YOLO is merged into the analysis system. According to the experiment results, the blue color is selected as the optimal background. The recognition accuracy reaches 99.39% with the blue background color samples, thus defect particles of HDPE could be detected and identified effectively.