Research On Vision Detection System For Quality Of Infusion Cover Products

Infusion cover is a commonly used medicine packing materials for the plastic infusion of encapsulation, directly contacted with the liquid medicine, the assemble quality and clean degree of infusion cover directly affect the use safety of liquid medicine, and is closely related to the safety of people’s life. Therefore, required strictly control the production quality of the infusion cover. Accordingly, this paper use vision detection technology, focus on the online automation detection method for the contour, assemble quality, clean degree of infusion cover, developed a high speed vision automatic detection machine, and successfully apply to the automatic production line of infusion cover, replace the traditional manual detection methods, avoid secondary pollution, ensure the production quality of the infusion cover greatly enhance the production efficiency and automatic level of manufacturers, have great social and economic benefits. The main research work of this paper as below:Firstly, this paper elaborated the background information and manual detection status of infusion cover, analysis of the advantages of online visual detection. Then the definition of machine vision and the compositions of vision system are introduced, meanwhile the application of machine vision in all aspects of our life and production is also presented.Secondly, after analysis of the system design requirements and the characteristics of the detection object, designed a visual imaging solutions and selected the key components of the light source, camera, lens etc, and designed with its matching mechanical execution system and electrical control system; Designed a unique set of sorting device uses airflow blowing type and infusion cap feeding track, detailed analysis of troubleshooting, time sharing signal control and signal rotary shifter and other key technologies of the electrical control system.Based on the quality detection algorithm of product of infusion cover, for different characteristics of the cover testing, gasket and finished product testing of infusion cap,3 sets of complete and embodiment of the detection algorithm is designed:Cover detected by self-difference algorithm based on image rotation and mirroring, accurate extraction to quality defects of cover; The gasket detection determine the gasket position whether level off based on the roundness of the gasket edge contour; firstly, finished product detected by bidirectional projection method to determine the center of two geometric characteristics, threading search method used by the geometric characteristics to get Eigen values, lastly, feature fuzzy decision method to determine the eligibility of the finished product. The experimental results show that the algorithm of this study of high real-time performance and the detection accuracy rate received 99%.At last, the overall software of testing system of product quality of infusion cover is developed. Designed motion control, detection algorithm, parameter configuration data and user management of the software modules, and described the multi-threading technology and DLL technology in the implementation of the software system application in detail.