Research And Application Of Cardboard Defect Detection And Control System Based On Machine Vision

With the rapid development of logistics industry and packaging industry,the demand for corrugated cardboard consumption is becoming larger and larger.At present,in the process of cardboard production,defect detection still relies on human eyes,which has low detection efficiency and high cost,and cannot meet the requirements of current industrial production.Moreover,temperature,as the most important factor affecting defect generation,is not well controlled.Therefore,the use of machine vision method to replace manual detection has become an urgent demand of the industry,and improving the temperature control system to improve defects is also of very important research significance.(1)A complete machine vision system is designed for the detection and improvement of cardboard defects,and the machine vision system is divided into three parts: image acquisition module,image processing module,and temperature control module.Each part is interconnected through the corresponding software and hardware combination,and then realize the function of defect detection and temperature control.(2)The working principle of the machine vision system is analyzed,and the overall scheme of the system is designed.The machine vision hardware system is built by selecting industrial camera,lens and other image acquisition equipment,PLC,touch screen and other temperature control equipment,and taking the server as the image processing center.(3)An improved Yolo v5 algorithm based on deep learning is designed for cardboard defects.The performance of the algorithm is improved by improving the activation function,loss function and prediction box filtering.The cardboard defect pictures were collected and the data set was completed,and the improved algorithm was tested with the data set.After testing,the corrugated board defect detection algorithm model has a good performance,the three aspects of improvement are very effective,to meet the requirements of the corrugated board defect detection.(4)According to the design principles and requirements of the temperature control module,the I/O ports of PLC were reasonably allocated,the overall circuit of the system was planned,and the PLC control program and human-computer interaction interface were designed by STEP 7-Microwin Smart and Win CC Flexible Smart V3 software respectively.The quality of the corrugated board is improved and defects are reduced.