Rebuilding Tissue Machine Vision Systems Without the Failure Points of Legacy Technology and Hardware, TAPPICon25

Machine vision solutions for web break troubleshooting and web inspection (defect detection) are mainstay technologies in the paper industry. Over time the common performance outcome of these systems becomes clear: the quality of the data provided decreases while the cost to maintain the compromised system increases. The cost of new machine vision systems, related engineering and installation cost and downtime of the machine vision system while it is being replaced often paralyze the decision to make changes. A proposed solution upgrades these siloed systems with a modernized, virtualized platform compatible with all industrial off the shelf camera technologies (GigE, analog, IP, and smart cameras), integrating with existing hardware and infrastructure while enabling future upgrades. Additionally, the paper tackles a specific challenge in tissue production: false defect detection due to dust and debris. A four-part solution is presented: (1) high-resolution smart cameras with sufficient frame rate using a one gigabyte backbone (2) software that filters false positives (3) a supervised deep learning neural network to classify defects and (4) ink and laser free tracking of these defects through the converting process. The combined approach delivers a reliable, accurate, and efficient machine vision solution for improving quality control, reducing waste, and increasing overall productivity in paper mills without the expense and time of starting over.

TAPPI conference proceedings and presentations, technical papers, and publication articles provide technical and management data and solutions on topics covering the Pulp, Paper, Tissue, Corrugated Packaging, Flexible Packaging, Nanotechnology and Converting Industries.

Simply select the quantity, add to your cart and your conference paper, presentation or article will be available for immediate download.