Real-time Paper and Paperboard Quality Analysis and Classification based on Paper Formation or Surface Appearance in Web Inspection System, 19PaperCon
Higher demands for paper and paperboard quality and the goals of more sustainable production reducing waste set new requirements for more advanced machine vision technologies to be utilized in web inspection system (WIS) for analyzing and classifying paper and paperboard properties during the production process. Both visual and structural paper web properties need to be analyzed, preferably covering a full 100% of the web, to achieve high accuracy in classification and to guarantee the required product quality. Paper formation and surface appearance are important paper properties which can be used for further analyzing many other paper properties like printability, strength, and paper surface appearance quality.
Optical transmission measurement can be used for analyzing paper or paperboard “look through” formation, which reveals the fiber and filler distribution and clusters of fibers, i.e., flocs of a sheet of paper. Accepted formation usually requires an adequate uniformity of fiber distribution, which means small enough floc sizes, which usually improve printability and strength of a paper product. Thus, increased floc sizes indicate worse structural paper properties causing for example lower paper strength. Uneven floc distribution can also cause poor and uneven ink penetration in printing.
Optical reflection measurement can be used for surface appearance analysis. Uneven unprinted paper or paperboard surface is caused for example by dirt on the surface, surface topography variations, surface reflectance variations, coating variations, or white top variations in paperboard. Correspondingly, in printed products the printing quality variations can be observed as mottling, which can be defined as undesired unevenness in observed print density.
Our new real-time machine vision methodology can handle all of the above mentioned transmission and reflection measurement cases. In our real-time imaging methods we utilize novel elements of artificial intelligence (AI) for analysis and classification of paper formation or surface formation qualities. These elements include for example real-time streaming video statistical feature extraction, real-time streaming video corrections based on unsupervised learning, real-time formation or surface formation feature extraction, real-time formation or surface formation pattern extraction, modeling and recognition, real-time unsupervised normal product quality learning and real-time product quality exception detection. Also real-time supervised learning is utilized in the WIS system to identify different paper making process failures, which are visible in paper or paperboard formation or surface formation depending on the customers’ needs. In this paper we show how our new machine vision methods can be used for real-time full web paper and paperboard formation or surface formation quality monitoring, analysis and classification in different production cases.
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.
Real-time Paper and Paperboard Quality Analysis and Classification based on Paper Formation or Surfa