Analysis of quality properties in paper drying with neural networks

The quality of paper is strongly dependent on drying conditions. It is difficult, if not impossible, to model the development of paper quality based on theoretical considerations. In this study neural networks have been applied to model the relationship between paper quality and drying conditions. Training material for neural network was generated by using our laboratory scale drying apparatus. By using trained neural networks it is possible to simulate behavior of the characteristics features of the paper quality without time-consuming test runs.