Efficiency Increase through Data-Based Modeling of Quality and Production Cost Factors in the Nonwoven Industry

Abstract

The carding process is the most important process for the production of nonwovens from fibers of finite length (staple fibers). The quality parameters of nonwovens are influenced in a highly complex way by a large number of properties of the raw material, the production settings and the environmental conditions. In particular, the setting of the card has an enormous influence on the quality of the nonwoven. In order to realize monetization effects in nonwoven production, the card is optimized from a technical and economical point of view using machine learning methods. For this purpose, the influences on the resulting nonwoven quality and the production costs are determined and a measuring system is developed which records all variables during production. The effect of the influencing variables on the target variables product quality and production costs is modeled using machine learning methods. Based on the developed models, a simulation is developed which simulates the expected product quality and the expected energy demand for different settings. For each setting, the specific production costs expected for the given settings are calculated. An optimization algorithm according to the ε-constraint method systematically searches the simulation results and selects the setting for which the required minimum quality is achieved and the production costs are lowest.

The following chapter contains sections that were previously published in: Cloppenburg, Frederik: Technische und wirtschaftliche Modellierung und Selbstoptimierung von Vliesstoffkrempeln, Düren: Shaker, 2019; Zugl.: Dissertation, RWTH Aachen University, 2019.