Answers are grounded in this paper and cite their sources.
Demonstrates improved moisture detection accuracy in cotton yarn sizing, suggesting better quality control.
Online moisture regain detection is essential for high-quality and efficient cotton yarn sizing. Currently, the widely used resistive moisture testers overlook the heterogeneity of warp sheet and environmental factors, leading to insufficient accuracy and environmental stability. This work investigates the moisture – resistance relationship of warp sheet under the complex conditions during sizing process and proposes a soft sensing method for warp sheet moisture regain via ensemble learning. First, a mechanism model of the Moisture – Resistance relationship (WS-MRM) is developed by considering the structural characteristics of warp sheet and environmental factors. Then, the WS-MRM mechanism model is integrated into a data-driven ensemble learning framework (including feedforward neural network, support vector regression, and adaptive boosting) to construct a physics-informed ensemble soft sensing model. Finally, the proposed method is implemented by integrating a resistive sensor with the hybrid model. The experiment results indicate that detection errors in the warp sheet moisture regain were reduced by 79.1% under laboratory conditions and by 47.8% under factory conditions after applying the soft sensing method. This method can effectively improve the online detection accuracy of resistive-type moisture regain meters in the sizing process.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: