One-dimensional convolutional neural network with data characterization measurement for cotton yarn quality prediction

Yarn quality prediction is vital in cotton spinning mills for stable production, quality assurance, and cost control. This paper built a machine-learning-based yarn quality prediction method, which contains two core parts: a novel data characterization measurement and a one-dimensional convolutional neural network (YQP-1D-CNN). Firstly, apply a statistical measurement to extract the variable-size feature indicators from the spinning technical parameters, including raw cotton blending scheme, yarn structure parameters, and production process parameters. Then a 1D-CNN prediction model is established based on the prior structural relationships between the feature indicators. Compared with the traditional ANNs, YQP-1D-CNN possesses fewer parameters, requires fewer training samples, and represents better generalization performance. In the experiment, 200 samples are collected from a spinning mill. The prediction performance of the proposed method is compared with six models in existing research. The YQP-1D-CNN shows the highest prediction R² and the lowest MSE on the overall performance. The better performance of YQP-1D-CNN on poor sample quality is verified better as well. The ablation experiment proves the advantages of the data characterization measurement and the 1D-CNN structure on yarn quality prediction. Finally, the YQP-1D-CNN has been tested in the spinning mill and met practical production requirements.