基于对称点模式和SE注意力机制的纺织废品定性分析模型的研究

打开文本图片集

中图分类号：TS195.644 文献标志码：A文章编号：2097-2911-（2025）06-0074-12

Abstract：Inviewofthe serious overlapping of infrared spectral data features inthequalitativeanalysis of the composition of waste textiles and the insuficient classification accuracy of traditional models，proposes a deep learning model based on the SDP （symmetrized dot patterns） and SE （squeeze excitation） attention mechanisms. The infrared spectral data of 20 types of single and mixed component textile fibers such as cellulose， wool，and polyester were colected （400 training sets and 200 test sets for each type）.The spectral data was mapped to polar coordinate images using SDP conversion to efectively enhance feature separability，and the optimal parameterswere determined through experiments （gain angle g=30∘ ，interval factor b=29 ）.On this basis，the SE-DCNN model was constructed by combining the hole convolution to expand the receptive field and introducing the SE attention mechanism to optimize the feature channel weight allcation. Ablation experiments showed that after fusing the SE module with the hole convolution，the model's determination coefficient （R²）on the test set increased to 0.992，and the mean absolute error （MAE）and root mean square eror （RMSE） were reduced to 0.64 and2.24 respectively. Compared with traditional methods （such as SVM， PCA+KNN and1D-CNN，SE-DCNN performs best in the mixed component prediction task （test set R2=0.947 ，MAE=1.05）.

Keywords： waste textiles;infrared spectrum;symmetrized dot patterns;atention mechanism; void convolution

随着全球纺织行业的迅速发展，纺织品的消费量持续增长，废旧纺织品的处理问题也愈发严峻。（剩余11920字）