Method for predicting pore size distribution of composite fiber membrane based on deep learning

The composite coded feature vector is generated through multimodal fusion and attention mechanism, and the correlation coding is performed with spinning process parameters. The deep prediction network is optimized by using a comparison learning and error correction mechanism, which solves the problems of low accuracy and insufficient adaptability of the pore size distribution prediction in the existing technology, and achieves high-precision and high-adaptive pore size distribution prediction.

CN119888731AActive Publication Date: 2025-04-25深圳桥斯技术有限公司
6 Cites 3 Cited by

Patent Information

Application Number
CN202510387383.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-03-31
Publication Date
2025-04-25
Estimated Expiration
2045-03-31

AI Technical Summary

Technical Problem

The existing pore size distribution prediction methods based on deep learning are difficult to effectively capture the complexity of the microstructure of fiber membranes, especially in terms of the difference in pore size gradients between the crosslinked and non-crosslinked regions, which leads to a decrease in prediction accuracy, and the model generalization ability is insufficient, making it difficult to adapt to pore size changes under different process conditions.

Method used

The multimodal fusion strategy is adopted to jointly encode the scanning electron microscope image and the atomic force microscope morphology data, and a composite coded feature vector is generated through the attention mechanism, region segmentation and pore size distribution dominant features are extracted and quantified, and the spinning process parameters are associated encoding. A contrast learning is used to optimize the depth prediction network, and the parameter weight is adjusted using an error correction mechanism.

Benefits of technology

The extraction accuracy of aperture distribution characteristics and the resolution ability of prediction models are improved, the applicability and generalization ability of prediction methods are enhanced, the prediction deviation is effectively reduced, and the overall prediction accuracy is improved.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a composite fiber membrane aperture distribution prediction method based on deep learning, and relates to the technical field of distribution prediction.The method comprises the steps that multiple kinds of image data are collected and coded respectively, and a composite coding feature vector is generated through an attention mechanism; based on the composite coding feature vector, performing region segmentation on a fiber cross-linked region and a non-cross-linked region, and extracting and quantifying pore size distribution dominant features; performing associated coding by combining the pore size distribution dominant characteristics and spinning process parameters; and based on the associated codes, optimizing the depth prediction network, and adjusting the parameter weights of the associated codes by adopting an error correction mechanism. The pore size distribution of the composite fiber membrane can be accurately predicted, and powerful support is provided for material design optimization and production process control.
Need to check novelty before this filing date? Find Prior Art