Enhancing AFP manufacturing with AI: Defects forecasting and classification

IF 14.2 1区材料科学 Q1 ENGINEERING, MULTIDISCIPLINARY

Composites Part B: Engineering Pub Date : 2025-05-28 DOI:10.1016/j.compositesb.2025.112655

Anatoly Koptelov, Bassam El Said, Iryna Tretiak

引用次数: 0

Abstract

In this work, a novel AI-driven framework for real-time defect prediction and classification for proactive quality control is introduced. By integrating autoencoders, Long Short-Term Memory (LSTM) networks, and Convolutional Neural Networks (CNNs) with the laser profilometry data acquisition into a joint pipeline, the proposed system is able to forecast defects in automated fibre placement tapes before they fully develop, enabling early corrective actions to reduce material waste and rework time. Experimental validation demonstrated the framework's ability to predict twist defects up to 5 mm before the defect appears under the sensor, and pucker defects 2 mm with an overall 94 % accuracy, offering a substantial advantage over conventional AFP defect sensors. The proposed system represents a step towards predictive defect management in AFP, enhancing efficiency of manufacturing and final product reliability.

Abstract Image

查看原文本刊更多论文

人工智能增强AFP制造：缺陷预测与分类

在这项工作中，引入了一种新的人工智能驱动框架，用于主动质量控制的实时缺陷预测和分类。通过将自动编码器、长短期记忆（LSTM）网络和卷积神经网络（cnn）与激光轮廓测量数据采集集成到一个联合管道中，该系统能够在自动化光纤放置胶带完全开发之前预测其缺陷，从而实现早期纠正措施，减少材料浪费和返工时间。实验验证表明，该框架能够在缺陷出现之前预测扭曲缺陷5毫米，褶皱缺陷2毫米，总体精度为94%，与传统的AFP缺陷传感器相比具有很大的优势。提出的系统代表了AFP中预测缺陷管理的一步，提高了制造效率和最终产品的可靠性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Composites Part B: Engineering 工程技术-材料科学：复合

CiteScore

24.40

自引率

11.50%

发文量

784

审稿时长

21 days

期刊介绍： Composites Part B: Engineering is a journal that publishes impactful research of high quality on composite materials. This research is supported by fundamental mechanics and materials science and engineering approaches. The targeted research can cover a wide range of length scales, ranging from nano to micro and meso, and even to the full product and structure level. The journal specifically focuses on engineering applications that involve high performance composites. These applications can range from low volume and high cost to high volume and low cost composite development. The main goal of the journal is to provide a platform for the prompt publication of original and high quality research. The emphasis is on design, development, modeling, validation, and manufacturing of engineering details and concepts. The journal welcomes both basic research papers and proposals for review articles. Authors are encouraged to address challenges across various application areas. These areas include, but are not limited to, aerospace, automotive, and other surface transportation. The journal also covers energy-related applications, with a focus on renewable energy. Other application areas include infrastructure, off-shore and maritime projects, health care technology, and recreational products.