arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.22397physics.comp-phcs.LG
收藏

将宽深神经网络与 squeeze-and-excitation 块集成用于增材制造纤维增强复合材料的多目标属性预测

Integrating Wide and Deep Neural Networks with Squeeze-and-Excitation Blocks for Multi-Target Property Prediction in Additively Manufactured Fiber Reinforced Composites

Department of Mechanical Engineering, Southern Methodist University(机械工程系,南方 Methodist 大学)

Behzad Parvaresh, Rahmat K. Adesunkanmi, Adel Alaeddini

AI总结:

本研究提出一种结合拉丁超立方采样与 squeeze-and-excitation 宽深神经网络的方法,用于高效预测增材制造纤维复合材料的多目标属性。

摘要:

通过增材制造(CFRC-AM)制造的连续纤维增强复合材料为打印轻质高比强度材料提供了机会。然而,其性能对工艺和材料参数的相互作用敏感,使全面实验测试不切实际。在本研究中,我们引入了一种数据高效、多输入、多目标学习方法,将拉丁超立方采样(LHS)引导的实验与 squeeze-and-excitation 宽深神经网络(SE-WDNN)相结合,以基于不同的制造参数联合预测 CFRC-AM 的多种机械和制造性能。我们使用 Markforged Mark Two 3D 打印机打印并测试了从 4,320 种组合设计空间中选出的 155 个试样。处理后的数据形成了我们所提出模型的输入输出集。我们比较了结果与常用机器学习模型的结果,包括前馈神经网络、Kolmogorov-Arnold 网络、XGBoost、CatBoost 和随机森林。我们的模型实现了最低的整体测试误差(MAPE = 12.33%),并在几个目标变量上相对于基线宽深神经网络表现出统计学显著的改进(配对 t检验,p <= 0.05)。SHapley Additive exPlanations(SHAP)分析揭示了增强策略是机械性能的主要影响因素。总体而言,本研究证明了 LHS 和 SE-WDNN 的结合能够实现可解释且样本高效的多目标预测,指导 CFRC-AM 中参数选择,以在机械行为和制造指标之间取得平衡。

英文摘要:

Continuous fiber-reinforced composite manufactured by additive manufacturing (CFRC-AM) offers opportunities for printing lightweight materials with high specific strength. However, their performance is sensitive to the interaction of process and material parameters, making exhaustive experimental testing impractical. In this study, we introduce a data-efficient, multi-input, multi-target learning approach that integrates Latin Hypercube Sampling (LHS)-guided experimentation with a squeeze-and-excitation wide and deep neural network (SE-WDNN) to jointly predict multiple mechanical and manufacturing properties of CFRC-AMs based on different manufacturing parameters. We printed and tested 155 specimens selected from a design space of 4,320 combinations using a Markforged Mark Two 3D printer. The processed data formed the input-output set for our proposed model. We compared the results with those from commonly used machine learning models, including feedforward neural networks, Kolmogorov-Arnold networks, XGBoost, CatBoost, and random forests. Our model achieved the lowest overall test error (MAPE = 12.33%) and showed statistically significant improvements over the baseline wide and deep neural network for several target variables (paired t-tests, p <= 0.05). SHapley Additive exPlanations (SHAP) analysis revealed that reinforcement strategy was the major influence on mechanical performance. Overall, this study demonstrates that the integration of LHS and SE-WDNN enables interpretable and sample-efficient multi-target predictions, guiding parameter selection in CFRC-AM with a balance between mechanical behavior and manufacturing metrics.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑