今日更新:Composites Part B: Engineering 2 篇,Composites Science and Technology 1 篇
An efficient machine learning-based model for predicting the stress-strain relationships of thermoplastic polymers with limited testing data
Shengbo Ling, Zhen Wu, Jie Mei, Shengli Lv
doi:10.1016/j.compositesb.2024.111600
用有限的测试数据预测热塑性聚合物应力-应变关系的高效机器学习模型
Thermoplastic polymers used in aeronautical structures such as poly-ether-ether-ketone (PEEK) usually exhibit nonlinear stress-strain relationships, which can be usually predicted by the physical and phenomenological models. For different thermoplastic polymers, however, existing models may encounter difficulties in reasonably predicting the stress-strain relationships. By reasonably using experimental data, the machine learning-based model can accurately predict the stress-strain relationships. In this paper, an efficient machine learning-based model is built to predict the stress-strain relationships of thermoplastic polymers by using the Kriging model, where limited testing data are merely used. Experiments of 69 specimens for PEEK are firstly performed under uniaxial tensile, where the temperatures range from 23 °C to 140 °C and the strain rates range from 10-3 s-1 to 10-1 s-1. Genetic algorithm is employed to train the proposed model based on the stress-strain relationships obtained from experiments. Moreover, the results predicted by the proposed Kriging-based model are compared with those obtained from the DSGZ (Duan-Saigal-Greif-Zimmerman) model. The results indicate that the Kriging-based model possesses better accuracy, lower complexity, and better robustness than the selected model, because the prior estimation is introduced by the assumption of Gaussian stochastic processes. In addition, the proposed model is also applied to Poly-Propylene (PP), PEEK at high temperatures, and polycarbonate (PC), it can be found that the Kriging-based model can also predict the stress-strain relationships of other amorphous and semi-crystalline thermoplastic polymers.
用于航空结构的热塑性聚合物,如聚醚-醚-酮(PEEK),通常表现出非线性的应力-应变关系,通常可以通过物理和现象学模型来预测。然而,对于不同的热塑性聚合物,现有的模型在合理预测应力-应变关系时可能会遇到困难。通过合理利用实验数据,基于机器学习的模型可以准确预测应力-应变关系。在本文中,建立了一个高效的基于机器学习的模型,通过使用Kriging模型来预测热塑性聚合物的应力-应变关系,其中仅使用有限的测试数据。首先对69个PEEK试件进行单轴拉伸试验,试验温度范围为23℃~ 140℃,应变速率范围为10-3 s-1 ~ 10-1 s-1。基于实验得到的应力应变关系,采用遗传算法对模型进行训练。并与DSGZ (Duan-Saigal-Greif-Zimmerman)模型的预测结果进行了比较。结果表明,由于基于高斯随机过程的假设引入了先验估计,与所选模型相比,基于kriging的模型具有更高的精度、更低的复杂度和更强的鲁棒性。此外,所提出的模型也适用于高温下的聚丙烯(PP)、PEEK和聚碳酸酯(PC),可以发现基于kriging的模型也可以预测其他非晶和半晶热塑性聚合物的应力应变关系。
A Sequential Meta-Transfer (SMT) Learning to Combat Complexities of Physics-Informed Neural Networks: Application to Composites Autoclave Processing
Milad Ramezankhani, Abbas. S.Milani
doi:10.1016/j.compositesb.2024.111597
序贯元迁移(SMT)学习以对抗物理信息神经网络的复杂性:应用于复合材料高压灭菌处理
Physics-Informed Neural Networks (PINNs) have gained popularity in solving nonlinear partial differential equations (PDEs) via integrating physical laws into the training of neural networks, making them superior in many scientific and engineering applications. However, conventional PINNs still fall short in accurately approximating the solution of complex systems with strong nonlinearity, especially in long temporal domains. Besides, since PINNs are designed to approximate a specific realization of a given PDE system, they lack the necessary generalizability to efficiently adapt to new system configurations. This entails computationally expensive re-training from scratch for any new change in the system. To address these shortfalls, in this work a sequential meta-transfer (SMT) learning framework is proposed, offering a unified solution for both fast training and efficient adaptation of PINNs in highly nonlinear systems with long temporal domains. Specifically, the framework decomposes PDE’s time domain into smaller time segments to create “easier” PDE problems for PINNs training. Then for each time interval, a meta-learner is assigned and trained to achieve an optimal initial state for rapid adaptation to a range of related tasks. Transfer learning principles are then leveraged across time intervals to further reduce the computational cost. Through a composites autoclave processing case study, it is shown that SMT is clearly able to enhance the adaptability of PINNs while significantly reducing computational cost, by a factor of 100.
物理信息神经网络(pinn)通过将物理定律集成到神经网络的训练中,在求解非线性偏微分方程(PDEs)方面得到了广泛的应用,使其在许多科学和工程应用中具有优越性。然而,对于具有强非线性的复杂系统,特别是长时间域的复杂系统,传统的pin神经网络在精确逼近解方面仍然存在不足。此外,由于pin被设计为近似给定PDE系统的特定实现,因此它们缺乏必要的通用性,无法有效地适应新的系统配置。这需要为系统中的任何新变化从头开始进行计算上昂贵的重新训练。为了解决这些不足,本文提出了一个顺序元迁移(SMT)学习框架,为长时域高度非线性系统中的pin n的快速训练和有效自适应提供了统一的解决方案。具体来说,该框架将PDE的时域分解为更小的时间段,从而为pin训练创建“更容易”的PDE问题。然后,对于每个时间间隔,分配并训练一个元学习器,以达到快速适应一系列相关任务的最佳初始状态。然后跨时间间隔利用迁移学习原理来进一步降低计算成本。通过复合材料热压罐加工案例研究表明,SMT明显能够增强pinn的适应性,同时显着降低计算成本,降低了100倍。
Transverse Cracking Signal Characterization in CFRP Laminates using Modal Acoustic Emission and Digital Image Correlation Techniques
Michal Šofer, Jakub Cienciala, Pavel Šofer, Zbyněk Paška, František Fojtík, Martin Fusek, Pavel Czernek
doi:10.1016/j.compscitech.2024.110697
基于模态声发射和数字图像相关技术的CFRP层合板横向裂纹信号表征
The process of formation and subsequent propagation of transverse cracks in 90o plies of carbon-fiber laminated composites was studied using modal acoustic emission approach and digital image correlation techniques. The results from modal acoustic emission approach, which included a newly developed processing tool for acoustic emission waveforms, provided information for identification and subsequent characterization or localization of signals originating from transverse cracking by analysis of the separated flexural and extensional Lamb wave modes in terms of their modal parameters. The digital image correlation method served as a verification tool of the acoustic emission data outputs in the terms of activity of significant localized events originating from the formation of the transverse crack in the 90oply. This made it possible to specify more locally the accompanying activity belonging to the formation or propagation of the magistral transverse crack. The manuscript also presents results related to the evolution of flexural/extensional wave modal parameters as the function of loading force for both [0/0/0/90]S and [90/0/0/0]S panels. It can be concluded that the detection of transverse cracks requires the need for applying a more complex acoustic emission data analysis methodology, while the standard parametric analysis, including the waveform peak frequency, is not sufficient. The presented methodology may serve as a basis for development of robust analysis tool capable of detecting the investigated phenomena.
采用模态声发射方法和数字图像相关技术研究了900层碳纤维层合复合材料横向裂纹的形成和后续扩展过程。模态声发射方法的结果,包括一个新开发的声发射波形处理工具,通过分析分离的弯曲和伸展Lamb波模态参数,为识别和后续表征或定位来自横向裂纹的信号提供了信息。数字图像相关方法可作为声发射数据输出的验证工具,用于验证源自90层横向裂缝形成的重要局部事件的活动性。这使得更局部地指定属于主横向裂缝形成或扩展的伴随活动成为可能。本文还介绍了[0/0/0/90]S和[90/0/0/0]S面板的弯曲/伸展波模态参数作为加载力函数的演变结果。可以得出结论,横向裂纹的检测需要应用更复杂的声发射数据分析方法,而包括波形峰值频率在内的标准参数分析是不够的。所提出的方法可以作为开发能够检测所研究现象的强大分析工具的基础。