STTR Phase I: Manufacturing of Enhanced Composites via Interlaminar Incorporation of CNT/Epoxy Nanoscaffolds using Genetic Algorithm Assisted Machine Learning and Neural Networks

该小企业技术转让计划（STTR）第一阶段项目的更广泛影响/商业潜力是提高航空航天，汽车，能源和其他应用中碳纤维增强复合材料的强度和刚度。碳纤维增强聚合物（CFRP）材料用于减轻重量而不影响结构部件的强度，但由于它们是逐层建造的，因此具有一定的弱点。 该项目将推进一种新的方法，以生产更高性能的汽车，飞机，涡轮机等。该过程可以高度自动化，具有成本效益，并与现有的CFRP制造无缝集成。可以将其纳入现有流程。更强、更轻的复合材料部件的持续发展也将对包括可再生能源在内的相关领域产生影响。 该技术有望降低运营成本，提高燃油效率并减少排放。这将对先进制造业的国家安全产生重大影响。该项目的重大技术创新是确定使用静电纺丝将碳纳米管（CNT）/环氧树脂纳米丝涂覆在预浸CFRP卷上，可以形成面积为平方米，厚度仅为数十微米的CNT增强粘合表面。该项目将使用低材料成本和高度自动化的工艺来解决CFRP预浸料层压板长期存在的整个厚度层间强度弱的问题。该项目将扩大主要创新，通过遗传算法辅助机器学习（GAML）和人工神经网络（ANN）发展对多尺度纳米簇增强CFRP先进复合材料的理论理解。我们的目标是建立一个实验和计算支持的GAML框架，以确定最佳的工艺参数和结构特征。结果将导致更好的优化工具在新的复合材料的设计，和仪器的发展，支持出现新的重量和成本节约的机会，在复合材料行业的复杂system.This奖项反映了NSF的法定使命，并已被认为是值得的支持，通过评估使用基金会的智力价值和更广泛的影响审查标准。

The broader impact/commercial potential of this Small Business Technology Transfer Program (STTR) Phase I project is to improve strength and stiffness of carbon fiber reinforced composites in aerospace, automotive, energy, and other applications. Carbon fiber reinforced polymer (CFRP) materials are used to reduce weight without compromising the strength of structural components, but because they are built layer by layer, they have certain weaknesses. This project will advance a new approach to to enable production of higher performance automobiles, airplanes, turbines and more. The process can be highly automated, cost-effective, and seamlessly integrated with existing CFRP manufacturing. This can be integrated into existing processes. The continued development of stronger and lighter composite parts will also have an impact in related fields including renewable energy resources. The technology holds the promise of reducing operating costs, improving fuel efficiency, and decreasing emissions. This will lead to significant impacts on national security in advanced manufacturing.The strong technical innovation in the project is identifying the use of electrospinning to coat a prepreg CFRP roll with carbon nanotube (CNT)/epoxy nanofilaments that can form a CNT-reinforced bonding surface that is square meters in area and just tens of microns in thickness. This project will address the longstanding weak through-thickness interlaminar strength of CFRP prepreg laminates using a low materials-cost and highly automated process. The project will expand on the primary innovation to develop a theoretical understanding of multiscale nanoscaffold-enhanced CFRP advanced composites through genetic algorithm assisted machine learning (GAML) and artificial neural networks (ANN). The objective is to establish an experimentally and computationally supported GAML framework for determining optimal processing parameters and structural features. Results will lead to better optimization tools in the design of new composite materials, and the development of instrumentation supporting the emergence of new weight and cost saving opportunities in the composite industry for complex systems.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.