This study investigates the flexural strength of 3D-printed nylon-carbon reinforced composite specimens, highlighting the impact of infill density and layer height on mechanical performance. The findings indicate that a printing layer height of 0.10 mm with 100% infill density exhibits the highest flexural strength, supporting a maximum load of 127 N, compared to 76.7 N at 50% infill density. Microstructural study has clearly illustrated the structural distortion, revealing that a rise in layer height correlates with an escalation in structural distortion. An Artificial Neural Network (ANN) model is thus utilized to achieve high predictive accuracy in order to predict flexural behaviour. R-values above 0.98 are obtained across training, validation, and test datasets, indicating that ANN-based modelling may be able to facilitate quick optimization of 3D printing parameters for high-performance applications. These findings establish carbon-reinforced nylon as a formidable competitor for use in industries such as aerospace and automotive, where strength and durability are important.

中文翻译：

---

碳增强 3D 打印尼龙的弯曲强度评估：使用 ANN 的实验验证


本研究调查了 3D 打印尼龙碳增强复合材料试样的弯曲强度，突出了填充密度和层高对机械性能的影响。研究结果表明，0.10 mm 的打印层高度和 100% 填充密度的打印层表现出最高的弯曲强度，支持 127 N 的最大负载，而填充密度为 50% 时为 76.7 N。微观结构研究清楚地说明了结构变形，揭示了层高的增加与结构变形的升级相关。因此，利用人工神经网络 （ANN） 模型来实现高预测精度，以预测弯曲行为。在训练、验证和测试数据集中获得高于 0.98 的 R 值，这表明基于 ANN 的建模可能能够促进快速优化 3D 打印参数，以实现高性能应用。这些发现使碳增强尼龙成为航空航天和汽车等行业使用的强大竞争对手，在这些行业中，强度和耐用性很重要。