基于人工神经网络的热固性树脂基复合材料固化变形预测研究综述

A review of prediction methods of process-induced distortions in thermoset composites based on artificial neural network

热固性树脂基复合材料相对于传统材料而言优点众多,如其出色的物理和力学性能,以及其前期设计和后期制造过程中的可设计性,在航空航天行业内极具吸引力。然而其工艺引起的变形缺陷仍是至关重要的问题,该缺陷会造成装配困难、残余应力等。本文报道了热固性树脂基复合材料热压成型工艺过程中产生的固化变形行为研究现状,主要介绍了固化变形机理、固化变形的数值模拟方法、人工神经网络方法及其在固化变形上的应用。重点放在人工神经网络方法在热固性树脂基复合材料固化变形研究的最新进展,为复合材料固化变形的高通量预测和逆向设计提供方向和参考,最后简要讨论其主要发展方向。

Thermosetting-matrix composites have become attractive in aerospace industry on account of their numerous advantages over conventional materials, such as their intriguing physical and mechanical properties, and their designable ability in terms of the design process and the subsequent manufacturing process. Despite these benefits, process-induced distortion is crucial issue since it cause assembly difficulties and residual stresses. This paper aimed at reporting the current research status of the process-induced distortion behavior of thermosetting-matrix composites, which was introduced during the hot forming process. The process-induced distortion mechanism, the related numerical simulation method, artificial neural network method and its application in the process-induced distortion were mainly introduced. An emphasis being placed on the state-of-art development of high-throughput prediction and inverse design of process-induced distortions based on artificial neural network. Finally, the future development directions of process-induced distortion and artificial neural network were briefly discussed.