在炭纤维/ABS树脂基复合材料导电性和拉伸强度实验数据的基础上,利用主成分分析-遗传算法后向传播(Principal Component Analysis-Genetic Algorithm Back Propagation,PCA-GABP)神经网络模式识别法,对炭纤维复合材料导电综合性参数进行智能分析识别。其中主成分分析法作为前处理过程优化样本集的选择,GABP神经网络较好地克服了BP网络非线性映射易陷入局部极小值问题。给出性能优良的目标参数优化区,并用实验予以验证。该模式识别方法可减少实验工作量,提高工作效率,在复合材料设计领域具有理论应用前景。 Based on the experimental data of electrical conductivity and tensile strength of carbon fiber / ABS resin matrix composites, Principal Component Analysis-Genetic Algorithm Back Propagation (PCA-GABP) neural network pattern recognition , Intelligent analysis and identification of the conductive composite parameters of carbon fiber composites. Among them, the principal component analysis (PCA) is the choice of the optimal sample set for the pretreatment process. The GABP neural network overcomes the problem that the nonlinear mapping of the BP network is apt to fall into the local minimum. The optimal parameters of the target area are given and verified by experiments. The pattern recognition method can reduce the experimental workload and improve work efficiency, and has theoretical application prospect in the field of composite material design.