复合材料层板冲击损伤检出概率预测研究  

Study on Probability Prediction of Impact Damage of Composite Laminates

作　　者：孙明波[1] 马秋丽 雷俊辉 张炎亮[1] SUN Ming-bo;MA Qiu-li;LEI Jun-hui;ZHANG Yan-liang(School of Management Engineering,Zhengzhou University,Zhengzhou 450001,China)

机构地区：[1]郑州大学管理工程学院,郑州450001

出　　处：《组合机床与自动化加工技术》2018年第7期97-99,共3页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：国家自然科学基金资助项目(71271194);河南省基础与前沿技术研究项目(162300410073)

摘　　要：针对航空领域复合材料层板冲击损伤检出概率的影响因素复杂、不确定性难以进行准确预测的问题,将BP神经网络和模糊推理系统相结合,提出了一种基于自适应神经模糊推理系统(Adaptive Neuron Fuzzy Inference System,ANFIS)的冲击损伤目视检测检出概率预测方法。首先利用仿真函数验证预测模型的有效性,然后以实验数据为例进行仿真分析,与传统的BP神经网络和支持向量机预测模型进行比较。仿真和实验结果表明,自适应神经模糊推理系统预测模型在目视检测损伤检出概率预测中具有更高的精度。Aiming at the problem that the influencing factors of the impact damage of composite laminates in the aviation field are complex and uncertain,and it is difficult to be accurately predicted.An adaptive neural fuzzy inference system risk detection method for visual inspection of impact damage is proposed,which combined a BP neural network and a fuzzy reasoning system.Firstly,the validity of the model is verified by the simulation function.Then,the experimental data are taken as an example to simulate and compare with the traditional BP neural network and support vector machine prediction model.The simulation and experimental results show that the adaptive neural fuzzy reasoning system prediction model has higher accuracy in visual detection of damage detection probability prediction.

关 键 词：复合材料 目视检测 冲击损伤 

分 类 号：TH165[机械工程—机械制造及自动化] TG506[金属学及工艺—金属切削加工及机床]