基于增量型极限学习机的飞机复合材料结构损伤识别

Aircraft Composite Structure Damage Identification Based on Incremental Extreme Learning Machine

针对飞机复合材料结构损伤难以有效识别问题,提出一种基于增量型极限学习机(incremental extreme learning machine,I-ELM)的飞机复合材料结构损伤识别新方法。首先对某型机用复合材料层合板进行冲击,而后对其进行疲劳拉伸试验,通过优化布局在复合材料层合板上的光纤光栅传感器募集应变信息,并对其进行预处理。采用互补总体平均经验模态分解(complementary ensemble empirical mode decomposition,CEEMD)方法对募集的应变信息进行自适应分解,得到多个本征模态分量(intrinsic mode function,IMF)。计算各阶IMF分量的样本熵,通过核熵成分分析(kernel entropy component analysis,KECA)方法对样本熵进行特征融合,构建融合特征向量。采用融合特征向量建立基于I-ELM损伤识别模型,通过实验对损伤识别模型的有效性进行了验证,并与所构建的BP的损伤识别模型的识别结果进行了比较。结果表明,该方法能有效对飞机复合材料结构损伤进行识别,具有很好的应用前景。

In order to effectively identify aircraft composite structure damage,a method based on incremental extreme learning machine of composite structure damage diagnosis was proposed. Firstly,the data of fiber optic sensor on composite material laminated plates was gathered and the data was pre-processed after striking and stretching on a composite laminated plates. Secondly,strain information were decomposed by complementary ensemble empirical mode decomposition,and IMFs were obtained. Meanwhile,the sample entropy of each IMF was derived.Then,a feature vector was built by kernel entropy component analysis. Finally,the fusion feature vector was used as building incremental extreme learning machine identification model. Through experiment data,the method of I-ELM was verified. The results show that the I-ELM model can more effectively realize aircraft composite structure damage identification comparing with BP model,and it has good engineering application value.