论文部分内容阅读
复合材料在现代飞机结构中的应用越来越广泛,为了有效地对飞机机翼健康状态进行预测,提出了基于多元经验模态分解(MEMD)和极限学习机(ELM)的飞机机翼健康状态预测方法。以某型飞机复合材料机翼盒段为具体研究对象,对其进行冲击与疲劳加载试验,利用光纤传感器及其采集系统募集飞机复合材料机翼盒段的原始应变信息,对其健康状态予以表征。对所采集的原始应变信息进行MEMD分解,提取分解后各频带信号的能量熵作为表征飞机复合材料机翼盒段健康状态的特征信息,采用动态主元分析法(DPCA)将所提取的能量熵特征信息进行融合,采用融合后所得到的能量熵构建ELM预测模型,对某型飞机复合材料机翼盒段健康状态进行预测。试验研究表明,本文方法可以有效实现飞机机翼的健康状态预测,具有很好的应用前景。
Composites are more and more widely used in modern aircraft structures. In order to effectively predict the health status of aircraft wings, the aircraft wing health status based on Multiple Empirical Mode Decomposition (MEMD) and Extreme Learning Machine (ELM) method of prediction. Taking the aircraft wing box section of a certain type of aircraft as the specific research object, the impact and fatigue loading tests were carried out. The optical fiber sensor and its acquisition system were used to raise the original strain information of the aircraft wing box segment, and their health status was characterized . The original strain information collected by MEMD decomposition, extraction and decomposition of the signal energy entropy of the envelope as a characterization of aircraft wing box health status characteristic information, the use of dynamic principal component analysis (DPCA) will extract the energy entropy The ELM prediction model was constructed by using the energy entropy obtained after the fusion, and the health status of a composite wing box was predicted. Experimental results show that the method proposed in this paper can effectively predict the health status of aircraft wings and has good application prospects.