模糊灰关联在QAR故障数据检测中的应用  

Application of fuzzy gray relational analysis in QAR fault data detection

作　　者：杨慧[1] 杨欣[1] 

机构地区：[1]中国民航大学计算机科学与技术学院,天津300300

出　　处：《计算机工程与设计》2015年第7期1896-1899,1965,共5页Computer Engineering and Design

基　　金：国家自然科学基金与中国民航联合基金项目(61179063);国家自然科学基金项目(61301245)

摘　　要：针对传统的灰色关联故障诊断算法无法解决大样本数据的问题,提出一种基于模糊分割灰关联的QAR(quick access recorder)故障数据检测算法。鉴于QAR数据是数据结构复杂、维数高的时间序列数据,利用模糊分割将QAR数据分割成不重叠的子序列,从中提取出待检测故障序列,计算待检测序列与标准序列间的灰关联度,根据最大关联度原则进行故障模式识别并确定诊断结果。仿真结果表明,该算法的预测结果与实际情况基本一致,具有简单可靠、诊断精度高等优点。In view of the faults that the traditional gray relational fault diagnosis algorithm fails to solve problems associating with large sample data,QAR（quick access recorder）fault data detection algorithm based on fuzzy segmentation of gray relational analysis was proposed.Given the fact that QAR data is high-dimensional time-series data which has complex data structure,the QAR data was divided into non-overlapping sub-class using fuzzy segmentation,and then the fault sequence was extracted to be detected.Thus gray correlation degree was calculated between the sequence to be detected and the standard sequence.Finally,the fault pattern recognition and the determination of the diagnosis results were presented according to the principle of maximum correlation degree.The simulation results show that the predicted results were basically concordant with the actual situation.Besides this algorithm has simple and reliable diagnostic precision.

关 键 词：灰色关联 故障诊断 模糊 QAR数据 时间序列数据 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]