{"title":"Research on airplane health forecast method based on the improved MGM(1, n)","authors":"Jianguo Cui, Desheng Song, Shiliang Dong, Mingzhuo Wang, Xiaopeng Liang, Xinhe Xu","doi":"10.1109/CCDC.2009.5195044","DOIUrl":null,"url":null,"abstract":"There is strong randomness and uncertainty lying in the health status of airplane. Because the former grey models can not forecast the random signals efficiently, a new forecast method for the health state of airplane, based on the improved MGM(1, n), is presented in this paper. The advanced acoustic emission (AE) technique is used to collect the health state information. The original AE signals are decomposed with the wavelet transform. The energy values, eigenvalues and standard deviation of the third layer wavelet decomposition low frequency coefficients are respectively extracted to form eigenvectors. Then the improved MGM(1, n) is established by these eigenvectors. The improved algorithm is realized by feeding back the errors between the forecast values and the actual ones so as to improve the forecast precision. Experiments show that the improved MGM(1, n) can forecast the airplane stabilizer fatigue crack more accurately than the GM (1, 1). And this new method has been successfully applied to the forecast system of the health state of airplane structure components.","PeriodicalId":127110,"journal":{"name":"2009 Chinese Control and Decision Conference","volume":"145 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2009-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2009 Chinese Control and Decision Conference","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CCDC.2009.5195044","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
There is strong randomness and uncertainty lying in the health status of airplane. Because the former grey models can not forecast the random signals efficiently, a new forecast method for the health state of airplane, based on the improved MGM(1, n), is presented in this paper. The advanced acoustic emission (AE) technique is used to collect the health state information. The original AE signals are decomposed with the wavelet transform. The energy values, eigenvalues and standard deviation of the third layer wavelet decomposition low frequency coefficients are respectively extracted to form eigenvectors. Then the improved MGM(1, n) is established by these eigenvectors. The improved algorithm is realized by feeding back the errors between the forecast values and the actual ones so as to improve the forecast precision. Experiments show that the improved MGM(1, n) can forecast the airplane stabilizer fatigue crack more accurately than the GM (1, 1). And this new method has been successfully applied to the forecast system of the health state of airplane structure components.