|
|
Ultrasonic Testing Based Multi-feature Extraction of UAV Composite Materials |
WANG Feng-lin,WANG Chang-long,HU Yong-jiang |
Department of UAV Engineering, Ordnance Engineering College, Shijiazhuang, Hebei 050003, China |
|
|
Abstract Due to the single feature extraction has not exert information as well as different features have different importance while recognizing UAV composite materials flaws, a method for multi-feature extraction in wavelet packet field and time-field is proposed. The new approach firstly decomposes signal with wavelet packet to get feature, using principal component analysis to decrease the dimension of feature vectors, then, extracts time-field feature considering composite materials characters. at last, the combined feature vectors algorithm is proposed using the matching method. The experimental results indicate the effectiveness of the proposed feature vectors while classifying the bond flaws in composite materials.
|
|
|
|
|
[1]潘荣华,宋国栋,杨学永.无人机复合材料结构和制造工艺[J].南京航空航天大学学报,2009,41(S):119-122.
[2]王浩全,曾光宇.玻璃纤维复合材料超声C扫描检测研究[J].兵工学报,2005,26(4):570-572.
[3]李惠芳,常宁.基于神经网络的金属与非金属材料粘接质量定量检测[J].北京工业大学学报,2009,35(8):1122-1125.
[4]蒋志峰,吴作伦,刘继忠.基于超声频域分析的碳纤维复合材料孔隙率检测[J].计量学报, 2006,27(1):53-56.
[5]Du Xiu-li, Wang Yan, Shen Yi. Ultrasonic signal classification based on ambiguity plane feature[J]. Journal of Systems Engineering and Electronics, 2009, 20(2):427-433.
[6]杜秀丽,沈毅,王艳.基于时频判别特征的焊缝超声检测缺陷分类[J].焊接学报,2008,29(2):89-92.
[7]严寒冰,殷国富. 基于MMW和ICER加权匹配的超声缺陷识别[J].数据采集与处理,2008,23(6):724-728.
[8]车红昆,吕福在,项占琴.超声检测信号多特征SVM Bayes融合识别[J].振动与冲击,2011,30(12): 265-269.
[9]张开银. 模式识别中的信息融合方法——二次决策[J].仪器仪表学报,2004,25(4):561-564.
[10]王伯雄,刘文峰,柳建楠,等.基于特征的超声信号分类检测方法[J].清华大学学报,2012,52(7): 941-945.
[11]Qian Du,Wei Wei,May D,et al.Noise-adjusted principal component analysis for buried radioactive target detection and classification[J].Nuclear Science,2010,7(6):3760-3767.
[12]鲍必赛,楼晓俊,李隽颖,等. 主成分分析在震动信号目标识别算法中的应用[J].华中科技大学学报,2012,40(7):24-28. |
|
|
|