Classifying pipe cracks by size from their pulse-echo ultrasonic signal is difficult but highly significant for the defect evaluation required in pipe testing and maintenance decision making. For this thesis, a binary Support Vector Machine (SVM) classifier, which divides pipe cracks into two categories: large and small, was developed using collected ultrasonic signals.
To improve the performance of this SVM classifier in terms of reducing test errors, we first combined the Sequential Backward Selection and Sequential Forward Selection schemes for input feature reduction. Secondly, we used the data dependent kernel instead of the Gaussian kernel as the kernel function in the SVM classifier. Thirdly, as it is time-consuming to use the classic grid-search method for parameter selection of SVM, this work proposes a Kernel Fisher Discriminant Ratio (KFD Ratio) which makes it possible to more quickly select parameters for the SVM classifier.
| Identifer | oai:union.ndltd.org:LACETR/oai:collectionscanada.gc.ca:AEU.10048/400 |
| Date | 11 1900 |
| Creators | Miao, Chuxiong |
| Contributors | Ming J. Zuo, Mechanical Engineering, Ming J. Zuo, Mechanical Engineering, Xiaodong Wang, Mechanical Engineering, Marinal Mandal, Electrical and Computer Engineering |
| Source Sets | Library and Archives Canada ETDs Repository / Centre d'archives des thèses électroniques de Bibliothèque et Archives Canada |
| Language | English |
| Detected Language | English |
| Type | Thesis |
| Format | 1126679 bytes, application/pdf |
| Relation | Chuxiong Miao; Yu Wang; Yonghong Zhang; Jian Qu; Zuo, M.J.; Xiaodong Wang; (2008), Electrical and Computer Engineering, 2008. CCECE 2008. Canadian Conference on 4-7 May 2008 Page(s):001627 - 001630 |
Page generated in 0.0017 seconds