Name
Title | ||
|---|---|---|
The Detection System of Oil Tube Defect Based on Multisensor Data Fusion by Classify Support Vector Machine |
Abstract | ||
|---|---|---|
Statistical learning theory is introduced to defect detection and a detection system of oil tube defect based upon support vector machine (SVM) is presented, it got the original information by multigroup vortex sensors and leakage magnetic sensors. The oil tube defect pattern had four class that is crack, etch pits, eccentric wear and unbroken, so the multi-classify support vector machine was adopt to make the multisensor data fusion to detect the defect pattern of oil tube correctly, moreover, the genetic algorithm(GA) was used to optimize SVM parameters. The experimental results show that this method is feasible and effective. |
Year | DOI | Venue |
|---|---|---|
2006 | 10.1109/ICICIC.2006.535 | ICICIC (3) |
Keywords | Field | DocType |
defect detection,support vector machine,oil tube defect,classify support,detection system,multisensor data fusion,oil tube,defect pattern,oil tube defect pattern,vector machine,svm parameter,eccentric wear,multi-classify support vector machine,genetic algorithm,support vector machines,genetic algorithms,statistical analysis,sensor fusion,pipelines | Statistical learning theory,Pipeline transport,Leakage (electronics),Pattern recognition,Computer science,Support vector machine,Vortex,Sensor fusion,Artificial intelligence,Genetic algorithm,Machine learning,Statistical analysis | Conference |
ISBN | Citations | PageRank |
0-7695-2616-0 | 1 | 0.38 |
References | Authors | |
1 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jingwen Tian | 1 | 36 | 13.10 |
| Meijuan Gao | 2 | 32 | 12.32 |
| Kai Li | 3 | 3 | 3.30 |