Assumptive and uncertain factors, few leak samples, complex non-linear pipeline systems are the problems often involved in the process of pipeline leak detection. Furthermore, the pressure wave changes of leakage are similar to these of valve regulation and pump closure. Thus it is difficult to establish a reliable model and to distinguish the leak signal pattern from others in pipeline leak detection. The veracity of leak detection system is limited. This paper presents a novel technique based on the statistical learning theory, support vector machine (SVM) for pipeline leak detection. Support Vector Machine (SVM) is learning system that uses a hypothesis space of linear functions in a high dimensional feature space, trained with a learning algorithm from optimization theory that implements a learning bias derived from statistical learning theory. SVM is based on the principle of structure risk minimization as opposed to the principle of empirical risk minimization in conventional techniques. Thus, SVM has good performance for classification over small sample set. In this paper, an overview of the limitations of traditional statistics and the advantage of statistical learning theory will be introduced. In this paper, an SVM classifier is used to classify the signal pattern with few samples. Firstly, the algorithm of the SVM classifier and steps of using the model to identify leakage signals are studied. Secondly, the classification results of the experiment show that SVM classifier has high recognition accuracy. In addition, SVM is compared with neural network method. Then the paper concludes that in terms of classification ability and generalization performance, SVM has clearly advantages than neural network method over small sample set, so SVM is more applicable to pipeline leak detection.
Skip Nav Destination
2008 7th International Pipeline Conference
September 29–October 3, 2008
Calgary, Alberta, Canada
Conference Sponsors:
- International Petroleum Technology Institute and the Pipeline Division
ISBN:
978-0-7918-4857-9
PROCEEDINGS PAPER
Leak Detection Method Based on Support Vector Machine Available to Purchase
XiaoJing Fan,
XiaoJing Fan
China University of Petroleum, Beijing, China
Search for other works by this author on:
LaiBin Zhang,
LaiBin Zhang
China University of Petroleum, Beijing, China
Search for other works by this author on:
Wei Liang,
Wei Liang
China University of Petroleum, Beijing, China
Search for other works by this author on:
ZhaoHui Wang
ZhaoHui Wang
China University of Petroleum, Beijing, China
Search for other works by this author on:
XiaoJing Fan
China University of Petroleum, Beijing, China
LaiBin Zhang
China University of Petroleum, Beijing, China
Wei Liang
China University of Petroleum, Beijing, China
ZhaoHui Wang
China University of Petroleum, Beijing, China
Paper No:
IPC2008-64118, pp. 517-522; 6 pages
Published Online:
June 29, 2009
Citation
Fan, X, Zhang, L, Liang, W, & Wang, Z. "Leak Detection Method Based on Support Vector Machine." Proceedings of the 2008 7th International Pipeline Conference. 2008 7th International Pipeline Conference, Volume 1. Calgary, Alberta, Canada. September 29–October 3, 2008. pp. 517-522. ASME. https://doi.org/10.1115/IPC2008-64118
Download citation file:
12
Views
Related Proceedings Papers
Related Articles
Fuzzy Recurrence Plots for Shallow Learning-Based Blockage Detection in a Centrifugal Pump Using Pre-Trained Image Recognition Models
J. Comput. Inf. Sci. Eng (October,2023)
Water Hammer Simulation in a Steel Pipeline System With a Sudden Cross Section Change
J. Fluids Eng (September,2021)
Related Chapters
System Automation
Pipeline Operation & Maintenance: A Practical Approach, Second Edition
Introduction to Pipeline Systems
Pipeline Pumping and Compression Systems: A Practical Approach
Applications for Operation
Pipeline System Automation and Control