Abstract
A fault detection model based on One-Class Support Vector Machine (OC-SVM), a new SVM method, is established to solve the large difference in sample size between the normal data and fault data of reefer containers. During the model training process, only the normal samples are needed to be learned, and an accurate identification of abnormal can be achieved, which may solve the problem of lack of fault samples in practice. By comparison experiments between different kernel functions and kernel parameter optimization, a fault detection model of reefer containers based on OC-SVM is established, and the test results show that the model has a high recognition rate against abnormal and low false alarm rate.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Zhong, Q.L., Cai, Z.X.: Sensor Fault Diagnosis based on One-Class SVM. Computer Engineering and Application 19, 1–3 (2006)
Scholkopf, B., Platt, J.C., Taylor, J.S., et al.: Estimating the support of a high-dimensional distribution. Neural Computation 13, 1443–1471 (2001)
Tax, D.M.J., Duin, R.P.W.: Support vector domain description. Pattern Recognition Letters 20, 1191–1199 (1999)
Xu, T., Luo, Y., He, D.K.: SMO Training Algorithm for Hyper-sphere One-class SVM. Computer Science 5(6), 178–180 (2008)
Vapnik, V.: SVM Method of Estimating Density, Conditional Probability, and Conditional Density. In: IEEE International Symposium on Circuits and Systems, May 28-31(2000)
Gary, G.L., Nelson, N.H., Norden, E.H.: Application of the Hilbert-Huang transform to machine tool condition/health monitoring. In: AIP Conference Proceedings, vol. 615(1), pp. 1711–1718 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ji, J., Han, H. (2011). Research on Fault Detection System of Marine Reefer Containers Based on OC-SVM. In: Lin, S., Huang, X. (eds) Advances in Computer Science, Environment, Ecoinformatics, and Education. CSEE 2011. Communications in Computer and Information Science, vol 215. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23324-1_63
Download citation
DOI: https://doi.org/10.1007/978-3-642-23324-1_63
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-23323-4
Online ISBN: 978-3-642-23324-1
eBook Packages: Computer ScienceComputer Science (R0)