Home           Contact us           FAQs           
     Journal Home     |     Aim & Scope    |    Author(s) Information      |     Editorial Board     |     MSP Download Statistics
2013 (Vol. 5, Issue: 16)
Article Information:

A Fault Detection Model of Marine Refrigerated Containers

Jun Ji and Houde Han
Corresponding Author:  Jun Ji 

Key words:  Fault detection, one-class svm, parameter optimization, refrigerated container, , ,
Vol. 5 , (16): 4066-4070
Submitted Accepted Published
March, 16, 2012 January 11, 2013 April 30, 2013

A fault detection model based on One-Class Support Vector Machine was established to solve the large difference in sample size between the normal data and fault data of refrigerated containers. During the model training process, only the normal samples were needed to be learned, and an accurate identification of abnormal was 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 refrigerated containers based on One-Class Support Vector Machine was established, and the test results show that the model has a high recognition rate against abnormal of 97.4% and zero false alarm rate.
Abstract PDF HTML
  Cite this Reference:
Jun Ji and Houde Han, 2013. A Fault Detection Model of Marine Refrigerated Containers.  Research Journal of Applied Sciences, Engineering and Technology, 5(16): 4066-4070.
    Advertise with us
ISSN (Online):  2040-7467
ISSN (Print):   2040-7459
Submit Manuscript
   Current Information
   Sales & Services
Home  |  Contact us  |  About us  |  Privacy Policy
Copyright © 2015. MAXWELL Scientific Publication Corp., All rights reserved