Research of Warship Equipment Faults Diagnosis System Based on Integrated Reasoning

Article Preview

Abstract:

Warship equipment diagnosis mechanism becomes more complicated with wide use of new technology. How to obtain the diagnosis result is a difficult problem in the field. According to the principle and shortage of traditional fault diagnosis, a new reasoning method was introduced for the warship equipment fault diagnosis, the method integrated the case-based reasoning (CBR), rule-based reasoning (RBR) and bayes-based reasoning (BBR), which can increase the systems flexibility and reasoning accuracy. The knowledge base, knowledge presentation and classification, reasoning process and reasoning realizations were mainly analyzed. The experiment shows that the reasoning method can provide a scientific basis for analysis and diagnosis of warship equipment.

You might also be interested in these eBooks

Info:

Periodical:

Advanced Materials Research (Volumes 756-759)

Pages:

4567-4571

Citation:

Online since:

September 2013

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2013 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] Qiang Cao. Design of Warship Equipment Fault Diagnosis Expert System based on Artificial Immune[J]. Ship & electronic engineering, 2005, 25(5): 42-45.

Google Scholar

[2] P.S. Rosembloom, A.R. Golding. Improving Accuracy by Combining Rule-based and Cased-based Reasoning[J]. Artificial Intelligence, 2006, 87(2): 215-254.

DOI: 10.1016/0004-3702(95)00120-4

Google Scholar

[3] Duan Jun. Study and Apply on Integrated Reasoning model of CBR, RBR and BBR in Traffic Accident Handing[J]. Journal of Baotou University, 2006, 25(2): 184-186.

Google Scholar

[4] Wei Dai, Bin Wang. A Diagnosis Expert System for Marine Diesel Engine based on CBR and RBR[J], Ship &Ocean Gineering, 2007, 36(5): 122-125.

Google Scholar

[5] Nick Crone, Aijun an, Christine Chan. Rule induction and case-based reasoning: Hybrid architectures appear advantageous[J]. IEEE Trans on Knowledge and Data Engineering, 2001, 11 (1): 166-174.

DOI: 10.1109/69.755625

Google Scholar