An effective fault detection approach for electrical equipment of propulsion system in a type of vessel based on subjective Bayesian principle

Electrical equipment in a vessel must endure threatening circumstance such as high humidity, high temperature, fierce shake, electromagnetic compatibility and others, which may result in the decrease of their reliability. Some faultinesses and bottlenecks caused in design and manufacturing process can also bring equipment into trouble. For the limitation of space in a vessel, a large number of equipments are located in some narrow places, which can bring the difficulty in eliminating faults and even in measuring some parameters to testify them. Because many kinds of electrical equipments cooperate to execute the same task for propulsion, lots of faults in different equipments can perform same breaker down appearances in this system. So it is a hard and crucial task for crew to rapidly detect and eliminate these faults to insure the safety of navigation. In this paper, The subjective Bayesian principle is employed to carry out the diagnosis decision, in the view of some uncertainties, so as to detect faults in these electrical equipments of propulsion system based on the former frequency of faults and potential priority level of measuring time and checkout time. Finally, a simulation experiment is made to validate and demonstrate the effectiveness of the method proposed in this paper.

[1]  K. Cios,et al.  A Bayesian approach for dealing with uncertainties in detection of coronary artery stenosis using a knowledge-based system , 1989, IEEE Engineering in Medicine and Biology Magazine.

[2]  I. F. Morrison,et al.  A statistical method for the detection of power system faults , 1997 .

[3]  T. Assaf,et al.  Diagnostic expert systems from dynamic fault trees , 2004, Annual Symposium Reliability and Maintainability, 2004 - RAMS.

[4]  Lingling Sun,et al.  Application of test & measure in microwave device characterization , 2005, 2005 Asia-Pacific Microwave Conference Proceedings.

[5]  He Yi-gang Research on the Fault Diagnosis of Analog Circuits Based on the Data Fusion with Neural Network , 2005 .

[6]  N.I. Elkalashy,et al.  Modeling and experimental verification of high impedance arcing fault in medium voltage networks , 2007, IEEE Transactions on Dielectrics and Electrical Insulation.

[7]  E. Culurciello,et al.  Electrical Noise Analysis of an Integrated Patch-Clamp Amplifier , 2007, 2007 IEEE Biomedical Circuits and Systems Conference.

[8]  D.F. Leite,et al.  Real-Time Model-Based Fault Detection and Diagnosis for Alternators and Induction Motors , 2007, 2007 IEEE International Electric Machines & Drives Conference.

[9]  Spilios D. Fassois,et al.  A Statistical Method for the Detection of Sensor Abrupt Faults in Aircraft Control Systems , 2008, IEEE Transactions on Control Systems Technology.

[10]  Shan Ning,et al.  A method of data fusion system for fault detection based on model-based diagnosis and evidence theory , 2008, 2008 International Conference on Condition Monitoring and Diagnosis.

[11]  João Miguel da Costa Sousa,et al.  An architecture for fault detection and isolation based on fuzzy methods , 2009, Expert Syst. Appl..

[12]  Karim Salahshoor,et al.  A fault detection and diagnosis system based on input and output residual generation scheme for a CSTR benchmark process , 2010, 2010 IEEE International Conference on Mechatronics and Automation.

[13]  Djaffar Ould Abdeslam,et al.  Adaline for fault detection in Electrical High Voltage transmission line , 2010, IECON 2010 - 36th Annual Conference on IEEE Industrial Electronics Society.

[14]  Tao Zhang,et al.  Low-Cost Fiber-Optic Temperature Measurement System for High-Voltage Electrical Power Equipment , 2010, IEEE Transactions on Instrumentation and Measurement.

[15]  Shuai Zhang,et al.  Two-stage structural damage detection using fuzzy neural networks and data fusion techniques , 2011, Expert Syst. Appl..