Abstract
In order to diagnose the fault of missile refrigeration system, aiming at the complex nonlinear relationship between the causes and symptoms of missile refrigeration system, we propose a method for fault diagnosis of refrigeration system based on the belief rule base (BRB). The method can use quantitative and qualitative information to establish a nonlinear model between input and output, and diagnose the system through optimization model. BRB can make comprehensive use of expert knowledge and historical data, which is more suitable for fault diagnosis. In order to address the problem of parameter inaccuracy in the initial BRB given by experts, combined with the information type of the failure of the refrigeration system, we use the chaotic particle swarm optimization learning model to train the initial BRB parameters given by experts to achieve the diagnosis of refrigeration faults in the refrigeration system. The experimental results show that the BRB after parameter optimization can better identify the state of the missile system and improve the accuracy of fault diagnosis.
Export citation and abstract BibTeX RIS
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.