A Multi-source Information Fusion Fault Diagnosis Method for Vectoring Nozzle Control System Based on Bayesian Network

The vectoring nozzle control system has a complex structure, with many excitation sources and strong fault correlation. To improve the accuracy of fault diagnosis, this paper presents an approach combining multi-source information fusion and Bayesian network to detect and identify the fault of vectoring nozzle control system. The multi-source diagnosis framework is established to fuse the characteristic information collected by different sensors of system. Based on the collected data, a multi-fault Bayesian network is constructed to fuse the time-frequency feature evidence body. In addition, a Bayesian classifier is designed to identify the fault type according to the maximum posterior probability criterion. Finally, a case study is designed to verify the method proposed in this paper, and the results show that the proposed method can detect the fault accurately, with an accuracy of not less than 90%. The diagnostic results are more reliable and have low uncertainty, which illustrates the validity of the proposed method and shows a broad practical application value in other comparable control systems.