The aircraft electrical system provides power for the normal operation of the aircraft. Its normal operation is critical to ensure the safe flight of the aircraft. Therefore, it is very important to identify the hazards in the aircraft electrical system. In this paper, a hazard identification and prediction system which can intelligently identify potential hazards in aircraft electrical system is proposed. The proposed hazard identification and prediction system mainly includes three processes: variable selection, hazard identification, and hazard prediction. In the process of variable selection, the stepwise regression analysis is used to select 8 main parameters that have the major influence on the DC bus voltage value from 18 parameters. In the process of hazard identification, support vector machine is used to identify pre-existing hazards in electrical system based on the status of all components. The identification accuracy of the support vector machine is 92.3%. When the electrical system does not have unacceptable hazards, a prediction of the variation range of the DC bus voltage value in the aircraft electrical system is performed. The average prediction relative error of support vector machine is only 0.86%. Overall, the identification accuracy and average prediction relative error show that the proposed hazard identification and prediction system can accurately and effectively identify and predict the hazards in the aircraft electrical system.
NOVEL WRAPPER APPROACH FOR VARIABLE SELECTION IN SUPPORT VECTOR MACHINE