Predicting the ejection velocity of ejection seat via BP neural network

The ejection velocity of escape system, which is a primary parameter of the sequencer control subsystem, determines the parachute shooting time. It is found that in some certain circumstances large errors of the measured velocity are generated, which significantly influence the performance of the escape system. In this paper, a method that predicts the ejection velocity by neural network was presented. Firstly, the mathematical model of ejection procedure was established, based on which, a module simulation solver on MSC.EASY5 fundamental platform was developed and programmed. According to this solver, considerable ejection conditions which were sufficient to contain all representative situations in the life-saving envelop of escape system were calculated. Then the relationship between ejection velocity and other parameters could be obtained from the simulation results. Subsequently, a back propagation (BP) neural network was established to fulfill the relationship. Further experimental validation indicated that the error generated can be accepted in engineering application. Consequently, method that predicts the ejection velocity via BP neural network was proved to be feasible and will be a useful technology for escape system.