In order to improve the reliability, security and validity of such type Missile Launcher, The faults prediction theory is introduced based on fuzzy neural network. The faults prediction analysis model is built, and an advanced training algorithm is proposed. Such algorithm is tested by using in the fault prediction of the missile launcher. The Experiment results illustrate that by using the proposed model, the faults prediction speed is faster 80% than ever, the prediction veracity is advanced, and the cost is reduced to 50%.
Bi-Real Net: Enhancing the Performance of 1-Bit CNNs with Improved Representational Capability and Advanced Training Algorithm