NEURAL-NETWORK-BASED FAILURE RATE FOR BOEING-737 TIRES

This paper presents an artificial neural network (ANN) model for forec asting the failure rate of Boeing-737 airplane tires. A neural model i s developed using the backpropagation algorithm as a Learning rule. Th e inputs to the neural network are independent variables and the outpu t is the failure rate of the tire. A comparison of the neural model wi th the Weibull model is made for validation purposes. It is found that the failure rate predicted by the ANN is closer in agreement with the real data than the failure rate predicted by the Weibull model.