Using neural networks for estimating cruise missile reliability

In an effort to assist Air Combat Command in its efforts to improve its current methodology for predicting the reliability of its Air Launched Cruise Missile and Advanced Cruise Missile stockpiles, an easy to use and maintain model was developed. The requirements were a model that delivers a 24-month prediction of cruise missile reliability using existing data sources, collection methods and software. It should be easily maintainable and developed to allow a layperson to enter updated data and receive an accurate reliability prediction. Such a model is presented which allows for the fusion of logistics regression, feed-forward neural networks and radial basis function neural network models.