A Stochastic Neural Network Model for Missile Reliability

The proposed project will develop prototype software for a Stochastic Neural Network for Missile Reliability Prognostics. A neural network model will be developed to predict missile reliability based on the environmental history of particular missiles.Prediction training will be employed to predict missile reliability at future times, based only on training data available at the current time. Principal components metrics will be used to quantify generic modeling uncertainty based on past experience,for purposes of evaluating the predictive accuracy of future reliability estimates. The innovation proposed here will combine the benefits of prediction training and generic uncertainty modeling to quantify the accuracy of reliability predictions based ona statistical comparison of earlier predictions with subsequent observations. Both will be correlated with measurements of the ambient environment recorded by a data logger. Statistical analyses of the environmental data will be performed to coincidewith the update of reliability information, reducing the environmental data to time dependent statistical parameters.In addition to providing the Army with a tool for missile reliability prognostics, an immediate spin-off might very well be the applicationto Sandia's maintenance of the Nation's nuclear weapons stockpile, where radiation is an important environmental factor. Other potential applications involve various types of mission-critical equipment used by all branches of the armed services, as wellas both military and commercial aircraft. ACTA has taken the first steps in developing a fiber-optic structural health monitoring system for aerospace vehicles under a SBIR project funded by NASA. This system will record stress cycle histories throughoutan aircraft for purposes of monitoring its structural health. The use of a reliability prognostics tool in conjunction with stress cycle monitoring could significantly improve the operational safety of military and commercial aviation.