Predicting the Reliability of a Complex System Using an Artificial Neural Network

摘要

The capability to predict the reliability of complex systems that must be deployedrnwithout overly prolonged or expensive testing is of increasing importance to the military test andrnevaluation community. The presentation of subsystem reliability data to an artificial neuralrnnetwork is a critical factor in the capability of such networks to produce accurate systemrnpredictions. By producing a matrix of values corresponding to subsystem reliabilities, using arnzero (0) for a nonexistent parallel resource and a one (1) for a nonexistent series subsystem, itrnwas possible to train an artificial neural network to accurately predict the overall systemrnreliability.