Skip to Main Content
Genetic algorithms are used for the systematic selection of inputs for a parameter modeling system based on a neural network function approximator. Due to the nature of the underlying system, issues such as learning, generalization, exploitation, and robustness are also examined. In the application considered, modeling critical parameters of the Space Shuttle Main Engine (SSME), the functional relationships among measured parameters are unknown and complex. Furthermore, the number of possible input parameters is quite large. Many approaches have been proposed for input selection, but they are either not possible due to insufficient instrumentation, are subjective, or they do not consider the complex multivariate relationships between parameters. Due to the optimization and space searching capabilities of genetic algorithms, they were employed in this study to systematize the input selection process. The results suggest that the genetic algorithm can generate parameter lists of high quality without the explicit use of problem domain knowledge.