Two methodologies for increasing the efficiency and effectiveness of computer analysis of aerospace structures will be addressed. The approach is the use of functional-link neural-net technology for generalization of quantitative analysis results so as to circumvent the need for extensive time-consuming reanalysis and the use of the episodal associative memory for capturing design experience for the guidance of subsequent designs. The functional-link net methodology is a neural-net technology developed by the firm and is particularly useful for learning functional relationships and for providing accurate quantitative estimates in response to designs and for converging in on optimal designs. The episodal associative memory is a computer architecture for organizing and storing experimental knowledge which can be retrieved associately in response to new tasks. This additional functionality can be effective in directing the creation and analysis of a new design.The resulting computer soft-ware systems will greatly enhance the power of all finite-element analysis tools and optimal design tools. This technology will find use in essentially all computer design aids offered commercially.aerospace, structures, analysis, optimal-design, neural networks, associative -memorySTATUS: Phase I Only
