Nateri K Madavan

7191161, Mar 13, 2007

Jul 31, 2003

10/637087

Man Mohan Rai - Los Altos CA, US
Nateri K. Madavan - Cupertino CA, US

The United States of America as represented by the Administrator of the National Aeronautics and Space Administration - Washington DC

G06E 1/00

706 15, 706 21, 706 26

A method and system for data modeling that incorporates the advantages of both traditional response surface methodology (RSM) and neural networks is disclosed. The invention partitions the parameters into a first set of s simple parameters, where observable data are expressible as low order polynomials, and c complex parameters that reflect more complicated variation of the observed data. Variation of the data with the simple parameters is modeled using polynomials; and variation of the data with the complex parameters at each vertex is analyzed using a neural network. Variations with the simple parameters and with the complex parameters are expressed using a first sequence of shape functions and a second sequence of neural network functions. The first and second sequences are multiplicatively combined to form a composite response surface, dependent upon the parameter values, that can be used to identify an accurate model.

6606612, Aug 12, 2003

Aug 13, 1999

09/374491

Man Mohan Rai - Los Altos CA
Nateri K. Madavan - Cupertino CA

The United States of America as represented by the Administrator of the National Aeronautics and Space Administration - Washington DC

G06E 100

706 15

A method and system for design optimization that incorporates the advantages of both traditional response surface methodology (RSM) and neural networks is disclosed. The present invention employs a unique strategy called parameter-based partitioning of the given design space. In the design procedure, a sequence of composite response surfaces based on both neural networks and polynomial fits is used to traverse the design space to identify an optimal solution. The composite response surface has both the power of neural networks and the economy of low-order polynomials (in terms of the number of simulations needed and the network training requirements). The present invention handles design problems with many more parameters than would be possible using neural networks alone and permits a designer to rapidly perform a variety of trade-off studies before arriving at the final design.