Keywords: Multi-component balance, multi-piece balance, balance calibration, neural networks, Levenberg-Marquardt algorithm
Abstract: The use of neural networks in the estimation of balance loading from the measured balance response is investigated. The neural network load estimates are compared to the estimated loading obtained from the more traditional approach using a polynomial calibration matrix; this calibration matrix is obtained from a global regression analysis of the balance calibration data. For the current work, multiple input, single output networks were trained using a Levenberg-Marquardt algorithm for each of the balance load gages.
NASA Ames Research Center, Moffett Field CA 94035-1000, (650) 604-5000
Privacy Statement
URL: http://rotorcraft.arc.nasa.gov/
This Website Maintained By: Randall L. Peterson.
Responsible NASA Official: Dr. William Warmbrodt (Chief)
Ames Research Center Homepage
NASA Homepage