A comparison of main rotor smoothing adjustments using linear and neural network algorithms

Helicopter main rotor smoothing is a maintenance procedure that is routinely performed to minimize destructive airframe vibrations induced by non-uniform mass and/or aerodynamic distributions in the main rotor system. This important task is both time consuming and expensive, so improvements to the process have long been sought. Traditionally, vibrations have been minimized by calculating adjustments based on an assumed linear relationship between adjustments and vibration response. In recent years, artificial neural networks have been trained to recognize non-parametric mappings between adjustments and vibration response. This study was conducted in order characterize the adjustment mapping of the Vibration Management Enhancement Programʹs PC-ground base system (PC-GBS), and compare it to the linear adjustment mapping used in the aviation vibration analyzer (AVA). Results show that, in a majority of situations, the neural network algorithms in PC-GBS produce adjustments that are identical to those produced by a linear algorithm similar to that used by AVA. Therefore, the use of neural networks for creating the mapping between adjustments and vibration response, provides no significant improvement over a linear mapping.