A Methodology to Predict the Empennage In-Flight Loads of a General Aviation Aircraft Using Backpropagation Neural Networks
Abstract
Back propagation neural networks were used to predict strains resulting from maneuver loads in the empennage structure of a Cessna l72P. The purpose of this research was to develop a methodology for the prediction of strains in the tail section of a general aviation aircraft that would not require installation of strain gages and to determine the minimum set of sensors necessary for a prediction suitable for small aircraft. This report provides a methodology for determining in-flight tail loads using neural networks. The method does not require the installation of strain gages on each airplane. It is an inexpensive and effective technique for collecting empennage load spectra for small transport airplanes already in service where installation of strain gages are impractical. Linear accelerometer, angular accelerometer, rate gyro, and strain gage signals were collected in flight using DAQBook portable data acquisition system for dutch-roll, roll, sideslip left, sideslip right, stabilized g turn left, stabilized g turn right, and push-pull maneuvers at airspeeds of 65 KIAS, 80 KIAS, and 95 KIAS. The sensor signals were filtered and used to train the neural networks. Modular neural networks were used to predict the strains. The horizontal tail neural network was trained with c.g. Nz and x-, y-, and z-axis angular accelerometer signals and predicted 93% of all strains to within 50 micro epsilon of measured values. The vertical tail neural network predicted 100% of all strains to within 50 micro epsilon of measured values.
Document Details
- Document Type
- Technical Report
- Publication Date
- Feb 01, 2001
- Accession Number
- ADA392843
Entities
People
- David S Kim
- Maciej Marciniak