Highly Accurate Multi-layer Perceptron Neural Network for Air Data System

Authors

  • H. S. Krishna Aeronautical Development Agency, Bangalore

DOI:

https://doi.org/10.14429/dsj.59.1574

Keywords:

Back propagation, calibration, curve-fitting, error, inner product, logistic function, neuron, perceptron, pressure probe, training network, synaptic weights

Abstract

The error backpropagation multi-layer perceptron algorithm is revisited. This algorithm is used to train and validate two models of three-layer neural networks that can be used to calibrate a 5-hole pressure probe. This paper addresses Occam's Razor problem as it describes the adhoc training methodology applied to improve accuracy and sensitivity. The trained outputs from 5-4-3 feed-forward network architecture with jump connection are comparable to second decimal digit (~0.05) accuracy, hitherto unreported in literature.

Defence Science Journal, 2009, 59(6), pp.670-674, DOI:http://dx.doi.org/10.14429/dsj.59.1574

Downloads

Published

2009-11-01

How to Cite

Krishna, H. S. (2009). Highly Accurate Multi-layer Perceptron Neural Network for Air Data System. Defence Science Journal, 59(6), 670–674. https://doi.org/10.14429/dsj.59.1574

Issue

Vol. 59 No. 6: Advances in Microelectromechanical Systems

Section

Short Communication

License

 Where otherwise noted, the Articles on this site are licensed under Creative Commons License: CC Attribution-Noncommercial-No Derivative Works 2.5 India