NEURAL NETWORK-BASED PREDICTION OF CARDIOVASCULAR RESPONSE DUE TO THE GRAVITATIONAL EFFECTS

Z. Li and W.W. Melek

Keywords

Orthostatic stress, cardiovascular dynamics, Gtransition, fuzzylogic, neural networks, adaptivenetworkbased fuzzy inference system

Abstract

It is well-documented in the literature that the orthostatic stress during flight maneuvers induces changes in pilots’ cardiovascular system by imposing dramatic changes to the blood circulation process. Research reported for prediction of cardiovascular system dynamic response during G-transition is limited. As such, more models are needed to gain insight into the behavior of cardiovascular response during G-transition. Therefore, the objective of this paper is to develop two novel models based on: (1) artificial neural network (ANN) and (2) adaptive-network-based fuzzy inference system (ANFIS) to predict the variations of the blood pressure (BP) with respect to flight maneuver’s parameters, i.e., dwell time, during G-transitions. The proposed models will be used to provide operational recommendations and pilot selection for any routinepredefined flight maneuver. The training data for ANN and ANFIS are based on experimental data sets collected from a man-rated electronic tilt table that applies gigahertz-acceleration transition from +0.861 Gz (head-up (HU)) to −0.767 Gz (head-down (HD)) and back to +0.861 Gz (HU) using either pitch or roll rotation. A case study is presented on how the model is intended to be used in future to predict pilot’s cardiovascular response and evaluate the pilot’s qualification for a specific maneuver.

Important Links:



Go Back