Journal of Engineering and Applied Sciences

Year: 2019
Volume: 14
Issue: 13
Page No. 4532 - 4541

Neural Network and Control for Arterial Oxygen Saturation in Neonatal Infants

Authors : Lafta E.J. Alkurawy

Abstract: This study describes the blood Oxygen Saturation (SpO2) for neonatal infant’s by modeling and control methods. Out of analyzing and study the biological and modeling system, the mechanisms of ventilation helped the blood to be oxygenated. The oxygenation of the blood affected by Fraction of inspired Oxygen (FiO2), rate of respiratory and rate of heart had an effect on the oxygenation. The SpO2 was modeled by two 2 different methods. The models discussed are a neural network model and mathematic model. The best acting model was mathematic model because it was capable to detect to changes the biological in the infant’s and precisely predict the SpO2 for an extended time and is related to apply input FiO2. Two different controllers were designed. The controllers are PI and PID controller and they were designed by using the model of dynamic in mathematical way and with neural network. The controllers were structured to control the SpO2 with altering the values of FiO2. The control of two models were tested to get the response of output for SpO2 at zero steady state error, minimum peak overshoot and minimum rise time. The control of two models were tested on data to be simulated. The controllers for two models was got to be PID to get SpO2 at 80-90% with changing values of the FiO2 is at 20-30%. The values of SpO2 and FiO2 submitted are contrast between value of the nominal actual and value of comparing which is the best for controllers.

How to cite this article:

Lafta E.J. Alkurawy , 2019. Neural Network and Control for Arterial Oxygen Saturation in Neonatal Infants. Journal of Engineering and Applied Sciences, 14: 4532-4541.

Design and power by Medwell Web Development Team. © Medwell Publishing 2024 All Rights Reserved