European Academic Research ISSN 2286-4822
ISSN-L 2286-4822
Impact Factor: 3.4546 (UIF)
DRJI Value : 5.9 (B+)
Article Details :
Article Name :
Neuro-Fuzzy and Neural Networks Models to Estimate Radon Exhalation Rate in Uranium OreRock Mine
Author Name :
EMAN SARWAT
Publisher :
Bridge Center
Article URL :
Abstract :
Radon gas concentration and its daughter products in underground uranium ore-rock mines are often controlled using system for mechanical ventilation. In those mines the calculation of exhalation rate is potentially based on ventilation system parameters. Neural Networks and Fuzzy logic as influential computational models for categorization and estimation, are used in many application fields. These two techniques are fairly complementary to each other in a way that what one is missing of the other can provide. Normally talking all kind of systems that include these two techniques can be called NeuroFuzzy systems. The present work has set a Neuro- Fuzzy and artificial neural network (ANN) model for predicting radon exhalation rate using experimental data of uranium ore-rock in China throughout mine ventilation. The effects of different ranges of training sample sets on forecasting performance of ANN and Neuro- Fuzzy are represented. Results show that Neuro-Fuzzy model used to predict radon exhalation rate of uranium ore-rock for the duration of mine ventilation, relatively give more accurate results than ANN methods. Furthermore, it is found that the models are more successful in terms of cost and time.
Keywords :
Neuro-Fuzzy; Uranium Mine; Ventilation; Radon Exhalation Rate; Artificial Neural Network.
Announcements
New Launched Project
onlineresearch
Recommend & Share
Copyright © 2013: www.euacademic.org , Best Viewed in IE7+, Chrome, Mozilla Firefox.