Artificial neural network-based temperature prediction in heat sinks with cross cuts fins
by V. Kannan; S. Arunkumar; Muniyandi Venkatesan
International Journal of Advanced Intelligence Paradigms (IJAIP), Vol. 7, No. 3/4, 2015

Abstract: Soft computing techniques are predominantly used in varied sectors of research for accurate prediction and optimisation. Recent advancements in artificial neural network (ANN) and its capability to predict the data have increased its range of applications including heat transfer problems. The present paper aims to predict base plate temperature of cross cut fins of variable height (5-15 mm), fin spacing (5.85-32 mm), number of crosscuts (0-5), heat duty (20-100 W) for constant fin thickness (3 mm) and base plate dimensions (180 × 250 mm). A neural network model is designed for a rectangular heat sink with cross cut fins. The model is developed using the data from numerical heat transfer calculation carried out in ANSYS FLUENT©. The numerical model is validated with similar experimental results available in literature. The simulated data are used to train several neural-network configurations and the best neural-network model is used for prediction. The ANN model is used to predict the base plate temperatures of cross cut fins. The results reveal the ability of using ANN for accurate prediction of base plate temperature.

Online publication date: Wed, 16-Dec-2015

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Advanced Intelligence Paradigms (IJAIP):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com