220
Views
2
CrossRef citations to date
0
Altmetric
Research Articles

A New Artificial Neural Network Model for the Output Voltage and Power Predictions of Permanent Magnet Generators with Variable Air Gaps

ORCID Icon, ORCID Icon & ORCID Icon
Pages 1131-1142 | Received 26 Sep 2022, Accepted 10 Nov 2022, Published online: 29 Nov 2022
 

Abstract

Abstract—An artificial neural network (ANN) model is recommended for the analysis and prediction of the output results of a recently designed and constructed generator known as a permanent magnet generator with axial flux. The generator is considered to generate a power scale of P = 3 kW, especially for off-grid household usage far from the network. This machine has an adjustable air gap mechanism, and P = 3 kW is the maximum power; thus, this power can be decreased comfortably by increasing the air gap further to 7 mm. In this case, the maximum power rate can be decreased to P = 1.5 kW according to the experimental confirmation. As a new technique, an ANN approach is introduced for the predictions of voltage and power obtained output for various electrical loads, rotor speeds, and air gaps because it is difficult to get output values for all those machine parameters. In addition, this ANN technique enables one to find the generated voltage and power for specific extremely low air gap values (i.e., 0.2 mm, 0.4 mm, 0.6 mm), which is hard in experimental work due to construction difficulties. The ANN model is used to predict the output values of the generator before any laboratory practice successfully, and the users can determine the correct air gap ranges to their required power regimes for this generator.

Additional information

Funding

The presented paper has been supported by TUBITAK (The Scientific and Technological Research Council of Turkey) with the grant (No. MAG-315M483). The authors have patents under Turkish Patent Institute (No. TR 2015 04164 B and TR 2013 13062 B).

Notes on contributors

Adem Tekerek

Adem Tekerek is an associate professor at Gazi University, Computer Engineering Department, Technology Faculty. He graduated from Technical Education Faculty, Computer Systems Education Department in 2007. He graduated from MSc program of Informatics Institute in 2010. His master thesis is about Institutional Content Management Systems. He graduated from PhD program of Informatics Institute in 2016. His PhD thesis is about Web Application Firewall algorithms. He published 35 papers on computer sciences. His research is artificial ıntelligence, machine learning, deep learning, data mining and their applications especially on information security.

Erol Kurt

Erol Kurt took his M. Sc. degree from the Inst. Science & Technology, Gazi University in Ankara, Turkey in 2001. He was awarded by an European Graduate College Grant during his Ph.D study at the Inst. Physics & Math., Bayreuth University in Germany. He completed his Ph. D. degree in 2004 on the instabilities of rotating magnetic fluids and worked at Turkish Atomic Energy Authority R&D Department for 3 years. He was assigned to the position of Assoc. Prof. at Technology Faculty, Gazi University. He is chairman to European Conf. Renewable Energy Systems (ECRES) and Interdisciplinary Conf. Mechanics, Computers and Electrics and the guest editor for many reputable journals. He is also the Editor-in-Chief and owner to J. Energy Systems (dergipark.org.tr/jes) and the member of Turkish Science Research Foundation (TUBAV). He is currently full Professor in Technology Faculty of Gazi University. He wrote some books on applied energy, physics and chaos phenomena in addition to many journal and conference papers. His main research areas include nonlinear phenomena in electrical/electronic circuits, electric machine design, mechanical vibrations, chaos, plasmas and magneto hydrodynamics.

Mehmet Tekerek

Mehmet Tekerek took his M.Sc. degree from the Inst. Science & Technology, Gazi University in Ankara, Turkey in 2000. He completed his Ph.D. degree from the Inst. Science & Technology, Gazi University in Ankara, Turkey in 2006 on Industrial Technology Education. He is working at Kahramanmaraş Sütçü İmam University as a professor & CEO of Kahramanmaraş TechnoPark Corp. His main research areas are robotics, industrial technology, computer science education.

Log in via your institution

Log in to Taylor & Francis Online

PDF download + Online access

  • 48 hours access to article PDF & online version
  • Article PDF can be downloaded
  • Article PDF can be printed
USD 61.00 Add to cart

Issue Purchase

  • 30 days online access to complete issue
  • Article PDFs can be downloaded
  • Article PDFs can be printed
USD 412.00 Add to cart

* Local tax will be added as applicable

Related Research

People also read lists articles that other readers of this article have read.

Recommended articles lists articles that we recommend and is powered by our AI driven recommendation engine.

Cited by lists all citing articles based on Crossref citations.
Articles with the Crossref icon will open in a new tab.