Application of artificial neural network to estimate power generation and efficiency of a new axial flux permanent magnet synchronous generator Emre C ¸ elik a,* , Halil G € or b , Nihat € Oztu ¨rk a , Erol Kurt a a Department of Electrical and Electronics Engineering, Faculty of Technology, Gazi University, Besevler, Ankara, Turkey b Department of Electrical and Electronics Engineering, Faculty of Engineering, Hakkari University, Hakkari, Turkey article info Article history: Received 28 October 2016 Received in revised form 28 December 2016 Accepted 25 January 2017 Available online xxx Keywords: Artificial neural network Axial flux permanent magnet syn- chronous generator Efficiency Estimation Power abstract An estimation study on the output power and the efficiency of a new-designed axial flux permanent magnet synchronous generator (AFPMSG) is performed. For the estimation al- gorithm, a multi-layer feedforward artificial neural network (ANN) is developed. Various experimental results from the generator have been used for the training purpose in the cases of different electrical loads and rotational speeds. Some experimental data is kept out of the training process for testing the network and the errors have been evaluated after the formation of the network. According to the findings, a network with three layers has been adequate to achieve very good error percentage between the ANN and laboratory studies. The maximal testing error percentages are found to be nearly 3% and 4% for the output power and efficiency estimations, respectively. According to that finding, the developed ANN has a good property that it can be used in place of the designed generator, especially when the generator mathematical model is required. In addition, since power and efficiency are important for present applications, the present tool can be used to es- timate the data for those characteristics of the machines and even it can be beneficial for the applications, where a nonlinear relationship among the power generation, generator efficiency, speed and load is required. © 2017 Hydrogen Energy Publications LLC. Published by Elsevier Ltd. All rights reserved. Introduction The present technology achieves to produce efficient perma- nent magnets (PM) with desired shape and magnetization by using the rare earth elements. That accelerates the industry to use them in many renewable energy applications, especially the wind energy generators [1e3]. The most known magnets, namely NdFeB have many industrial and scientific applications over electrical machines. The main features can be mentioned for their higher magnetic flux densities, easy magnetization and shaping. According to literature, there exist some superiorities of the AFPMSGs over the current excited synchronous generators or squirrel cage ones: high efficiency, stability, reliability and cost [4,5]. After the appli- cation of optimization, high power densities with increased efficiency and reduced cogging torque can be obtainable for low wind turbines [6,7]. * Corresponding author. Fax: þ90 312 89 47. E-mail address: emrecelik@gazi.edu.tr (E. C ¸ elik). Available online at www.sciencedirect.com ScienceDirect journal homepage: www.elsevier.com/locate/he international journal of hydrogen energy xxx (2017) 1 e8 http://dx.doi.org/10.1016/j.ijhydene.2017.01.168 0360-3199/© 2017 Hydrogen Energy Publications LLC. Published by Elsevier Ltd. All rights reserved. Please cite this article in press as: C ¸ elik E, et al., Application of artificial neural network to estimate power generation and efficiency of a new axial flux permanent magnet synchronous generator, International Journal of Hydrogen Energy (2017), http://dx.doi.org/10.1016/ j.ijhydene.2017.01.168