Artificial neural network analysis on an axial flux permanent magnet generator having variable air gap and power regime

TEKEREK A., KURT E.

SADHANA-ACADEMY PROCEEDINGS IN ENGINEERING SCIENCES, cilt.46, sa.4, 2021 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 46 Sayı: 4
  • Basım Tarihi: 2021
  • Doi Numarası: 10.1007/s12046-021-01768-0
  • Dergi Adı: SADHANA-ACADEMY PROCEEDINGS IN ENGINEERING SCIENCES
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Aerospace Database, Communication Abstracts, INSPEC, Metadex, zbMATH, Civil Engineering Abstracts
  • Anahtar Kelimeler: Artificial neural network, generator, axial flux, air gap, power, SYNCHRONOUS GENERATOR, DESIGN, CONTROLLER, PMG
  • Gazi Üniversitesi Adresli: Evet

Özet

In the present study, an artificial neural network (ANN) design has been proposed to analyze and estimate the output quantities of a newly manufactured generator, namely axial flux permanent magnet generator (AFPMG). The machine has been designed with a maximum power of 3 kW for the household electric power generation. As one of the innovative points, this machine has a variable air gap between the stator and the rotors, thereby the maximal power scale can be determined easily by adjusting the air gap between 2 mm and 7 mm. It means that the maximal power has values between 3 kW and 1.5 kW. ANN approach for such a machine is important in the sense that the estimation of output power, voltage and current values under various speeds and electrical loads are vital for the optimum operation of the machine. The designed ANN algorithm has been successful to estimate the output power and voltage of the newly produced generator for different air gap and speed and electrical load parameters.