Application of artificial neural network to estimate power generation and efficiency of a new axial flux permanent magnet synchronous generator

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 algorithm, 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 estimate 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. (C) 2017 Hydrogen Energy Publications LLC. Published by Elsevier Ltd. All rights reserved.