In this paper two artificial intelligence techniques to predict and control behavior of a 25W fabricated proton exchange membrane (PEM) fuel cell, have been investigated. These approaches are: "Parametric Neural Network (PNN)" and "Group Method of Data Handling (GMDH)" for the first time. A PNN model is developed by introducing a "p" parameter in the activation function of the neural network. PNN model with its specific tangent hyperbolic transfer function have the ability to be with different nonlinearity degrees of input data. To develop GMDH network, quadratic polynomial was utilized. To determine proper weights of GMDH network, back propagation algorithm has been used. The input layer consists of gas pressure, fuel cell temperature and input current experimental data, to predict the output voltage. The results show that both generalized Parametric and GMDH-type neural networks are reliable tools to predict the output voltage of PEM fuel cell with high coefficient of determination values of 0.96 and 0.98.

In this study, design, design calculations and simulation of a permanent magnet generator, which includes two sections of radialand axial flux, are discussed. The output power from the generator is 1.1 kilowatt. In the design of the generator, a cone-shapedstructure with a 90-degree cone angle of 45 degrees from the sides is used for the rotor. In order to compare the various structuresof the synchronous generator, and given that today, permanent magnet generators have been considered with regard to featuressuch as lower weight, higher yields and higher power density than other conventional generators. A finite element analysis of thegenerator developed in Maxwell software. In the radial flux section, the generator includes a conical rotor and a cone stator. Thewindings on the external stator are trapezoidal and are located in stator racks. The finite element analysis of the generator confirmsthat permanent magnet magnets designed on the inner rotor have provided a magnetic flux equal to 1.2 Tesla in the air gap betweenthe generator and the winding of the stator. The rotor magnetic field analysis, rotor magnetic field strength, magnetic field intensity,and magnetic field density at a speed of 500 rpm for cone structure have been performed. In the axial flux section, the generatorconsists of two rotors and a grooved stator, which is obtained by simulating a 1.1 kW power with a sinusoidal three-phase voltage.Two sections of radial flux with a cone-shaped rotor and axial flux side by side make up the generator.