This paper includes an experimental study of hydrogen mass flow rate and inlet hydrogen pressure effect on the fuel cell performance. Depending on the experimental results, a model of fuel cell based on artificial neural networks is proposed. A back propagation learning rule with the log-sigmoid activation function is adopted to construct neural networks model. Experimental data resulting from 36 fuel cell tests are used as a learning data. The hydrogen mass flow rate, applied load and inlet hydrogen pressure are inputs to fuel cell model, while the current and voltage are outputs. Proposed model could successfully predict the fuel cell performance in good agreement with actual data. This work is extended to developed fuel cell feedback

In this study, an analytical model depending on experimental results for InPInGaAs
avalanche photodiode at low bias was presented and the characteristics of
gain for this photodiode were determined directly by the impulse response. The
model have considered the most important mechanisms contributing the
photocurrent, they are trapping, photogeneration in the undepleted region and
charge-carriers velocity due to the built-in electrical field. Also, the bandwidth
was determined as a function to the total gain of photodiode and it was mainly
determined by diffusion and trapping processes at low gain regarding to the multilayer
structure considered in this study

The auditory system can suffer from exposure to loud noise and human health can be affected. Traffic noise is a primary contributor to noise pollution. To measure the noise levels, 3 variables were examined at 25 locations. It was found that the main factors that determine the increase in noise level are traffic volume, vehicle speed, and road functional class. The data have been taken during three different periods per day so that they represent and cover the traffic noise of the city during heavy traffic flow conditions. Analysis of traffic noise prediction was conducted using a simple linear regression model to accurately predict the equivalent continuous sound level. The difference between the predicted and the measured noise shows that

Biped robots have gained much attention for decades. A variety of researches has been conducted to make them able to assist or even substitute for humans in performing special tasks. In addition, studying biped robots is important in order to understand the human locomotion and to develop and improve control strategies for prosthetic and orthotic limbs. Some challenges encountered in the design of biped robots are: (1) biped robots have unstable structures due to the passive joint located at the unilateral foot-ground contact. (2) They have different configuration when switching from walking phase to another. During the singlesupport phase, the robot is under-actuated, while turning into an over-actuated system during the double-support pha

This paper experimentally investigated the dynamic buckling behavior of AISI 303 stainless steel aluminized and as received intermediate columns.  Twenty seven specimens without aluminizing (type 1) and 75 specimens with hot-dip aluminizing at different aluminizing conditions of dipping temperature and dipping time (type 2), were tested under dynamic compression loading (compression and torsion), dynamic bending loading (bending and torsion), and under dynamic combined loading (compression, bending, and torsion) by using a rotating buckling test machine. The experimental results werecompared with tangent modulus theory, reduced modulus theory, and Perry Robertson interaction formula. Reduced modulus was formulated to circular cross-

Fatigue failure is almost considered as the predominant problem affecting automotive parts under dynamic loading condition. Thus, more understanding of crack behavior during fatigue can strongly help in finding the proper mechanism to avoid the final fracture and extent the service life of components. The main goal of this paper is to study the fracture behavior of low carbon steel which is used mostly in automotive industry. For this purpose, the fractography of samples subjected to high and low stress levels in fatigue test then was evaluated and analyzed. Hardness and tensile tests were carried out to determine the properties of used steel. Also, the samples were characterized by microstructure test and XRD analysis to examine the con

Feed Forward Back Propagation artificial neural network (ANN) model utilizing the MATLAB Neural Network Toolbox is designed for the prediction of surface roughness of Duplex Stainless Steel during orthogonal turning with uncoated carbide insert tool. Turning experiments were performed at various process conditions (feed rate, cutting speed, and cutting depth). Utilizing the Taguchi experimental design method, an optimum ANN architecture with the Levenberg-Marquardt training algorithm was obtained. Parametric research was performed with the optimized ANN architecture to report the impact of every turning parameter on the roughness of the surface. The results suggested that machining at a cutting speed of 355 rpm with a feed rate of 0.07 m