A hybrid method of GA and BP for short-term economic dispatch of hydrothermal power systems
Mathematics and Computers in Simulation - Special issue from the IMACS/IFAC international symposium on soft computing methods and applications: “SOFTCOM '99” (held in Athens, Greece)
Adaptive Neural Network Control of Robotic Manipulators
Adaptive Neural Network Control of Robotic Manipulators
Approximation-based control of nonlinear MIMO time-delay systems
Automatica (Journal of IFAC)
Adaptive NN control for a class of strict-feedback discrete-time nonlinear systems
Automatica (Journal of IFAC)
| Hi-index | 0.00 |
Artificial Intelligence (AI) techniques, particularly the NeuralNetworks (NNs), are recently having significant impact on powerelectronics. In a Proton Exchange Membrane (PEM) fuel cell system,there is a strong relationship between the available electricalpower and the actual operating conditions: gas conditioning,membrane hydration state, temperature, current set point, etc.Thus, a 'minimal behavioural model' of a fuel cell system able toevaluate the output variables and their variations is highlyinteresting. In this paper, we are interested in controlling thepowers by using Neural Networks Controllers under the assumptionthat any system of production is subjected permanently to loadsteps change variations. So a static production system including aProton Exchange Membrane Fuel Cell (PEMFC) is subjected tovariations of active and reactive power. Then, the goal is to makethe system follows these imposed variations. In this work, a PEMfuel cell NN model is proposed using a quasi-Newton method andimplemented on Matlab/Simulink® software,Levenberg-Marquardt training algorithm, activation functions andtheir causes on the effectiveness of the performance modelling arediscussed, the quasi-Newton NN control is described and resultsfrom the analysis as well as the limitations of the approach arepresented.