No abstract

Africans in general and specially Beninese’s low rate access to electricity requires efforts to set up new electricity production units. To satistfy the needs, it is therefore very important to have a prior knowledge of the electrical load. In this context, knowing the right need for the electrical energy to be extracted from the Beninese network in the long term and in order to better plan its stability and reliability, a forecast of this electrical load is then necessary. The study has used the annual power grid peak demand data from 2001 to 2020 to develop, train and validate the models. The electrical load peaks until 2030 are estimated as the output value. This article evaluates three algorithms of a method used in artificial neural networks (ANN) to predict electricity consumption, which is the Multilayer Perceptron (MLP) with backpropagation. To ensure stable and accurate predictions, an evaluation approach using mean square error (MSE) and correlation coefficient (R) has been used. The results have proved that the data predicted by the Bayesian regulation variant of the Multilayer Perceptron (MLP), is very close to the real data during the training and the learning of these algorithms. The validated model has developed high generalization capabilities with insignificant prediction deviations.

No abstract

The performance of an electric machine depends on its ability to resist rising internal temperature and ambient temperature. In particular when it is a combination with a heat engine, it is essential to know the thermal characteristics of the electric machine in connection with its operating environment to decide which type of machine for a better result. This work will make a comparative thermal study of three types of generators namely: the permanent magnet generator (PMSG), the squirrel cage asynchronous generator (SCIG) and the switched reluctance generator (SRG), all driven by Stirling engine. The method involves solving the heat propagation equation to determine the thermal resistance network for each machine. The resolution of the network combined with the finite element method will allow a comparison of the temperature rise and its effect on the performance of each machine. The simulation results show that the temperature of the PMSG windings stabilizes at 430 K while that of the others stabilizes at 373 K and 346 K respectively. However, when comparing the performances for the specifications of this work (i.e., produce minimum electric power of 2kW at low speed generated by the Stirling engine), PMSG is the one that fulfil all the requirements. For the use of this machine for the generator set, it will be necessary to use magnets of types GNS-39EH whose operating temperature is approximately 473K (200 ° C) with magnetic induction of 1.22 T. Keywords: choice of machines, thermal network, Finite Element Method, machine’s performances, Stirling engine.

The performance of an electric machine depends on its ability to resist rising internal temperature and ambient temperature. In particular when it is a combination with a heat engine, it is essential to know the thermal characteristics of the electric machine in connection with its operating environment to decide which type of machine for a better result. This work will make a comparative thermal study of three types of generators namely: the permanent magnet generator (PMSG), the squirrel cage asynchronous generator (SCIG) and the switched reluctance generator (SRG), all driven by Stirling engine. The method involves solving the heat propagation equation to determine the thermal resistance network for each machine. The resolution of the network combined with the finite element method will allow a comparison of the temperature rise and its effect on the performance of each machine. The simulation results show that the temperature of the PMSG windings stabilizes at 430 K while that of the others stabilizes at 373 K and 346 K respectively. However, when comparing the performances for the specifications of this work (i.e., produce minimum electric power of 2kW at low speed generated by the Stirling engine), PMSG is the one that fulfil all the requirements. For the use of this machine for the generator set, it will be necessary to use magnets of types GNS-39EH whose operating temperature is approximately 473K (200 ° C) with magnetic induction of 1.22 T. Keywords: choice of machines, thermal network, Finite Element Method, machine’s performances, Stirling engine.