Installations and the detection of their faults has become a major challenge. In order to develop a reliable approach for monitoring and diagnosis faults of these components, a test rig was mounted. In this article, a Multi Layer Perceptron (MLP) Artificial Neural Network (ANN) has been structured and optimized for online monitoring of induction motors. The input layer of our ANN used eight indicators calculated from the collected time signals and which represent the different states of the motor (Healthy, broken rotor bars, bearing fault and Misalignment) and the output layer used a codified matrix. However, based on L27 Taguchi design, the architecture for the hidden layers of our network is chosen, with the use of the Levenberg-Marquardt learning algorithm. Garson's algorithm and connection weight approach showed that there's a great sensitivity of the crest factor, the kurtosis and the variance on the effectiveness of our diagnostic system. Consequently, the obtained results are capable of detecting faults in the induction motor under different operating conditions.

This paper deals with the improvement of the energy quality using shunt active power filter. The three-phase grid-connected photovoltaic generator consists in solar panels, a three-phase voltage inverter connected to the grid and a nonlinear load constituted by a diode rectifier bridge supplying a resistive load in series with an inductor. In so doing, three main challenges arise from the application context. First, the harmonic currents and the reactive power must be compensated. The second challenge is the injection of active solar energy into the grid. Third, Maximum Power Point Tracking (MPPT) must be found. This paper proposes a method addressing those challenges. For the first and the second one, direct current and power controls is used. For the third challenge, an algorithm is proposed which take in account the electrical variables and the variation of the solar irradiation. Simulation results of the proposed method are shown. The method is illustrated with two different strategies: Hysteresis Control and Direct Power Control (DPC) for a variable load. Obtained results are presented and compared in this paper to confirm the robustness and the superiority of DPC strategy compared to Hysteresis Control strategy. In the same context, the simulation carried out in this article shows promising results with THD approximates 1.33 %.

No abstract

No abstract

No abstract