State Estimation for Monitoring Using MLP Neural Networks Based on Adaptative Learning Algorithm Observer Applied to Modular Capacitor Four Level DC–DC Chopper

Adaptative algorithm learning for artificial neural network approach is anticipated for estimation of unknown disturbances and faults by using the multi-layer perceptron, the weight parameters are updated by using the adaptative observer learning strategy applied to modular capacitor dc–dc chopper. A monitoring system and fault indentification in modular capacitor dc–dc converter is proposed. The method for detecting and locating this type of fault is carried out using advanced intelligent techniques based on a Perceptron Multilayer Artificial Neural Network (MLP-ANN); its database uses statistical indicators characterizing current and flying capacitors voltage. The effectiveness of the proposed method is illustrated using experimentally obtained control signals on converter parameters, and the results have shown good accuracy in detecting and locating faults.