Harmonic minimization of a solar fed cascaded H Bridge inverter using Artificial Neural Network

The major concern in the design of inverters is dealing with harmonics. Harmonics in inverter are generated due to improper selection of switching angles to the gates of the inverter switches. The presence of harmonics in inverter output will affect the loads connected to it. This paper deals with the selective harmonic elimination problem in multilevel inverter using Artificial Neural Networks (ANN) to generate the switching angles for an eleven-level full-bridge cascaded H bridge multilevel inverter powered by five varying DC input sources (solar panels). The Harmonic equations are solved and angles are obtained such that the fundamental was kept constant and the low-order harmonics were minimized or eliminated. The different data sets of angle values for various input DC voltage conditions are obtained. The data sets thus collected are used to train the multi-layered feed forward neural network. The trained network is then tested for its performance. The network model is integrated with cascaded H bridge multilevel inverter to generate the switching angles in real-time.