Study on PID neural-network-based inverter space-vector pulse width modulation strategy

A PID neural-network-based space-vector pulse width modulation (SVPWM) for a three-level inverter is proposed in this paper. A three-level inverter has lots of switching states about the vectors, and the implementation of modulation algorithm is considerably complex. In the proposed design, fast implementation of SVPWM algorithm is realized based on PID neural network instead of conventional neural network. A three-layer feedforward PID neural network takes command voltage and angle as input information and generates 12 symmetrical PWM waves for the three phases by means of a single timer and logic circuits. The measured data are used to test the proposed system by a backpropagation algorithm in the MATLAB Neural Network Toolbox. The result shows that performance is perfect in the whole linear modulation region.