Neural Network and Bias Correction Controls for Fast Transient Response of DC-DC Converter

We present a neural network based control method of DC-DC converter to realize fast transient response in coordination with the PID control. The neural network control effectively improves the transient response by modifying the reference value in the PID control dynamically using its predictions in the transient state. In addition, neural network timing control and bias correction are also adopted to obtain faster convergence. In the presented method, data acquisition and repetitive training of neural networks are proceeded off-line and the on-line prediction by repetitive trained neural networks is implemented in a commercially available computation unit. Experimental results confirm that our presented method obtains the significantly faster transient response compared to the conventional PID control.