This paper presents an artificial intelligence – Deep Belief Network (DBN) gain-scheduling adaptive PI controller scheme for dual active bridge (DAB) converter. The PI gains are allowed to vary within a predetermined range and therefore eliminate the problems faced by the conventional PI controller. The performance of the proposed controller is simulated and compared with the conventional fixed PI controller under various conditions. The experimental prototype of the DAB converter is implemented using a digital signal processor of TMS320F28335 manufactured by Texas Instrument to examine and to evaluate the performance criteria of the proposed controller. Simulation and experimental results show improvements in transient as well as steady state responses of the proposed controller over the conventional fixed PI controller.