An alternative approach for intelligent tuning of a control loop will be presented in this paper. The objective is to design an algorithm which will tune the controller employing a neuro-fuzzy based algorithm. Structure and design method based on this approach will be explored, which include an adaptive network employed as building block, the back-propagation gradient method and least square estimator as a hybrid learning rule, and its integration with tuning algorithm. The effectiveness and the performance of the proposed intelligent tuning method will be demonstrated by on-line controller tuning of a process mini-plant.