In this research, an intelligent multi-objective nonlinear model predictive control (NMPC) scheme is proposed for its application in the ‘on-line’ optimization of dynamical gas turbine model. The scheme proposed belongs to the sub-optimal NMPC strategies where near-optimal, instead of global optimal, control solutions are obtained at each control sampling time. The complexity of NMPC implementation for highly nonlinear and multi-objective control problems is very high due to its non-quadratic and non-convex multi-objective optimization nature. Therefore, this problem needs to be solved at each sampling time. For this purpose, the model predictive control strategy is utilized in this paper as an effective control design framework in order to realize the desired multi-objective optimization. Multi-objective particle swarm optimization (MOPSO) method is applied to optimize the nonlinear model predictive control (NMPC).