This paper presents an intelligent, model-based predictive control (IMPC) strategy for motion control a flexible-link robot manipulator. The proposed IMPC is based on a two-level hierarchical control architecture. This control structure is used to combine the advantages of crisp model-based predictive control and knowledge-based soft control techniques. The top-level is a fuzzy-rule based intelligent decision-making system. The low-level consists of two modules: Real time system identification module, and the model-based predictive control (MPC) module. The top-level intelligent fuzzy-rule based tuner interacts with the low-level modules. Based on the desired system performance, the state feedbacks, and the knowledge base, the top-level fuzzy tuner automatically adjusts the tuning parameters of the MPC controller. It is also able to adjust the model structure of system identification module, if necessary, for large model errors, and will increase the robustness of the controller. A multi-stage MPC algorithm is used by MPC module to ensure the nominal stability of the controller based on Lyapunov’s theorem. Physical implementation of the IMPC in a prototype flexible link manipulator system (FLMS) is explored. The performance of the proposed IMPC scheme is evaluated using computer simulations of the prototype FLMS. The results show that the IMPC can effectively control the motion of a flexible-link robot manipulator.