Abstract: An algorithm of generalized predictive control with iterative learning (ILGPC) was proposed for a repeatable batch process. Adding an iterative learning feed-forward loop in GPC loop by utilizing the previous process I/O information, the algorithm improves the control performance of repeatable operation process and reduces the tracking error through predictive estimation and learning part of repeatable disturbance. The stability of the algorithm is also analyzed, and the stability and robustness of the proposed algorithm are verified by a simulation of an intermittent polymerization reaction process.