This study describes a pressure tracking control of hydroforming process which is used for precision forming of sheet metal. The hydroforming operation is performed between the high-pressure chamber controlled by pressure control valve and the punch moving at a constant speed. Since the pressure in the forming chamber is a critical factor to the quality of the product, it is important to control the forming pressure to follow a prescribed pressure trajectory. However, because of the punch motion and the nonlinearities of the hydraulic components, the pressure tracking control using conventional control technique is very difficult to design and does not guarantee satisfactory performances. To account for these nonlinearities and uncertainties of the process, an iterative learning controller is proposed using Cerebellar Model Arithmatic Computer (CMAC).
The experimental result shows that the proposed learning control is superior to any fixed gain controller in the sense that it enables the system to do the same work more effectively as the number of operation increases. In addition, regardless of the uncertainties and nonlinearities of the forming process dynamics it can be effectively applied with little a prior knowledge about the process.