In resistance spot welding, regardless of the optimal condition, bad weld quality was still produced due to complicated manufacturing processes such as electrode wear, misalignment between the electrode and workpiece, poor part fit-up, and etc.. Therefore, the goal of this study was to measure the process signal which contains weld quality information, and to develop the process fault monitoring system. Welding force signal obtained through variety experimental conditions was analyzed and divided into three categories: good, shunt, and poor fit-up group. And then a monitoring algorithm made up of an artificial neural network that could estimate the process fault of each different category based on pattern was developed.