Human-machine interface based on force touch panel has attract enormous attention, for the merits of high human-machine interaction efficiency. Many studies and re- searches are devoted to diverse force touch technologies. Broad applications in both actual use and research have been developed, such as 3D Touch and force-based keystroke authentication. The fruitful results are based on the assumption that users’ touch habits remain unchanged along the time, thus a stationary customized force sensing model can be build. However, in long- term use, users’ touch habits changed due to time-drifting and specific-event, causing stationary force sensing model’s performance decreased. To address this issue, a rectified artificial neural network for long-term force sensing in piezoelectric touch panels is presented in this paper. With additional information of touching time and sign of specific-event, the predictions of force level are rectified, achieving an accuracy of 94.79% on long-term data set. The proposed technique enables customized force sensing in long-term use and enhancing human-machine interactive efficiency.