For process monitoring, principal component analysis (PCA) has been widely used. Since PCA is able to capture the correlation among variables, PC-based monitoring outperforms traditional statistical process control methods, such as the Shewhart chart. Nevertheless, PC-based monitoring cannot detect changes in the correlation while the indices monitored are within their control limits. In order to detect such changes in the correlation, a new monitoring method is proposed. In the proposed method, PCA is applied to data within a predefined time-window, and the change of direction of each principal component is calculated at each step. This method is thus termed Moving PCA (MPCA), as PCA is applied on -line by moving the time-window. The fault detection performance of the proposed monitoring method and the traditional PC-based method is compared using simulated data. It is found that the proposed monitoring method using MPCA functions better than the traditional PC-based method in many cases.