In order to grasp the process operating performance in real time, an online assessment method for process operating performance based on Fisher discriminant analysis(FDA) is proposed. The modeling data corresponding to different operating performances is separated and identified by the algorithm of offline modeling data classification and identification. The approach extracts the characteristics contained in different operating performances by FDA and establishes the assessment models. In online assessment, the process operating performance can be evaluated by the similarities between the characteristics of sampling window and each performance grade. The proposed method is used to evaluate the process operating performance of a hydrometallurgical process, and the simulation results show its effectiveness.