Condition monitoring is very important for system safety and condition-based maintenance. Time series prediction capabilities of machine learning like support vector regression (SVR) can be utilized for prognostics. But, choosing optimal parameters for SVR is an important step in SVR model design, which heavily affects the performance of SVR. So, a whale optimization algorithm (WOA) based algorithm is proposed for SVR parameters selection. The proposed algorithm has been evaluated through some benchmark datasets. Furthermore, the proposed method with moving window technology is used to condition prognostics of the Tennessee Eastman process. Experiments and engineering application show that the SVR-WOA method is effective, by noting that the computation time is shortened in some application scenarios.