Anomaly detection for heavy power generation gas turbine considering the effect of output power variation

Abstract

In the frequency modulation process of the heavy power generation gas turbine, the variation of output power will cause the fluctuation of the operating parameters. In order to detect the anomaly of the true performance deterioration accurately, a novel statistical anomaly detection model was developed. First, the mathematical description of the operating parameters under three different operating conditions—unsteady-state, steady-state and normal, steady-state and anomaly—was presented according to the characteristics of parameters and output power. Second, the new characteristic test statistic P-ratio based on the T-statistic was proposed for the anomaly detection under the steady-state condition. Then, the on-line steady-state detection algorithm based on the Gaussian mixture model was built for the unsteady-state identification. Finally, the efficacy of the model was examined on the synthetic deterioration data, which superimposes the anomaly simulation signal data on the real healthy data from a real power generation gas turbine. The testing result is shown to be satisfactory with respect to the false positive rate and the true positive rate. Future research is required to further improve the accuracy of the proposed model.