Examination of the sensitivity parameters to detect automatic cavitation in Hydro-turbines of the SefidRood dam considering remaining useful life

In this research، the evaluation of cavitation threshold detection and the automation of the detection process with regard to the Remaining Useful Life (RUL) of the Sefidrood power plant turbine، has been studied. The input of generated model by MATLAB program includes data driven from kaplan hydro turbine located on Tarik hydro power plant. The proposed model is based on 61 features resulting from 6 cavitation sensitivity parameters and 17 operational conditions. For training in MATLAB program, 12 individual data sets and 4095 unique combinations were created and 408 data were selected for examination. The training data combined with sensor rating and cavitation sensitivity feature were employed to predict the cavitation and the best training data set with 98% accuracy. The results showed that the use of a fully automated process for sensitivity determination and cavitation classification was more suitable than the use of a process based on manually selected thresholds. Furthermore, considering the operational conditions and RUL, the automation of determination of cavitation threshold without human intervention was much more accurate.