Submitting an automation method for detection cavitations in hydro turbines considering sensitivity parameters (Sefidroud hydroelectric power plant dam)

In this research, submitting a method for evaluation of detection cavitation specifications and also automation of cavitation threshold has been investigated. The case study was based on Kaplan hydro turbine data located on Tarik hydropower plant at Sefidroud dam. The foundation of method was employment MATLAB program, sensor classification sensor locations and cavitation sensitivity. For training in MATLAB program, 12 individual data sets and 4095 unique combinations were created and 408 data selected for examinations. The training data combined with sensor types and cavitation sensitivity features were employed to predict the cavitation threshold and the best training data set with more than 90 % 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 methods. The proposed research is useful for automation cavitation detection to hydro power turbine operators to predict the remaining useful life in futures.