Feature Selection for Monitoring Erosive Cavitation on a Hydroturbine

Abstract

This paper presents a method for comparing and evaluating cavitation detection features - the first step towards estimating remaining useful life (RUL) of hydroturbine runners that areimpacted by erosive cavitation. The method can be used to quickly compare features created from cavitation survey data collected on any type of hydroturbine, sensor type, sensor location, and cavitation sensitivity parameter (CSP). Although manual evaluation and knowledge of hydroturbine cavitation is still required for our feature selection method, the use of principal component analysis greatly reduces the number of plots that require evaluation. We present a case study based on a cavitation survey data collected on a Francis hydroturbine located at a hydroelectric plant and demonstrate the selection of the most advantageous sensor type, sensor location, and CSP to use on this hydroturbine for long-term monitoring of erosive cavitation. Our method provides hydroturbine operators and researchers with a clear and effective means to determine preferred sensors, sensor placements, and CSPs while also laying the groundwork for determining RUL in the future.

Extended Isolation Forests for Fault Detection in Small Hydroelectric Plants

“…Multivariate statistical methods such as Principal Component Analysis (PCA) [25], Independent Component Analysis (ICA) [26] and Least Square Support Vector Machine (LS-SVM) [27][28][29][30], have been widely applied for fault detection and diagnosis in hydro-generating systems. For instance, PCA decomposition is applied to aid experts in identifying and selecting the main features which contribute to cavitation in hydro-turbines [31]. Recent studies have proposed a new monitoring method, based on ICA-PCA that can extract both non-Gaussian and Gaussian information of process data for fault detection and diagnosis [32].…”

Condition-based maintenance in hydroelectric plants: A systematic literature review

“…Nevertheless, combining other variables such as temperature, electrical signature, pressure, and acoustic emission in multi-source systems is a trend in the research, given the capacity of these other variables not only to identify other failure modes that vibration does not capture, but also to help in classifying the type of failure. Studies associating the feature importance of monitored variables with the types of failure, like cavitation 18 and partial discharge, 98 can guide the design of new hydroelectric CBM systems. Hybrid models: The explainability of data-driven models, or machine explainability, offers the potential to provide insights into model behavior using various methods such as visualization, feature importance scores, counterfactual explanation, or influential data.…”

“…Nevertheless, combining other variables such as temperature, electrical signature, pressure, and acoustic emission in multi-source systems is a trend in the research, given the capacity of these other variables not only to identify other failure modes that vibration does not capture, but also to help in classifying the type of failure. Studies associating the feature importance of monitored variables with the types of failure, like cavitation 18 and partial discharge, 98 can guide the design of new hydroelectric CBM systems.…”

“…Sudden changes in the local pressure of the liquid form bubbles that collapse, radiating acoustic energy waves, and causing the erosion of nearby surfaces. 18 Sand erosion increases the likelihood of cavitation, since eroded surfaces increase wall turbulence and, consequently, reduce the local pressure. 19 Cavitation is more likely in Francis turbines and reversible pump turbines than in Kaplan turbines.…”

“…The aim is to decrease the training instability and increase the generalizability and convergence speed of the model. Other data-driven methods found in the literature are the support vector machine 60,81 (SVM) and the principal component analysis 18 (PCA).…”