Forecasting Models for Hydropower Unit Stability Using LS-SVM

Abstract

This paper discusses a least square support vector machine (LS-SVM) approach for forecasting stability parameters of Francis turbine unit. To achieve training and testing data for the models, four field tests were presented, especially for the vibration inY-direction of lower generator bearing (LGB) and pressure in draft tube (DT). A heuristic method such as a neural network using Backpropagation (NNBP) is introduced as a comparison model to examine the feasibility of forecasting performance. In the experimental results, LS-SVM showed superior forecasting accuracies and performances to the NNBP, which is of significant importance to better monitor the unit safety and potential faults diagnosis.

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].…”

The Prediction Method on the Early Failure of Hydropower Units Based on Gaussian Process Regression Driven by Monitoring Data

“…Based on the comprehensive consideration of the bearing vibration, active power, and working head information of the units, a condition parameter degradation assessment, and prediction model was proposed to evaluate and forecast hydropower units [13,20,21]. Based on the least square support vector machine model, the Y-direction vibration data of the bearing and the monitoring data of the draft tube were predicted to realize the diagnosis of potential faults [22].…”

Alternative method for modelling structural and functional behaviour of a Storage Hydroelectric Power Plant using MLD approach

“…Acord to Lui et al [2] the transient process in hydropower stations, including the interactions among hydraulics, mechanism, and electricity, is complicated. The closure of guide vanes and spherical valve induces a change in the flow inertia, which causes changes in the turbine rotational speed and hydraulic pressure in the piping system.When the working condition dramatically changes during transients, drastic changes in the waterhammer pressure and high rotational speed may lead to serious accidents that will endanger the safety of the hydraulic structure and turbine unit [1][2][3] and affect the power grid stability [4]. Therefore, simulating the transient process of hydropower stations is necessary.…”

“…A unit is often operated through rough zone which will cause the unit vibration and the stability performance will decline. [3] Finally, in the case of Great Brittian 1/3 of the cfomplete electrical power is generated by a Hydropower plant installed in Dinorwig Wales with a special characteristics to be demostrated in this report [4] Futhermore, section 2 is devoted to describe the Dinorwig Hydropower Plant(DHP) as structural as functional manner. The hybrid model proposed to define the unsual behaviour for the Plant is developed in section 3.…”

“…3 + 0.8204s 2 + 2.788s + 3.031 (Because of the TF is represent in continuous time domain , a bilinear programming script was developed in M AT LAB© to be converted at Z discrete time domain applying the Invariant Impulse Method (Eq. 6) and through the Tustin method or Bilinear Transformation (Eq.…”