Increasing the operating range and energy production in Francis turbines by an early detection of the overload instability

Abstract With the increasing entrance of wind and solar power for the generation of electricity, more flexibility is demanded to hydropower plants. More flexibility means that hydro turbines have to increase the operating range between minimum and maximum power. In Francis turbines the maximum power is limited by the appearance of a strong hydraulic excitation called overload instability. When the turbine operates at loads higher than design, the cavitating vortex rope that is generated in the draft tube may become unstable, producing huge pressure fluctuations, vibrations and power swing. Turbines are not allowed to operate under these conditions in order to avoid the destruction of the unit. The overload instability emerges abruptly, even when the machine is operating in a smooth condition. No visible transition can be detected by the monitoring system, so turbine operators have no margin to react. To avoid this phenomenon, operators limit the maximum power much before reaching this condition. By doing that, the maximum power is limited as well as the regulation capacity of the unit. In this paper, the feasibility of detecting the onset of this phenomenon is analyzed. Data-driven methods and artificial intelligence techniques, including principal component analysis, self-organizing map and artificial neural networks, are applied to the data available from experimental tests in a Francis turbine. The signals of vibration, pressure fluctuations and other parameters are combined and studied. The possibilities of a premature detection of the instability before it occurs are discussed. The method could be implemented in the monitoring system of the unit so that the operating range could be safely increased.

[1]  Ming Zhao,et al.  A convolutional neural network based feature learning and fault diagnosis method for the condition monitoring of gearbox , 2017 .

[2]  A. Presas,et al.  On the use of artificial neural networks for condition monitoring of pump-turbines with extended operation , 2020 .

[3]  Eduard Egusquiza Estévez,et al.  Condition monitoring of pump-turbines , 2014 .

[4]  James Baglin,et al.  Improving Your Exploratory Factor Analysis for Ordinal Data: A Demonstration Using FACTOR. , 2014 .

[5]  Alexandre Presas,et al.  Feasibility of Using PZT Actuators to Study the Dynamic Behavior of a Rotating Disk due to Rotor-Stator Interaction , 2014, Sensors.

[6]  Erkki Oja,et al.  Engineering applications of the self-organizing map , 1996, Proc. IEEE.

[7]  Olli Simula,et al.  A Self-Organizing Map for Clustering Probabilistic Models , 1999 .

[8]  Andres Müller,et al.  Draft tube discharge fluctuation during self-sustained pressure surge: fluorescent particle image velocimetry in two-phase flow , 2013 .

[9]  Alexandre Presas,et al.  Extension of Operating Range in Pump-Turbines. Influence of Head and Load , 2017 .

[10]  Andres Müller,et al.  Experimental Hydro-Mechanical Characterization of Full Load Pressure Surge in Francis Turbines , 2017 .

[11]  Alexandre Presas,et al.  Power swing generated in Francis turbines by part load and overload instabilities , 2017 .

[12]  R. A. Saeed,et al.  3D fluid–structure modelling and vibration analysis for fault diagnosis of Francis turbine using multiple ANN and multiple ANFIS , 2013 .

[13]  Alexandre Presas,et al.  Sensor-Based Optimized Control of the Full Load Instability in Large Hydraulic Turbines , 2018, Sensors.

[14]  Luigi Garibaldi,et al.  PCA-based detection of damage in time-varying systems , 2010 .

[15]  Robert X. Gao,et al.  Deep learning and its applications to machine health monitoring , 2019, Mechanical Systems and Signal Processing.

[16]  Alexandre Presas,et al.  Behavior of Francis turbines at part load. Field assessment in prototype: Effects on the hydraulic system , 2019 .

[17]  Alexandre Presas,et al.  Fatigue life estimation of Francis turbines based on experimental strain measurements: Review of the actual data and future trends , 2019, Renewable and Sustainable Energy Reviews.

[18]  Ulrich Schmoch,et al.  How to use indicators to measure scientific performance: a balanced approach , 2010 .

[19]  F. Avellan,et al.  Study of the vortex-induced pressure excitation source in a Francis turbine draft tube by particle image velocimetry , 2015 .

[20]  Alexandre Presas,et al.  Overview of the experimental tests in prototype , 2017 .

[21]  Alexandre Presas,et al.  Detection and analysis of part load and full load instabilities in a real Francis turbine prototype , 2017 .

[22]  Meik Schlechtingen,et al.  Comparative analysis of neural network and regression based condition monitoring approaches for wind turbine fault detection , 2011 .

[23]  M. Schlechtingen,et al.  Using Data-Mining Approaches for Wind Turbine Power Curve Monitoring: A Comparative Study , 2013, IEEE Transactions on Sustainable Energy.

[24]  Alexandre Presas,et al.  Detection of Hydraulic Phenomena in Francis Turbines with Different Sensors , 2019, Sensors.

[25]  Miguel A. Sanz-Bobi,et al.  SIMAP: Intelligent System for Predictive Maintenance: Application to the health condition monitoring of a windturbine gearbox , 2006, Comput. Ind..

[26]  Alexandre Presas,et al.  Behavior of Francis turbines at part load. Field assessment in prototype: Effects on power swing , 2019, IOP Conference Series: Earth and Environmental Science.

[27]  Alexandre Presas,et al.  Condition monitoring of pump-turbines. New challenges , 2015 .

[28]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[29]  Alessandro Moschitti,et al.  UNITN: Training Deep Convolutional Neural Network for Twitter Sentiment Classification , 2015, *SEMEVAL.

[30]  A. Presas,et al.  Improved damage detection in Pelton turbines using optimized condition indicators and data-driven techniques , 2021, Structural Health Monitoring.

[31]  Jorma Laaksonen,et al.  Variants of self-organizing maps , 1990, International 1989 Joint Conference on Neural Networks.

[32]  Zhengwei Wang,et al.  Resonance investigation of pump-turbine during startup process , 2014 .

[33]  Andres Müller,et al.  LDV survey of cavitation and resonance effect on the precessing vortex rope dynamics in the draft tube of Francis turbines , 2016 .

[34]  David Valentín,et al.  Advanced condition monitoring of Pelton turbines , 2018 .

[35]  Peter K. Dörfler.  On the High-partial-load Pulsation in Francis Turbines , 2019 .

[36]  Enrico Zio,et al.  Artificial intelligence for fault diagnosis of rotating machinery: A review , 2018, Mechanical Systems and Signal Processing.

[37]  Vladlen Koltun,et al.  An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling , 2018, ArXiv.

[38]  Alexandre Presas,et al.  Condition monitoring of a prototype turbine. Description of the system and main results , 2017 .

[39]  Daming Lin,et al.  A review on machinery diagnostics and prognostics implementing condition-based maintenance , 2006 .

[40]  Lionel Tarassenko,et al.  Guide to Neural Computing Applications , 1998 .

[41]  Andres Müller,et al.  Fluid–structure interaction mechanisms leading to dangerous power swings in Francis turbines at full load , 2017 .

[42]  Xin Liu,et al.  A review on fatigue damage mechanism in hydro turbines , 2016 .

[43]  E. Lehmann.  Testing Statistical Hypotheses , 1960 .

[44]  Alexandre Presas,et al.  Dynamic response of the MICA runner. Experiment and simulation , 2017 .

[45]  Kristin L Sainani,et al.  Introduction to principal components analysis. , 2014, PM & R : the journal of injury, function, and rehabilitation.

[46]  Grant,et al.  HYdropower plants PERformance and flexiBle Operation towards Lean integration of new renewable Energies , 2020 .