1 Hybrid Fault Prognosis for Excitation Capacitors of Self-Excited Induction Generator for Wind Energy Applications Massinissa Derbal 1 , Houari Toubakh 2 , Moamar Sayed-Mouchaweh 3 , and Abdelhamid Bouchachia 4 1 Laboratoire de Recherche en Electrotechnique, École nationale polytechnique, Algiers, 16200, Algeria massinissa.derbal@g.enp.edu.dz 2 Electrical Engineering Lab, Kasdi Merbah University, Ouargla, 30000, Algeria houari.toubakh@univ-ouargla.dz 3 Computer Science and Automatic Control Lab, École Mines-Telécom IMT, Lille, 59000, France. moamar.sayed-mouchaweh@imt-lille-douai.fr 4 School of Design, Engineering and Computing, Bournemouth University, Dorset, BH12 5BB, United Kingdom. abouchachia@bournemouth.ac.uk ABSTRACT This paper presents a new fault prognosis approach applied to wind turbine system based on self-excited induction generator (SEIG) for offshore and isolated areas. This generator is very sensitive to wind speed variation and excitation source. The SEIG is excited by a capacitor bank with an appropriate value to ensure the good operating of the production system. Capacitor bank faults are usually related to chemical aging, electrical and thermal stress conditions. These abnormalities can affect one or more properties of the system, which can lead to failures or even complete breakdown of the production system. Specifically, in this paper, we propose a saturated flux model for the SEIG and develop a hybrid monitoring method that detects faults occurrence gradually and estimates the remaining useful life (RUL). Such monitoring method applies data mining techniques in order to identify and track the faults using only useful data that captures the dynamics of the degradation. Moreover, to deploy efficient maintenance schedules, RUL is estimated by exploiting wind speed (variable and max speed) information. The proposed hybrid fault prognosis method is tested under variable excitation capacitors degradation scenarios. The obtained results confirm the robustness and accuracy of the proposed method. 1. INTRODUCTION Nowadays, the use of wind energy as a renewable energy source, has grown rapidly and has become more important as the consciousness of global warming due to consumption of fossil energy and environmental pollution has increased (Derbal & Toubakh, 2018). Most wind farms in the world are offshore, where wind conditions are generally better, and the issues of noise and the impact on the landscape are somewhat improved. However, the reliability of an offshore wind generator and the resources required to maintain it can make up to 30% of the overall cost of energy produced. Typically, offshore wind generators failures require greater repair resources (i.e. material cost and labor) which leads to higher cost of energy. Consequently, wind farm developers try to select wind turbines with low failure rates and those that require the least amount of maintenance resources. Because of accessibility issues, reliability of turbines becomes even more important as offshore wind energy generation increases (Carroll, McDonald and McMillan, 2016). Self-excited induction generator is the best electromechanical converter to replace the synchronous generator in stand-alone power generators driven by sustainable energy resources such as micro-hydroelectric, biogas, wind, thermal, etc. SEIG is quite robust, relatively inexpensive and interestingly needs minimum maintenance. Using this generator in isolated and offshore wind energy system justifies the importance of supervising their normal operations (Derbal & Toubakh, 2018). Unexpected faults of wind generator based on SEIG may occur in electronic control units, electric systems, hydraulic systems, the generator, the gearbox, the rotor cage malfunctions and the stator phase imbalance. Faults can occur also in excitation capacitor, which can lead to performance degradation, unscheduled turbine shutdown, and even Massinissa Derbal et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.