Open AccessNeural Network Controlled Primitive Fault Analysis and Monitoring of Wind Turbine Gear Box
Author(s) -
B. Raja Mohamed Rabi,
K. Kanimozhi
Publication year - 2019
Publication title -
international journal of recent technology and engineering
Language(s) - English
Resource type - Journals
ISSN - 2277-3878
DOI - 10.35940/ijrte.b2404.078219
Subject(s) - downtime , turbine , wind power , condition monitoring , fault (geology) , artificial neural network , reliability engineering , identification (biology) , fault detection and isolation , minification , train , automotive engineering , computer science , engineering , control engineering , artificial intelligence , electrical engineering , mechanical engineering , botany , actuator , seismology , biology , programming language , geology , cartography , geography
The problem considered in this paper is minimization of operational and maintenance costs of Wind Energy Conversion Systems (WECS). A continuous condition monitoring system is to be designed for reducing these costs. Hence preliminary identification of the degeneration of the generator health, facilitating a proactive response, minimizing downtime, and maximizing productivity is made possible. The inaccessibility of Wind generators situated at heights of 30m or more height also creates problem in condition monitoring and fault diagnosis. This opens up the research on condition monitoring and fault diagnosis in WECS (blades, drive trains, and generators). Therefore different type of faults, their generated signatures, and their diagnostic schemes are discussed in this paper. The paper aims in validating the application of neural networks for the analysis of wind turbine data, so that possible future failures may be predicted and rectified earlier.