Estimation of generator lifetime of offshore wind turbines using digital twin and machine learning methods

نوع: Type: thesis

مقطع: Segment: masters

عنوان: Title: Estimation of generator lifetime of offshore wind turbines using digital twin and machine learning methods

ارائه دهنده: Provider: EDRIS NAZARI

اساتید راهنما: Supervisors: Dr. Abbas Ramezani

اساتید مشاور: Advisory Professors: Dr. Mohammad Mehdi Shahbazi

اساتید ممتحن یا داور: Examining professors or referees: Dr. Mohsen Hassan Babai Nozadian and Dr. Younes Solgi

زمان و تاریخ ارائه: Time and date of presentation: 2023

مکان ارائه: Place of presentation: Class 3

چکیده: Abstract: In recent years, the need to produce energy, especially renewable energy, has been one of the most important concerns of mankind. One of these cases is offshore wind turbines, which have helped humans a lot to produce energy. Access to these turbines is difficult and costly, so special attention should be paid to the lifespan of its parts. One of the most important electrical parts of the wind turbine is the generator. So, estimating the lifespan of generators can be a great help to people to reduce the cost of maintenance and repair. To estimate the lifespan of a generator, there must be enough information and data to be able to do this accurately. By using simulation and in MATLAB program, we obtain this information, which contains information both when an error occurs and in the dynamic state of the system. Using Simulink outputs in MATLAB program, we sampled the signals and prepared the data for the input of our neural network. In this research, we used machine learning and CNN and LSTM neural networks to estimate lifespan. In the system we simulated, we had four types of errors and we also considered thirteen types of errors and of course a number of states under the name of dynamic state of the system. By using these neural networks and several consecutive tests, we reached the best results and these networks gave us an accuracy of about 80%

فایل: ّFile: Download فایل