In the previous paper, diverse data acquisition methods based on data types for condition monitoring wind turbines is explored. The present study investigates advanced signal processing techniques in the field of condition monitoring of wind turbines. Methods include synchronous sampling, signal decomposition, envelope analysis, statistical evaluation, model-based approaches, Bayesian methods, and artificial intelligence techniques. Comparison and analysis of these methods and their applications in wind turbine fault detection and diagnosis are presented in this coming study. Moreover, the survey encompasses innovative approaches using various data sources, addressing challenges in components like bearings, gearboxes, blades, and generators. Insights into the evolution of data-driven decision-making in the wind energy sector are provided, with a focus on strengths, limitations, and future directions. A summarized table offers an overview of studies, highlighting monitored components, data types, and methods.
Heibati, R., Alipour-Sarabi, R., & Bathaee, S. M. T. (2023). A survey on the most practical signal processing methods in conditional monitoring in wind turbines. Scientia Iranica, (), -. doi: 10.24200/sci.2023.62911.8101
MLA
Reza Heibati; Ramin Alipour-Sarabi; Seyed Mohammad Taghi Bathaee. "A survey on the most practical signal processing methods in conditional monitoring in wind turbines". Scientia Iranica, , , 2023, -. doi: 10.24200/sci.2023.62911.8101
HARVARD
Heibati, R., Alipour-Sarabi, R., Bathaee, S. M. T. (2023). 'A survey on the most practical signal processing methods in conditional monitoring in wind turbines', Scientia Iranica, (), pp. -. doi: 10.24200/sci.2023.62911.8101
VANCOUVER
Heibati, R., Alipour-Sarabi, R., Bathaee, S. M. T. A survey on the most practical signal processing methods in conditional monitoring in wind turbines. Scientia Iranica, 2023; (): -. doi: 10.24200/sci.2023.62911.8101
)