Multidimensional clustering based fault diagnosis method for wind turbine transmission chain

Abstract

Abstract With the rapid development of wind power generation, ensuring the reliability and fault diagnosis of wind turbine transmission chains has become a focal point. Traditional clustering methods that address the fault diagnosis problem in wind turbine transmission chains suffer from low fault discrimination and accuracy, as they rely on a single indicator. This paper proposes a two-dimensional clustering model that utilizes multiple indicators to address the issue of distinguishing similar faults within the wind turbine transmission chain from various perspectives and dimensions. The proposed approach involves collecting vibration signals from the transmission chain of wind turbines using sensors and using the root mean square and kurtosis of the fault signal as clustering features. A multidimensional polar coordinate clustering model is established, with the signal kurtosis representing the polar angle and the root mean square representing the polar radius. The clustering of fault signals within wind turbine transmission chains is achieved by optimizing the clustering boundaries by establishing a clustering boundary optimization equation. The results of the developed clustering model are evaluated using external and internal evaluation methods. Experimental results demonstrate that this method exhibits high accuracy and low computational complexity in diagnosing faults within wind turbine transmission chains. In comparison with other clustering methods, the proposed method outperforms them according to the experimental results. Hence, this study presents a novel approach for health monitoring and fault diagnosis of the transmission chain of wind turbines, which has significant implications for improving the reliability of wind turbine operation and reducing maintenance costs.