Data-driven fault diagnosis for wind turbines using modified multiscale fluctuation dispersion entropy and cosine pairwise-constrained supervised manifold mapping

作者：

Highlights：

• RTSMFDE is proposed for measuring the complexity of time series.

• CPCSMM is proposed for extracting low-dimensional and sensitive features.

• A novel data-driven fault diagnosis method for wind turbines is proposed.

• Experiment results show the effectiveness of the proposed methods.

摘要

•RTSMFDE is proposed for measuring the complexity of time series.•CPCSMM is proposed for extracting low-dimensional and sensitive features.•A novel data-driven fault diagnosis method for wind turbines is proposed.•Experiment results show the effectiveness of the proposed methods.

论文关键词：Wind turbine,Fault diagnosis,Supervised manifold mapping,Multiscale dispersion entropy,Support vector machine

论文评审过程：Received 15 April 2021, Revised 10 June 2021, Accepted 30 June 2021, Available online 2 July 2021, Version of Record 8 July 2021.

论文官网地址：https://doi.org/10.1016/j.knosys.2021.107276