Erroneous vibration signals caused by sensor malfunction, shutdown transients, and abnormal acquisition conditions can degrade the reliability of automated industrial monitoring pipelines. This paper presents a deployment-oriented analysis of Multi-Dimensional Entropy (MDE) for vibration data quality control in wind turbines, focusing on computational efficiency, model-agnostic capability, physical interpretability, and robustness. Experiments on 57,643 labeled industrial vibration records from 12 wind farms and 14 turbine units, covering main bearings, gearboxes, and generators, together with cross-platform deployment validation and cross-turbine generalization tests on 4,152 unseen records from 3 additional wind farms, show that MDE provides a stable and discriminative feature representation across different classifiers and heterogeneous operating conditions while maintaining low computational and memory requirements. These results demonstrate that MDE can serve as a lightweight and deployment-ready feature layer for vibration data quality control, thereby improving the reliability of industrial monitoring pipelines and reducing the risk of error propagation into downstream diagnostic and prognostic tasks in wind energy applications.
Deshui Li, Xiao-Ming Yuan, Zishun Wang et al.· 0 citations
Ensuring measurement data quality is essential for reliable condition monitoring of industrial wind turbine drivetrains, where vibration measurements can be affected by sensor malfunctions, turbine shutdown conditions, and other non-diagnostic states. Such invalid measurements may compromise the reliability of subsequent monitoring and data-driven analysis procedures. This study proposes a Multi-Dimensional Entropy (MDE) metric as a front-end data quality assessment and control mechanism for vibration measurement validity evaluation. By characterizing signal distributions from multiple perspectives, including time-domain amplitude, spectral amplitude, and frequency-band energy, MDE captures statistical differences between valid and erroneous vibration measurements. By integrating MDE and RMS as feature representations, lightweight machine learning models are employed as evaluation tools to assess the effectiveness of the proposed representation. Experiments on a large-scale, heterogeneous real-world dataset comprising 57,643 vibration samples collected from 12 wind farms and 14 turbine units, covering multiple drivetrain components, diverse sensor brands, and varying sampling configurations over long-term operation, demonstrate that the proposed method achieves over 99 percent accuracy in identifying erroneous vibration measurements. The proposed approach can be deployed as a front-end data quality gate before downstream signal processing, feature extraction, and condition monitoring procedures, ensuring that subsequent analyses are performed using reliable vibration measurements. The results demonstrate the robustness of MDE under heterogeneous sensor configurations and highlight its potential for industrial-scale vibration measurement quality assessment.