Algorithmic performance constraints for wind turbine condition monitoring via convolutional sparse coding with dictionary learning. (August 2021)

• Record Type: Journal Article
• Authors: Martin-del-Campo, Sergio; Sandin, Fredrik; Schnabel, Stephan
• Is Part Of: Proceedings of the Institution of Mechanical Engineers. Volume 235:Number 4(2021)
• Page Start: 660
• Page End: 675
• Publication Date: 2021-08
• Subjects: Unsupervised feature learning -- dictionary learning -- sparse coding -- conditon monitoring -- wind turbine; Reliability (Engineering) -- Mathematical models -- Periodiclals; Risk assessment -- Mathematical models -- Periodicals; Engineering design -- Mathematical models -- Periodicals; 620.00452
• DOI: 10.1177/1748006X20984260
• Languages: English
• ISSNs: 1748-006X

Abstract

We analyze vibration signals from wind turbines with dictionary learning and investigate the relation between dictionary distances and faults occurring in a wind turbine output shaft rolling element bearing and gearbox under different data and compute constraints. Dictionary learning is an unsupervised machine learning method for signal processing, which permits learning a set of signal-specific features that have been used to monitor the condition of rotating machines, including wind turbines. Dictionary distance is one such feature, and its effectiveness depends on an adequate selection of the dictionary learning hyperparameters and the data availability, which typically is constrained in condition monitoring systems for remotely located wind farms. Here we evaluate the characteristics of the dictionary distance feature under healthy and faulty conditions of the wind turbines using different options for the selection of the pretrained dictionary, the sparsity of the signal model which determines the compute requirements, and the interval between data samples. Furthermore, we compare the dictionary distance feature to the typical time-domain features used in condition monitoring. We find that the dictionary distance based feature of a faulty wind turbine deviates by a factor of two or more from the population distribution several weeks before the gearbox bearing fault was reported, using a data sampling interval as long as 24 h and a model sparsity as low as 2.5%.