A Wear Condition Warning Method for Wind Turbine Gearbox Based on Oil Online Monitoring Using Learnable Multiscale Convolutional Neural Network

This article presents a wear condition warning method based on oil online monitoring for wind turbine gearboxes. The method comprises a high-performance machine vision sensor capable of detecting and tracking both magnetic and nonmagnetic colored wear metal particles larger than <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$4~\mu $ </tex-math></inline-formula>m in lubricating oil. Following the detection, image feature extraction is conducted utilizing the U-Net network in conjunction with the watershed algorithm, designing to acquire and categorize particulate matter into distinct size fractions: 4–<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$6~\mu $ </tex-math></inline-formula>m, 6–<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$14~\mu $ </tex-math></inline-formula>m, 14–<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$21~\mu $ </tex-math></inline-formula>m, 21–<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$38~\mu $ </tex-math></inline-formula>m, 38–<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$70~\mu $ </tex-math></inline-formula>m, and sizes exceeding <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$70~\mu $ </tex-math></inline-formula>m. Furthermore, the study proposed a novel approach termed learnable multiscale convolutional neural network (LMCNN), which integrates online real-time monitoring with offline laboratory analysis. This method effectively extracts oil characteristics under diverse operational conditions, demonstrating robust performance. The fault detection accuracy achieved with the testing dataset stands at 97.78%, surpassing conventional methods, such as K-nearest neighbors (KNNs), decision trees (DTs), random forests (RFs), and multilayer perceptrons (MLPs). Moreover, when combined with historical data from the preceding three years, the system’s high rate of successful warning accuracy substantiates its robustness and reliability in the context of predictive maintenance for wind turbine gearboxes.