FreqICE: Efficient Blade Icing Detection on Wind Turbines via Frequency Learning

Icing on wind turbine blades in high-altitude, mountainous, and maritime regions poses significant challenges, leading to power degradation and revenue loss. Existing blade icing detection methods mainly rely on deep learning techniques, such as Graph Neural Networks (GNNs) and Transformers, to analyze Supervisory Control and Data Acquisition (SCADA) data from wind turbine sensors. However, these approaches are computationally intensive, suffer from high latency, and require significant computational resources. Moreover, they often transmit SCADA data to centralized data centers for processing, which introduces delays and compromises data quality due to network instability. Additionally, these methods struggle to capture persistent and transient patterns in SCADA data, resulting in low detection accuracy. To overcome these challenges, we propose FreqICE, an efficient blade icing detection model via frequency-domain learning. FreqICE employs a lightweight frequency-domain multilayer perceptron (Freq MLP) combined with a multiview pretrained codebook, ensuring efficient detection inference. The codebook learns persistent patterns from multiple views and can be retrieved via simple table lookups, while the Freq MLP captures transient temporal features effectively. A feature attention block is used to emphasize the most important feature patterns. Together, these modules effectively capture both persistent and transient patterns, enabling effective and efficient blade icing detection on wind turbines. Experimental results demonstrate that FreqICE achieves state-of-the-art (SOTA) detection accuracy across all baseline models. Compared with the existing SOTA method, FreqICE significantly reduces model complexity while maintaining high accuracy. Specifically, it decreases the total number of parameters from 301 510 to 50 694, achieving a $5.9\times $ reduction. It also lowers the multiply-accumulate (MACC) counts from 8.01 to 0.04 million, leading to a $200.3\times $ acceleration. Additionally, peak memory usage is reduced from 13.46 to 0.30 MB, marking a $44.9\times $ decrease. This substantial reduction in memory footprint facilitates deployment on resource-constrained devices without compromising performance.