Search

The advancement of low-cost, non-manually labeled big data technologies for fault detection in wind turbines is crucial to guarantee their safe and efficient operation. In this context, Normal Behavior Modelling (NBM) is a prevalent approach. However, existing NBM methods for wind turbine fault detection inadequately utilize complex spatial–temporal correlations within the Supervisory Control and Data Acquisition (SCADA) during the normal behavior prediction stage. To cope with this limitation, this paper propose a hierarchical spatial-temporal autocorrelation graph neural network method for online wind turbine pitch system fault detection. This approach integrates a dynamic graph network with an adaptive structure for spatial correlation learning and a transformer model with autocorrelation attention to identify periodic time-distance correlations. Furthermore, a hierarchical neural network, specifically designed for wind turbine physical structure, enhances local information extraction through seven latent graph neural networks and a probsparse attention mechanism. The proposed method demonstrates significant effectiveness in real-world applications, as evidenced by data from a Shanghai wind farm. [ABSTRACT FROM AUTHOR]

Solid wastes have been widely applied in porous asphalt pavement, but some of them may contain pollutants. Whether their leachate during rainfall events poses a threat to nearby watersheds has not received enough attention. Based on the laboratory rainfall and infiltrate test, this study evaluated the leachate risks of fine solid wastes in porous asphalt mixture (PA). Based on the runoff pollution characteristics in Shanghai, China, the purification performance of PA with diatomite filler was explored. The results showed that a small amount of Al and Fe in solid waste fillers might infiltrate during intensive rainfall. The diatomite filler could improve pollutants removal rates via physical filtration and selective chemical adsorption effects. The correlations between rainfall characteristics and the removal rates were further developed, which indicated the increase of rainfall time and intensity adversely affected the removal rates. The composition of PA for different runoff pollution characteristics was proposed as well. • Leachate environmental impacts of fine solid wastes in PA were evaluated. • Pollutant removal effects of PA with different diatomite contents were analyzed. • Traces of Al and Fe in solid waste fillers will leach during intensive rainfalls. • Diatomite filler remove pollutants via physical filtration and chemical adsorption. • Composition of PA is proposed for areas with different runoff pollution characteristics. [ABSTRACT FROM AUTHOR]