Wind Turbine Gearbox Fault Diagnosis Method Based on Improved CNN-XGBoost Fusion Model Under Gramian Angular Difference Field

• • GADF transformation converts 1D vibration signals into 2D images with sparse matrix encoding, preserving temporal correlation and suppressing noise; this directly addresses the <90% accuracy ceiling of conventional EMD/Teager-based methods and enables reliable early-stage fault warning in wind farms. • • Embedding CBAM in the CNN convolutional layers provides dual channel and spatial attention, increasing global feature extraction; this overcomes the shallow two-layer convolution limitation of prior multiscale CNNs and improves discrimination of weak fault signatures under variable load. • • Replacing ReLU with the βc-ACONC activation function eliminates neuron necrosis and enables selective activation, preserving valid features while filtering noise; this extends the model's usable training depth and stabilizes convergence on high-dimensional GADF inputs. • • ISSA-optimized XGBoost hyperparameters deliver >99% diagnostic accuracy on the laboratory gearbox dataset, a decisive improvement over the 20–30% fault contribution and 10–15% maintenance cost burden of gearbox failures, enabling condition-based maintenance with direct cost reduction.