Ultra-short-term electricity load forecasting is crucial for real-time power system operation, but its accuracy is limited by the nonstationary and multiscale characteristics of load data. To address this issue, this study proposes a multi-scale decomposition–clustering and heterogeneous gated fusion framework. The original load sequence is decomposed by ICEEMDAN and then grouped into high-, mid-, and low-frequency components using K-means clustering. MS-gTCN is used to capture high-frequency fluctuations, adaptive DLinear is used to model low-frequency trends, and a gated fusion mechanism is designed for mid-frequency components. A lightweight error correction network is further introduced to reduce residual prediction errors. Experiments on two real-world datasets show that the proposed method achieves the best performance across 1-, 4-, 8-, and 12-step horizons. For the 12-step task, it reduces MAE by 29.3% on Dataset A and 26.2% on Dataset B compared with the second-best baselines. Compared with ICEEMDAN-LSTM on Dataset A, it reduces MAE by 17.7% and improves $R^2$ from 0.9127 to 0.9418. Ablation, sensitivity, significance, and complexity analyses further verify the effectiveness, robustness, and real-time feasibility of the proposed framework.

Surface defect detection of lithium battery electrodes is vital for industrial automation but remains challenging due to scale variations and complex backgrounds. To address these challenges, this study proposes CEBW-YOLO11, an enhanced YOLO11n-based framework specifically designed for lithium battery electrode sheet defect detection. The proposed method integrates C3k2-DWR for multi-scale feature extraction, EAC for discriminative feature enhancement, BiFPN-DySample for adaptive feature fusion, and Wise-Inner-IoU for bounding box regression optimization. Experimental results on the electrode defect dataset demonstrate that, compared with the baseline YOLO11n, CEBW-YOLO11 improves Precision, Recall, and mAP@0.5 by 3.8, 4.7, and 3.8 percentage points, respectively. The proposed model achieves an inference speed of 90 FPS at an input resolution of 640 × 640 pixels, showing its potential for real-time electrode defect inspection applications.