MoEKAN: Multi-Scale Transformer-Based Gating KAN Experts Network for Time Series Forecasting

An on-load tap changer (OLTC) is a critical component of power transformers, and the vibration signals generated during its operation provide valuable information for forecasting equipment conditions and anomalies. In this study, we propose a novel mixture-of-experts-based Kolmogorov-Arnold network (KAN) model, referred to as MoEKAN, to enhance the accuracy of time series forecasting for the vibration signals of the OLTC. The proposed MoEKAN incorporates reversible instance normalization (RevIN) to flexibly adapt to changes in data distribution and employs a transformer-based gating mechanism to dynamically integrate forecasts from various KAN expert models. In addition, multi-scale signal processing is performed to effectively capture the complex periodicity and patterns present in the vibration data. Experiments using real OLTC operational data demonstrate that the MoEKAN model achieves superior forecasting performance, recording forecasting errors with MSE, MAE, and MAPE values of 133.4579, 7.2801, and 4.4272, respectively, outperforming all comparison models. These results validate the practicality and contribution of the proposed model and confirm its potential as a highly reliable diagnostic tool for condition monitoring and predictive maintenance of OLTCs.