A new fault location method based on the three-terminal travelling wave method is proposed for the fault location problem of multi-branch overhead line–cable transmission lines. Firstly, the process of fault travelling wave propagation in overhead transmission lines and the phenomenon of refraction are analysed, and an improved phase-mode transformation is introduced to decouple the electromagnetic coupling and perform fault phase selection. Secondly, the Pearson correlation coefficient is introduced to compare the similarity of the current travelling waveforms at different measurement points in order to implement fault segmentation. To solve the problems of the complexity of the fault travelling wave propagation process and the difficulty of identifying the travelling wavehead, the Hilbert–Huang transform is used to extract the fault signal characteristics, and the travelling wave arrival moment is accurately calculated by the sampling error correction method to determine the fault location. Finally, the accuracy and stability of the method are verified via a simulation test on the MATLAB/Simulink platform. The results show that the proposed positioning method combining the three-terminal travelling wave method with HHT and sampling error correction can locate the fault location more accurately, and it has good potential for application in the engineering field. It provides a new technical means for fault location in overhead transmission lines, which is expected to become one of the most important technologies in the future power system.

This study proposes a multi-strategy improved Aquila optimizer (MIAO) to address the key limitations of the original Aquila optimizer (AO). First, a phasor operator is introduced to eliminate excessive control parameters in the X2 phase, transforming it into an adaptive parameter-free process. Second, a flow direction operator enhances the X3 phase by improving population diversity and local exploitation. The MIAO algorithm is applied to optimize Long Short-Term Memory (LSTM) hyperparameters, forming the MIAO_LSTM model for monthly railway freight forecasting. Comprehensive evaluations on 15 benchmark functions show MIAO’s superior performance over SOA, PSO, SSA, and AO. Using freight data (2005–2021), MIAO_LSTM achieves lower MAE, MSE, and RMSE compared to traditional LSTM and hybrid models (SSA_LSTM, PSO_LSTM, etc.). Further, Grey Relational Analysis selects high-correlation features (≥0.8) to boost accuracy. The results validate MIAO_LSTM’s effectiveness for practical freight predictions.