Hierarchical Fault Diagnosis in Transmission Systems: Comparative Machine Learning for Fault Classification and Zonal Location with Traveling-Wave-Based Distance Estimation

This study evaluates a hierarchical workflow for fault diagnosis in transmission systems by integrating established machine-learning techniques for fault-type classification and zonal fault location with a complementary double-ended traveling-wave procedure for point-location estimation. The contribution lies at the level of process integration and comparative evaluation rather than in the proposal of a new machine-learning or traveling-wave algorithm. The methodology was evaluated using the IEEE 9-bus test system. Symmetrical and asymmetrical short-circuit scenarios were automatically simulated at multiple positions along six transmission lines using DIgSILENT PowerFactory, and the resulting oscillographic records were exported in COMTRADE format, producing a database of 2952 fault events. Phase voltages and currents, together with positive-, negative-, and zero-sequence components, were used to evaluate Decision Trees, Self-Organizing Maps (SOM), Artificial Neural Networks (ANN), and k-Nearest Neighbors (KNN) for fault-type classification and zonal fault location. Under the simulated noise-free conditions and the adopted fixed hold-out partition, all four algorithms correctly classified the 591 fault-type testing observations, yielding 100% test-set accuracy. This result characterizes the specific evaluation subset considered in the study; repeated, cross-validated, or grouped partitions were not performed, and neighboring simulated fault positions may therefore be represented across the training and testing subsets. For zonal fault location, the ANN exhibited the strongest and most consistent observed performance in the retained 590-event evaluation set, with class-specific recall values between approximately 0.96 and 0.99 across the six fault zones, whereas the Decision Tree provided a favorable compromise between zonal discrimination and computational efficiency. Some model-specific hyperparameter values from the original executions are unavailable in the retained experimental record, which limits exact replication of those original configurations; the reported results correspond to the evaluated executions documented in this study. As a complementary third component of the workflow, the double-ended traveling-wave procedure based on discrete wavelet analysis was illustrated for one AG event simulated at 25% of the transmission-line length, producing a normalized point-location estimate of approximately 25.07% from the local terminal. This single-event analysis demonstrates the operation of the traveling-wave processing sequence, while broader multi-event validation is outside the present experimental scope. Overall, the results demonstrate the coordinated application of fault-type classification, zonal fault location, and traveling-wave-based point-location refinement within a common diagnostic workflow. The findings should be interpreted within the deterministic simulation conditions, fixed evaluation subsets, and experimental records considered in this study.