Data-Driven Fault Detection and Classification for MTDC Systems by Integrating HCTSA and Softmax Regression

The requirement of fast fault isolation poses a great challenge to the safe operation of multi-terminal direct current (MTDC) systems. In order to make a better tradeoff between the speed and reliability of the protection scheme, it is imperative to mine more valuable information from fault transient signals. This paper puts forward a data-driven framework capable of digging out and synthesizing multi-dimensional features to achieve fast and reliable DC fault detection and classification in MTDC systems. Highly comparative time-series analysis (HCTSA) is first adopted to extract extensive features with clear physical interpretations from fault current waveforms, and a few features valuable to fault identification are then selected utilizing the greedy forward search. Based on the reduced features, a softmax regression classifier (SRC) is further proposed to calculate the probability of each fault category with a relatively minor on-line computational burden. Numerical simulations carried out in PSCAD/EMTDC have demonstrated the proposed approach is effective under different fault conditions, robust against noise corruptions as well as abnormal samplings, and replicable in various DC grids. In addition, comprehensive comparison studies with conventional derivative-based protection methods and some typical artificial intelligence based (AI-based) methods have been conducted. It is verified that the proposed method has the advantages of higher fault identification accuracy over conventional protections and shallow structure AI-based methods, better interpretability as well as lower on-line computing complexity over the deep architecture AI-based approaches.

Automated summary

This paper presents a data-driven framework for fast and reliable DC fault detection and classification in MTDC systems. Extensive features are extracted using highly comparative time-series analysis (HCTSA) with clear physical interpretations, and valuable features for fault identification are selected using a greedy forward search. A softmax regression classifier (SRC) is proposed based on the reduced features to calculate the probability of each fault category with a minor online computational burden. Numerical simulations demonstrate the effectiveness of the proposed approach under different fault conditions and its robustness against noise corruptions and abnormal samplings.