A novel fault detection algorithm for high voltage DC networks

Faults in high voltage DC networks can lead to inefficient operation, power outage or even equipment damage. Therefore, several approaches have been proposed to monitor, detect, and handle such problems. Due to high currents during faults, run-time for detecting malfunctions is crucial. Thus, fast recognition of small deviations that might lead to an abnormal operation is quintessential in minimizing consequences. This work presents a novel fault-detection mechanism, which is based on locality-sensitive hashes and its run-time scales linearly with the number of analyzed samples. To detect a malfunction, the algorithm uses reference signals corresponding to the normal operating point. Yet, only 19 reference signals were sufficient and delivered results comparable to a system using 100. When having only 19 references, the detector's runtime is below 0.15 ms for an analyzed signal of 400 samples. Apart from fault detection, the proposed mechanism can also be used to reduce the storage requirements of the monitoring system. For a later investigation of a faulty event, the monitoring system must store the samples containing signal degradation. Even some temporary small changes can yield valuable information regarding the cause of the fault. However, storing many samples inevitably leads to big storage units, which are costly. To address this issue, the proposed mechanism sends a criticality factor to the monitoring system, based on which the signal samples may be compressed or removed.