This paper proposes a comprehensive novel multi-terminal HVDC protection scheme based on artificial neural network (ANN) and high frequency components detected from fault current signals only. The method is shown to accurately detect, classify and locate overhead line faults. Unlike existing travelling wave based methods which must capture the initial wavefront and require high sampling rates, the new approach is more robust since it gives accurate fault detection and fault location over a range of windowed post-fault signals. Furthermore, the proposed method is fault resistance independent meaning even a very high fault impedance has no effect on accurate fault location. A three-terminal VSC-HVDC system is modelled in PSCAD/EMTDC, which is used for obtaining the fault current data for transmission line terminals. The method is verified by studying different cases with a range of fault resistances in various fault locations, and in addition, external faults. The results show that the proposed method gives fast (<5 ms) and reliable (100%) fault detection and classification and accurate location (<1.16%) for DC line faults.
|Number of pages||10|
|Journal||Electric Power Systems Research|
|Early online date||7 Apr 2017|
|Publication status||Published - 1 Jul 2017|
- Artificial neural network
- Fault current signal
- Fault detection
- Fault location
- Transmission line
- VSC-HVDC system
FingerprintDive into the research topics of 'New ANN method for multi-terminal HVDC protection relaying'. Together they form a unique fingerprint.
- Department of Electronic & Electrical Engineering - Emeritus Professor
Person: Honorary / Visiting Staff