Enhanced distance protection for HVDC lines using adaptive neuro-fuzzy inference systems

Area of Science:

• Electrical Engineering
• Power Systems Engineering

Background:

• Accurate and fast fault detection is essential for the reliable operation of DC transmission systems.
• Existing methods for high-voltage DC transmission lines (HVDC-TLs) face challenges in detecting faults, especially those with high resistance.

Purpose of the Study:

• To propose a novel approach for fault detection, classification, and localization in HVDC-TLs.
• To enhance the performance and reliability of protection schemes for HVDC-TLs.

Main Methods:

• A distance protection scheme was developed using a fuzzy inference system (FIS).
• An adaptive neuro-fuzzy inference system (ANFIS) was trained for precise fault location estimation.
• The transmission line was divided into three zones for fault location identification.
• Simulations were conducted using PSCAD and MATLAB on a monopolar DC transmission line model.

Main Results:

• The proposed FIS model effectively detects and classifies faults, including those with high resistance.
• The ANFIS accurately estimates fault location per kilometer.
• The developed distance protection scheme demonstrated superior performance compared to existing methods.

Conclusions:

• The novel fuzzy inference-based approach offers improved accuracy and speed for fault management in HVDC-TLs.
• The method is effective for estimating fault areas and locating faults, enhancing overall system protection.