A Data-Aided Power Transformer Differential Protection without Inrush Blocking Module

TL;DR

This paper introduces a data-driven transformer differential protection method that accurately distinguishes inrush from fault currents without relying on inrush blocking modules, enhancing protection sensitivity and speed.

Contribution

It proposes an innovative combination of an Attention-based Fully Convolutional Network and a physical model to effectively extract the fundamental component of non-inrush current, avoiding false blocking.

Findings

The method accurately differentiates inrush and fault currents in simulations.

Experimental results confirm improved protection sensitivity and response time.

The approach is effective even with weak internal faults hidden in inrush currents.

Abstract

When a slightly faulty transformer closes without load, the current waveform presents the coexistence of inrush and fault current. At this time, the inrush blocking module will block the relay, which may delay the removal of the slight fault and lead to more serious faults. To address this problem, this paper proposes a data-aided power transformer differential protection without inrush blocking module. The key to eliminating the negative influence of inrush current is to extract the fundamental component from the non-inrush part of the current waveform, which corresponds to the unsaturation period of the transformer core. Firstly, a data-aided module, namely an Attention module embedded Fully Convolutional Network (A-FCN), is built to distinguish the inrush and non-inrush parts of the current waveform. Then, a physical model of the current waveform is built for the non-inrush part, and the fundamental component is extracted by the nonlinear least square (NLS) algorithm. The proposed method can avoid the block of differential protections when inrush current occurs, which improves the sensitivity and rapidity of the relay, especially in the case of a weak internal fault hidden in inrush current. Finally, simulation and experimental data verify the effectiveness and generalization of the proposed method.