Skip to main content

Table 1 Comparison of the ANN-based fault location methods

From: Hybrid classifier for fault location in active distribution networks

Method

Type

Inputs

Outputs

Considered fault types

Considering the effect of DG

Thukaram et al. [3]

Feedforward ANN

Three-phase steady-state voltage and current

Line reactance to the fault from the main substation

All types

–

Pourahmadi-Nakhli and Safavi [4]

Feedforward ANN

Energy content of voltage transients around the characteristic frequencies

Fault distance from the main substation

Single-line to ground

–

Rafinia and Moshtagh [5]

Feedforward ANN

Information extracted using DWT and analysis of the recorded transients

Fault distance from the main substation

All types

✓

Chen et al. [6]

Feedforward ANN

Information extracted from voltage signals recorded at different locations

Distance to the fault from all voltage sensors and the faulted line- section

Earth faults

✓

Dashtdar et al. [7]

Feedforward ANN

High frequency components of current signals

Line impedance to the main substation, faulted line-section

All types

–

Chunju et al. [8]

WFNN

High frequency and low-frequency components of voltage and current transients

Fault distance from the main substation

Single-line to ground

–

Aslan and Yagan [9]

Feedforward ANN

High frequency and low-frequency components of voltage and current transients

Fault distance from the main substation

All types

–

Mora et al. [10]

ANFIS

Patterns obtained from measured substation current

Faulted zone

All types

–

Javadian et al. [11]

Feedforward ANN

Ratio of injected fault currents of DGs to substation current

Distance to the fault from all DGs and the main substation

All types

✓

The proposed method

Feedforward ANN

Three-phase steady-state voltages and currents of substation and DGs

Fault location, faulted line-section and distance to the fault from all DGs and the main substation

All types

✓