Subtopic Deep Dive

Artificial Neural Networks for Fault Location in Microgrids
Research Guide

What is Artificial Neural Networks for Fault Location in Microgrids?

Artificial Neural Networks for Fault Location in Microgrids applies ANN models trained on PSCAD simulations to locate faults using impedance or traveling wave methods in inverter-dominated radial and looped microgrids.

ANNs process voltage and current signals from PMUs or synchrophasors for precise fault pinpointing (Gururajapathy et al., 2017, 335 citations). RBF networks classify and locate faults from instantaneous samples (Mahanty and Gupta, 2004, 208 citations). LSTM and CNN models handle high-impedance faults in PV-integrated systems (Veerasamy et al., 2021, 192 citations; Thomas et al., 2023, 184 citations). Over 20 papers since 2004 address microgrid-specific challenges.

15
Curated Papers
3
Key Challenges

Why It Matters

ANN fault locators reduce outage times in microgrids by enabling sub-cycle fault isolation, vital for renewable-heavy grids with bidirectional power flows (Kar and Samantaray, 2013). RBF networks achieve 98% accuracy in transmission line fault location using wavelet features (Mahanty and Gupta, 2004). LSTM classifiers detect high-impedance faults in solar PV systems, preventing fires and improving reliability (Veerasamy et al., 2021). GCN frameworks integrate topology for distribution fault location (Chen et al., 2019). These methods support resilient operation in remote microgrids serving hospitals and military bases.

Key Research Challenges

Inverter Harmonic Distortion

Inverter-dominated microgrids introduce harmonics that degrade ANN input signals (Kar and Samantaray, 2013). Training data from PSCAD must capture diverse fault types amid noise (Belagoune et al., 2021). S-transform preprocessing helps extract time-frequency features for robust classification.

Limited PMU Coverage

Sparsely placed PMUs limit wide-area data for ANN training (Aminifar et al., 2014, 254 citations). Graph convolutional networks incorporate topology to compensate (Chen et al., 2019). Radial topology assumptions fail in looped microgrids.

High-Impedance Fault Detection

HIFs produce weak signatures undetectable by traditional relays (Veerasamy et al., 2021). LSTM networks analyze time-series data for subtle patterns (Belagoune et al., 2021, 258 citations). Real-time processing requires optimized architectures.

Essential Papers

1.

Fault location and detection techniques in power distribution systems with distributed generation: A review

Sophi Shilpa Gururajapathy, Hazlie Mokhlis, Hazlee Azil Illias · 2017 · Renewable and Sustainable Energy Reviews · 335 citations

2.

Fault Location in Power Distribution Systems via Deep Graph Convolutional Networks

Kunjin Chen, Jun Hu, Yu Zhang et al. · 2019 · IEEE Journal on Selected Areas in Communications · 285 citations

This paper develops a novel graph convolutional network (GCN) framework for\nfault location in power distribution networks. The proposed approach integrates\nmultiple measurements at different buse...

3.

Fault detection and classification in electrical power transmission system using artificial neural network

Majid Jamil, Sanjeev Kumar Sharma, Rajveer Singh · 2015 · SpringerPlus · 259 citations

5.

Synchrophasor Measurement Technology in Power Systems: Panorama and State-of-the-Art

Farrokh Aminifar, Mahmud Fotuhi‐Firuzabad, Amir Safdarian et al. · 2014 · IEEE Access · 254 citations

Phasor measurement units (PMUs) are rapidly being deployed in electric power networks across the globe. Wide-area measurement system (WAMS), which builds upon PMUs and fast communication links, is ...

6.

Time‐frequency transform‐based differential scheme for microgrid protection

Susmita Kar, Subhransu Rajan Samantaray · 2013 · IET Generation Transmission & Distribution · 233 citations

The study presents a differential scheme for microgrid protection using time‐frequency transform such as S‐transform. Initially, the current at the respective buses are retrieved and processed thro...

7.

Application of RBF neural network to fault classification and location in transmission lines

Rabindra Nath Mahanty, Preeti Gupta · 2004 · IEE Proceedings - Generation Transmission and Distribution · 208 citations

The application of radial basis function (RBF) neural networks for fault classification and location in transmission lines is presented. Instantaneous current/voltage samples have been used as inpu...

Reading Guide

Foundational Papers

Start with Mahanty and Gupta (2004, RBF basics, 208 citations) for ANN fundamentals, then Aminifar et al. (2014, PMU infrastructure, 254 citations), Kar and Samantaray (2013, microgrid protection, 233 citations) for domain context.

Recent Advances

Study Veerasamy et al. (2021, LSTM for PV-HIFs, 192 citations), Thomas et al. (2023, CNN transformers, 184 citations), Belagoune et al. (2021, LSTM regression, 258 citations) for state-of-the-art.

Core Methods

RBF with instantaneous samples (Mahanty and Gupta, 2004); LSTM time-series classification (Veerasamy et al., 2021); GCN topology integration (Chen et al., 2019); S-transform preprocessing (Kar and Samantaray, 2013); PSCAD training data.

How PapersFlow Helps You Research Artificial Neural Networks for Fault Location in Microgrids

Discover & Search

Research Agent uses searchPapers('ANN fault location microgrids') to retrieve 25+ papers including Gururajapathy et al. (2017, 335 citations), then citationGraph reveals clusters around RBF (Mahanty and Gupta, 2004) and LSTM methods. findSimilarPapers on Chen et al. (2019) uncovers GCN applications; exaSearch('PMU microgrid fault ANN') finds niche PSCAD simulation papers.

Analyze & Verify

Analysis Agent applies readPaperContent to extract RBF training protocols from Mahanty and Gupta (2004), then runPythonAnalysis recreates accuracy metrics using NumPy/pandas on voltage samples. verifyResponse with CoVe cross-checks claims against Aminifar et al. (2014) PMU data; GRADE scores evidence strength for LSTM vs CNN performance (Thomas et al., 2023).

Synthesize & Write

Synthesis Agent detects gaps in looped microgrid coverage via contradiction flagging between radial-focused papers, generates exportMermaid diagrams of ANN architectures. Writing Agent uses latexEditText for equations, latexSyncCitations imports 15 references, latexCompile produces IEEE-formatted review with gap analysis.

Use Cases

"Reproduce RBF fault locator accuracy from Mahanty 2004 using Python"

Research Agent → searchPapers → readPaperContent (Mahanty and Gupta, 2004) → Analysis Agent → runPythonAnalysis (NumPy wavelet simulation, pandas accuracy metrics) → matplotlib plot of 98% precision vs fault distance.

"Write LaTeX review of ANN vs LSTM for microgrid faults"

Synthesis Agent → gap detection (LSTM advantages) → Writing Agent → latexEditText (intro/methods) → latexSyncCitations (10 papers) → latexCompile → PDF with S-transform equations and bibliography.

"Find GitHub code for GCN fault location in distribution systems"

Research Agent → searchPapers (Chen et al., 2019) → Code Discovery → paperExtractUrls → paperFindGithubRepo → githubRepoInspect → PyTorch GCN implementation with topology matrices and 95% accuracy demo.

Automated Workflows

Deep Research workflow scans 50+ papers via searchPapers → citationGraph → structured report ranking ANN methods by microgrid accuracy (RBF > LSTM). DeepScan's 7-step analysis verifies Chen et al. (2019) GCN claims with runPythonAnalysis on PSCAD data. Theorizer generates hypotheses combining PMU data (Aminifar et al., 2014) with hybrid CNN-LSTM architectures.

Frequently Asked Questions

What defines ANN fault location in microgrids?

ANNs trained on PSCAD-simulated impedance/traveling wave data locate faults in inverter-based radial/looped microgrids using voltage/current inputs (Mahanty and Gupta, 2004).

What are key ANN methods used?

RBF networks process instantaneous samples (Mahanty and Gupta, 2004); LSTM handles time-series for HIFs (Veerasamy et al., 2021); GCN integrates topology (Chen et al., 2019).

What are the most cited papers?

Gururajapathy et al. (2017, 335 citations) reviews techniques; Mahanty and Gupta (2004, 208 citations) introduces RBF; Aminifar et al. (2014, 254 citations) covers PMU foundations.

What open problems remain?

Real-time processing of sparse PMU data in looped microgrids; hybrid ANN models for HIFs under harmonics; validation beyond PSCAD simulations.

Research Power Systems Fault Detection with AI

PapersFlow provides specialized AI tools for Engineering researchers. Here are the most relevant for this topic:

See how researchers in Engineering use PapersFlow

Field-specific workflows, example queries, and use cases.

Engineering Guide

Start Researching Artificial Neural Networks for Fault Location in Microgrids with AI

Search 474M+ papers, run AI-powered literature reviews, and write with integrated citations — all in one workspace.

See how PapersFlow works for Engineering researchers