Fault detection framework using neural networks for condition monitoring of high voltage equipment in power grids

back to project index

Project abstract

Asset management is a coordinated activity for the organization to get value from an asset. As the main part of asset management, maintenance includes all the technical and corresponding administrative actions to keep or restore the asset to the desired state in which it can perform its required functions. Traditional maintenance is usually based on scheduled monitoring and physical inspections. With the industrial internet of things developing, more operation data could be accessible and condition-based maintenances show promising for electrical equipment. This project targets to utilize operation data and neural networks to identify underlying operational risks for condition monitoring and preventive maintenance of high voltage equipment.

Summary of work

The project uses an online dataset as the main input. It built a framework using autoencoders and recurrent neural networks to model normal operations. Control charts are applied to evaluate current operating conditions and trigger alarms towards operational risks. The framework is tested with actual failure events.

Event log

-

Project reference-group

Nilanga Abeywickrama,  Hitachi ABB Power Grids
Michele Luvisotto,  Hitachi ABB Power Grids
Jan-Henning Juergensen,  Hitachi ABB Power Grids
Tommie Lindquist,  Svenska kraftnät
Cristian Rojas,  KTH

Publications by this researcher

See alternatively the researcher's full DiVA list of publications, with options for sorting.
Publications in journals and conferences usually will not show until a while after they are published.

An Anomaly Detection Approach Based on Autoencoders for Condition Monitoring of Wind Turbines
Jose Eduardo Urrea Cabus,   Yue Cui,   Lina Bertling.
2022,   17th International Conference on Probabilistic Methods Applied to Power Systems (PMAPS), JUN 12-15, 2022, Manchester, ENGLAND

Fault Diagnostics of Power Transformers Using Autoencoders and Gated Recurrent Units with Applications for Sensor Failures
Yue Cui,   Lina Bertling Tjernberg.
2022,   17th International Conference on Probabilistic Methods Applied to Power Systems (PMAPS), JUN 12-15, 2022, Manchester, England

A fault detection framework using RNNs for condition monitoring of wind turbines
Yue Cui,   Pramod Bangalore,   Lina Bertling.
2021,   Wind Energy

A Fault Detection Framework Using Recurrent Neural Networks for Condition Monitoring of Wind Turbines
Yue Cui.
2021,   Thesis (PhD), KTH Royal Institute of Technology, TRITA-EECS-AVL 2021:4

Wind Turbine Health Assessment Framework Based on Power Analysis Using Machine Learning Method
Qiuyi Huang,   Yue Cui,   Lina Bertling,   Pramod Bangalore.
2019,   2019 IEEE PES Innovative Smart Grid Technologies Europe, ISGT-Europe 2019, Bucharest, Romania, September 29 - October 2, 2019

An anomaly detection approach based on machine learning and scada data for condition monitoring of wind turbines
Yue Cui,   Pramod Bangalore,   Lina Bertling Tjernberg.
2018,   2018 International Conference on Probabilistic Methods Applied to Power Systems, PMAPS 2018, 24 June 2018 through 28 June 2018

An Anomaly Detection Approach Using Wavelet Transform and Artificial Neural Networks for Condition Monitoring of Wind Turbines' Gearboxes
Yue Cui,   Pramod Bangalore,   Lina Bertling Tjernberg.
2018,   2018 POWER SYSTEMS COMPUTATION CONFERENCE (PSCC)

Applying High Performance Computing to Probabilistic Convex Optimal Power Flow
Zhao Yuan,   Mohammad Reza Hesamzadeh,   Yue Cui,   Lina Bertling Tjernberg.
2016,   International Conference on Probabilistic Methods Applied to Power Systems (PMAPS), OCT 16-20, 2016, Beijing, PEOPLES R CHINA

Publication list last updated from DiVA on 2024-08-22 22:57.

Page started: 2021-02-01
Last generated: 2024-08-22