Prognostics for Electromagnetic Relays Using Deep Learning
Electromagnetic Relays (Electromagnetic Relay (EMR)s) are omnipresent in electrical systems, ranging from mass-produced consumer products to highly specialised, safety-critical industrial systems. Our detailed literature review focused on EMR reliability highlighting the methods used to estimate the...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9671352/ |
| _version_ | 1823964368482598912 |
|---|---|
| author | Lucas Kirschbaum Valentin Robu Jonathan Swingler David Flynn |
| author_facet | Lucas Kirschbaum Valentin Robu Jonathan Swingler David Flynn |
| author_sort | Lucas Kirschbaum |
| collection | DOAJ |
| description | Electromagnetic Relays (Electromagnetic Relay (EMR)s) are omnipresent in electrical systems, ranging from mass-produced consumer products to highly specialised, safety-critical industrial systems. Our detailed literature review focused on EMR reliability highlighting the methods used to estimate the State of Health or the Remaining Useful Life emphasises the limited analysis and understanding of expressive EMR degradation indicators, as well as accessibility and use of EMR life cycle data sets. Prioritising these open challenges, a deep learning pipeline is presented in a prognostic context termed Electromagnetic Relay Useful Actuation Pipeline (EMRUA). Leveraging the attributes of causal convolution, a Temporal Convolutional Network (TCN) based architecture integrates an arbitrary long sequence of multiple features to produce a remaining useful switching actuations forecast. These features are extracted from raw, high volume life cycle data sets, namely EMR switching data (Contact-Voltage, Contact-Current). Monte-Carlo Dropout is utilised to estimate uncertainty during inference. The TCN hyperparameter space, as well as various methods to select and analyse long sequences of multivariate time series data are investigated. Subsequently, our results demonstrate improvements using the developed statistical feature-set over traditional, time-based features, commonly found in literature. EMRUA achieves an average forecasting mean absolute percentage error of ±12 % over the course of the entire EMR life. |
| first_indexed | 2024-12-17T17:42:39Z |
| format | Article |
| id | doaj.art-98788434b002482a8454212584beb9e6 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-17T17:42:39Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-98788434b002482a8454212584beb9e62022-12-21T21:39:09ZengIEEEIEEE Access2169-35362022-01-01104861489510.1109/ACCESS.2022.31406459671352Prognostics for Electromagnetic Relays Using Deep LearningLucas Kirschbaum0https://orcid.org/0000-0002-8270-1729Valentin Robu1https://orcid.org/0000-0002-9280-2072Jonathan Swingler2David Flynn3https://orcid.org/0000-0002-1024-3618Smart-Systems Group, School of Engineering and Physical Science, Heriot-Watt University, Edinburgh, U.KCWI, Dutch National Research Institute for Mathematics and Computer Science, Intelligent and Autonomous Systems, Amsterdam, XG, The NetherlandsSmart-Systems Group, School of Engineering and Physical Science, Heriot-Watt University, Edinburgh, U.KSmart-Systems Group, School of Engineering and Physical Science, Heriot-Watt University, Edinburgh, U.KElectromagnetic Relays (Electromagnetic Relay (EMR)s) are omnipresent in electrical systems, ranging from mass-produced consumer products to highly specialised, safety-critical industrial systems. Our detailed literature review focused on EMR reliability highlighting the methods used to estimate the State of Health or the Remaining Useful Life emphasises the limited analysis and understanding of expressive EMR degradation indicators, as well as accessibility and use of EMR life cycle data sets. Prioritising these open challenges, a deep learning pipeline is presented in a prognostic context termed Electromagnetic Relay Useful Actuation Pipeline (EMRUA). Leveraging the attributes of causal convolution, a Temporal Convolutional Network (TCN) based architecture integrates an arbitrary long sequence of multiple features to produce a remaining useful switching actuations forecast. These features are extracted from raw, high volume life cycle data sets, namely EMR switching data (Contact-Voltage, Contact-Current). Monte-Carlo Dropout is utilised to estimate uncertainty during inference. The TCN hyperparameter space, as well as various methods to select and analyse long sequences of multivariate time series data are investigated. Subsequently, our results demonstrate improvements using the developed statistical feature-set over traditional, time-based features, commonly found in literature. EMRUA achieves an average forecasting mean absolute percentage error of ±12 % over the course of the entire EMR life.https://ieeexplore.ieee.org/document/9671352/Electromagnetic relayprognosticsprognostics and health managementpredictive maintenanceremaining useful lifeartificial intelligence |
| spellingShingle | Lucas Kirschbaum Valentin Robu Jonathan Swingler David Flynn Prognostics for Electromagnetic Relays Using Deep Learning IEEE Access Electromagnetic relay prognostics prognostics and health management predictive maintenance remaining useful life artificial intelligence |
| title | Prognostics for Electromagnetic Relays Using Deep Learning |
| title_full | Prognostics for Electromagnetic Relays Using Deep Learning |
| title_fullStr | Prognostics for Electromagnetic Relays Using Deep Learning |
| title_full_unstemmed | Prognostics for Electromagnetic Relays Using Deep Learning |
| title_short | Prognostics for Electromagnetic Relays Using Deep Learning |
| title_sort | prognostics for electromagnetic relays using deep learning |
| topic | Electromagnetic relay prognostics prognostics and health management predictive maintenance remaining useful life artificial intelligence |
| url | https://ieeexplore.ieee.org/document/9671352/ |
| work_keys_str_mv | AT lucaskirschbaum prognosticsforelectromagneticrelaysusingdeeplearning AT valentinrobu prognosticsforelectromagneticrelaysusingdeeplearning AT jonathanswingler prognosticsforelectromagneticrelaysusingdeeplearning AT davidflynn prognosticsforelectromagneticrelaysusingdeeplearning |