Matches in SemOpenAlex for { <https://semopenalex.org/work/W2138354408> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2138354408 abstract "Railway track circuits are electrical systems that are used for train detection. The identification of faults in these track circuits and the estimation of the severity of these faults is crucial for the safety and availability of railway networks. In this thesis a method is proposed to solve these tasks based on the commonly available measurement signals. By considering the signals from multiple track circuits in a geographic area, faults can be identified from their spatial and temporal dependencies. In this thesis, artificial neural networks are used to learn these dependencies from historical data. Although not enough measurement data was available during the writing of this thesis, it is more than likely that reasonable amounts of (unlabeled) measurement data will become available at a later time, as the required measurement equipment has already been installed. To train the networks in this thesis, the small available dataset is analyzed and used together with the currently available understanding of the fault dependencies to make a generative model. The synthetic data produced by this model are used to train and test the neural networks in this thesis. Artificial neural networks have recently achieved state of the art performance on difficult pattern recognition problems in several different fields such as image recognition and speech recognition. These recent successes can be largely attributed to the combination of large networks and large datasets. In the condition monitoring domain large datasets are generally not available. This prevents the use of the large neural networks that have become so successful in other fields. In-spite of this, some of the ideas that have become popular in other domains might still have value in the condition monitoring domain. This thesis focuses on bringing the Long-Short Term Memory architecture and the concept of end-to-end learning to the condition monitoring domain. To address the fact that only a limited amount of labeled data will be available, an unsupervised learning strategy is investigated. This strategy will use unlabeled data to pre-train a network so that it can more efficiently learn from the scarce labeled data. For the fault isolation task, it is shown in this thesis that when a large amount of labeled training data is available, the end-to-end learning strategy can detect and diagnose faults in the data from the generative model very accurately. When only a small amount of labeled data is available, it is shown that using a pre-trained network works better than using end-to-end learning." @default.
- W2138354408 created "2016-06-24" @default.
- W2138354408 creator A5033347648 @default.
- W2138354408 date "2015-06-01" @default.
- W2138354408 modified "2023-09-27" @default.
- W2138354408 title "Neural network based condition monitoring for track circuits" @default.
- W2138354408 hasPublicationYear "2015" @default.
- W2138354408 type Work @default.
- W2138354408 sameAs 2138354408 @default.
- W2138354408 citedByCount "0" @default.
- W2138354408 crossrefType "journal-article" @default.
- W2138354408 hasAuthorship W2138354408A5033347648 @default.
- W2138354408 hasConcept C111919701 @default.
- W2138354408 hasConcept C116834253 @default.
- W2138354408 hasConcept C119857082 @default.
- W2138354408 hasConcept C124101348 @default.
- W2138354408 hasConcept C127313418 @default.
- W2138354408 hasConcept C153180895 @default.
- W2138354408 hasConcept C154945302 @default.
- W2138354408 hasConcept C165205528 @default.
- W2138354408 hasConcept C175551986 @default.
- W2138354408 hasConcept C191926282 @default.
- W2138354408 hasConcept C202444582 @default.
- W2138354408 hasConcept C33923547 @default.
- W2138354408 hasConcept C41008148 @default.
- W2138354408 hasConcept C50644808 @default.
- W2138354408 hasConcept C59822182 @default.
- W2138354408 hasConcept C761482 @default.
- W2138354408 hasConcept C76155785 @default.
- W2138354408 hasConcept C86803240 @default.
- W2138354408 hasConcept C89992363 @default.
- W2138354408 hasConcept C9652623 @default.
- W2138354408 hasConceptScore W2138354408C111919701 @default.
- W2138354408 hasConceptScore W2138354408C116834253 @default.
- W2138354408 hasConceptScore W2138354408C119857082 @default.
- W2138354408 hasConceptScore W2138354408C124101348 @default.
- W2138354408 hasConceptScore W2138354408C127313418 @default.
- W2138354408 hasConceptScore W2138354408C153180895 @default.
- W2138354408 hasConceptScore W2138354408C154945302 @default.
- W2138354408 hasConceptScore W2138354408C165205528 @default.
- W2138354408 hasConceptScore W2138354408C175551986 @default.
- W2138354408 hasConceptScore W2138354408C191926282 @default.
- W2138354408 hasConceptScore W2138354408C202444582 @default.
- W2138354408 hasConceptScore W2138354408C33923547 @default.
- W2138354408 hasConceptScore W2138354408C41008148 @default.
- W2138354408 hasConceptScore W2138354408C50644808 @default.
- W2138354408 hasConceptScore W2138354408C59822182 @default.
- W2138354408 hasConceptScore W2138354408C761482 @default.
- W2138354408 hasConceptScore W2138354408C76155785 @default.
- W2138354408 hasConceptScore W2138354408C86803240 @default.
- W2138354408 hasConceptScore W2138354408C89992363 @default.
- W2138354408 hasConceptScore W2138354408C9652623 @default.
- W2138354408 hasLocation W21383544081 @default.
- W2138354408 hasOpenAccess W2138354408 @default.
- W2138354408 hasPrimaryLocation W21383544081 @default.
- W2138354408 hasRelatedWork W1812109034 @default.
- W2138354408 hasRelatedWork W2029126611 @default.
- W2138354408 hasRelatedWork W2058764642 @default.
- W2138354408 hasRelatedWork W2066428990 @default.
- W2138354408 hasRelatedWork W2080083479 @default.
- W2138354408 hasRelatedWork W2100194594 @default.
- W2138354408 hasRelatedWork W2109014976 @default.
- W2138354408 hasRelatedWork W2138883129 @default.
- W2138354408 hasRelatedWork W2141931760 @default.
- W2138354408 hasRelatedWork W2466170565 @default.
- W2138354408 hasRelatedWork W2528709811 @default.
- W2138354408 hasRelatedWork W2744790985 @default.
- W2138354408 hasRelatedWork W2773131928 @default.
- W2138354408 hasRelatedWork W2988533417 @default.
- W2138354408 hasRelatedWork W2996850586 @default.
- W2138354408 hasRelatedWork W3023170583 @default.
- W2138354408 hasRelatedWork W3092775294 @default.
- W2138354408 hasRelatedWork W3133607401 @default.
- W2138354408 hasRelatedWork W3161010649 @default.
- W2138354408 hasRelatedWork W3175176244 @default.
- W2138354408 isParatext "false" @default.
- W2138354408 isRetracted "false" @default.
- W2138354408 magId "2138354408" @default.
- W2138354408 workType "article" @default.