Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306148319> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4306148319 abstract "Many finite-element simulations are required to fully evaluate the performance of a motor design candidate at different operating points. In this work, we investigate deep learning based surrogate modeling technique for motor design optimization to reduce simulations required. In particular, we introduce topological data analysis to electric machine design, which extracts topological features from motor design images for the training of machine learning models. We introduce the process of computing persistence homology and Betti sequences, which serve as vectorized input data for machine learning models. We propose two-channel deep learning models, with one convolutional network branch built for motor image data, and another multi-layer perceptron branch for Betti sequences. We show with numerical tests that two-channel models perform better in prediction accuracy and generalization capability compared with models without topological feature input. The results show that the proposed strategy is effective for image- based deep learning problems." @default.
- W4306148319 created "2022-10-14" @default.
- W4306148319 creator A5015844567 @default.
- W4306148319 creator A5039610053 @default.
- W4306148319 creator A5073320770 @default.
- W4306148319 date "2022-09-05" @default.
- W4306148319 modified "2023-10-02" @default.
- W4306148319 title "Topological Data Analysis for Image-based Machine Learning: Application to Electric Motors" @default.
- W4306148319 cites W1798863697 @default.
- W4306148319 cites W1991566301 @default.
- W4306148319 cites W2071020865 @default.
- W4306148319 cites W2096736341 @default.
- W4306148319 cites W2117539524 @default.
- W4306148319 cites W2144044408 @default.
- W4306148319 cites W2153986241 @default.
- W4306148319 cites W2194775991 @default.
- W4306148319 cites W2424211690 @default.
- W4306148319 cites W2613791983 @default.
- W4306148319 cites W2759752204 @default.
- W4306148319 cites W2788361005 @default.
- W4306148319 cites W2892377642 @default.
- W4306148319 cites W2911499573 @default.
- W4306148319 cites W2921710869 @default.
- W4306148319 cites W2922327436 @default.
- W4306148319 cites W2927592310 @default.
- W4306148319 cites W2963129226 @default.
- W4306148319 cites W2999000694 @default.
- W4306148319 cites W2999315501 @default.
- W4306148319 cites W3041095260 @default.
- W4306148319 cites W3047266019 @default.
- W4306148319 cites W4226236156 @default.
- W4306148319 doi "https://doi.org/10.1109/icem51905.2022.9910734" @default.
- W4306148319 hasPublicationYear "2022" @default.
- W4306148319 type Work @default.
- W4306148319 citedByCount "2" @default.
- W4306148319 countsByYear W43061483192023 @default.
- W4306148319 crossrefType "proceedings-article" @default.
- W4306148319 hasAuthorship W4306148319A5015844567 @default.
- W4306148319 hasAuthorship W4306148319A5039610053 @default.
- W4306148319 hasAuthorship W4306148319A5073320770 @default.
- W4306148319 hasConcept C108583219 @default.
- W4306148319 hasConcept C119599485 @default.
- W4306148319 hasConcept C119857082 @default.
- W4306148319 hasConcept C127413603 @default.
- W4306148319 hasConcept C154945302 @default.
- W4306148319 hasConcept C184720557 @default.
- W4306148319 hasConcept C41008148 @default.
- W4306148319 hasConcept C50644808 @default.
- W4306148319 hasConcept C60908668 @default.
- W4306148319 hasConcept C81363708 @default.
- W4306148319 hasConceptScore W4306148319C108583219 @default.
- W4306148319 hasConceptScore W4306148319C119599485 @default.
- W4306148319 hasConceptScore W4306148319C119857082 @default.
- W4306148319 hasConceptScore W4306148319C127413603 @default.
- W4306148319 hasConceptScore W4306148319C154945302 @default.
- W4306148319 hasConceptScore W4306148319C184720557 @default.
- W4306148319 hasConceptScore W4306148319C41008148 @default.
- W4306148319 hasConceptScore W4306148319C50644808 @default.
- W4306148319 hasConceptScore W4306148319C60908668 @default.
- W4306148319 hasConceptScore W4306148319C81363708 @default.
- W4306148319 hasFunder F4320323533 @default.
- W4306148319 hasLocation W43061483191 @default.
- W4306148319 hasOpenAccess W4306148319 @default.
- W4306148319 hasPrimaryLocation W43061483191 @default.
- W4306148319 hasRelatedWork W1501213224 @default.
- W4306148319 hasRelatedWork W2731899572 @default.
- W4306148319 hasRelatedWork W3116150086 @default.
- W4306148319 hasRelatedWork W3133861977 @default.
- W4306148319 hasRelatedWork W4200173597 @default.
- W4306148319 hasRelatedWork W4231994957 @default.
- W4306148319 hasRelatedWork W4312417841 @default.
- W4306148319 hasRelatedWork W4321369474 @default.
- W4306148319 hasRelatedWork W4322750901 @default.
- W4306148319 hasRelatedWork W4381616756 @default.
- W4306148319 isParatext "false" @default.
- W4306148319 isRetracted "false" @default.
- W4306148319 workType "article" @default.