Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312995256> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4312995256 endingPage "416" @default.
- W4312995256 startingPage "410" @default.
- W4312995256 abstract "ECM (Electrochemical Machining) with a micro-second pulsed power supply can decrease stray current corrosion and thus provide better surface quality on top of higher machining accuracy. However, the use of a pulsed power supply makes it challenging to predict the final workpiece profile based on the typical multi-physical-based FEM(Finite Element method) models. First, it is impractical to introduce high-frequency pulsed electric current (ns - µs) into a multi-physical model because of time step limitations. Second, there arise problems of compatibility of the time-steps within each physical module, as e.g. hydrogen bubbles have a lifetime of ms, the power supply would use μs, and thermal phenomena take ms. Multi-scale models have been proposed, but the prediction accuracies are rather low and computation times are very long. In this article, based on machine learning approaches, we present 3 data-driven ECM models for predicting the final workpiece profile when using pulsed-ECM: the linear regression (LR) model, the neural network (NN) model, and the convolutional neural network (CNN) model. After training this data-driven ECM model with different levels of pulse voltage and electrolyte flow conditions, predictions and experimental validation are conducted. Experiments with parameters outside the training parameter window are also carried out to show the performance and general applicability of our data-driven ECM model. The machine learning model shows a good generalizing ability, the CNN model presents a prediction MSE of 7.60. The present results also demonstrate that more accurate predictions will be achieved when using in-processing data. Hence, the prediction accuracy of data-driven models can be further improved on top of advancing in-processing monitoring systems." @default.
- W4312995256 created "2023-01-05" @default.
- W4312995256 creator A5027856062 @default.
- W4312995256 creator A5034422993 @default.
- W4312995256 creator A5058609826 @default.
- W4312995256 creator A5059189164 @default.
- W4312995256 creator A5063771724 @default.
- W4312995256 date "2022-01-01" @default.
- W4312995256 modified "2023-09-30" @default.
- W4312995256 title "Profile prediction in ECM using machine learning" @default.
- W4312995256 cites W2003263748 @default.
- W4312995256 cites W2187012331 @default.
- W4312995256 cites W2593026044 @default.
- W4312995256 cites W2768753204 @default.
- W4312995256 cites W2794249437 @default.
- W4312995256 cites W2801602632 @default.
- W4312995256 cites W2911489611 @default.
- W4312995256 cites W2981236968 @default.
- W4312995256 cites W3025736319 @default.
- W4312995256 cites W3127596205 @default.
- W4312995256 doi "https://doi.org/10.1016/j.procir.2022.09.192" @default.
- W4312995256 hasPublicationYear "2022" @default.
- W4312995256 type Work @default.
- W4312995256 citedByCount "3" @default.
- W4312995256 countsByYear W43129952562023 @default.
- W4312995256 crossrefType "journal-article" @default.
- W4312995256 hasAuthorship W4312995256A5027856062 @default.
- W4312995256 hasAuthorship W4312995256A5034422993 @default.
- W4312995256 hasAuthorship W4312995256A5058609826 @default.
- W4312995256 hasAuthorship W4312995256A5059189164 @default.
- W4312995256 hasAuthorship W4312995256A5063771724 @default.
- W4312995256 hasBestOaLocation W43129952561 @default.
- W4312995256 hasConcept C11413529 @default.
- W4312995256 hasConcept C119599485 @default.
- W4312995256 hasConcept C119857082 @default.
- W4312995256 hasConcept C127413603 @default.
- W4312995256 hasConcept C135628077 @default.
- W4312995256 hasConcept C147789679 @default.
- W4312995256 hasConcept C154945302 @default.
- W4312995256 hasConcept C165801399 @default.
- W4312995256 hasConcept C17525397 @default.
- W4312995256 hasConcept C185592680 @default.
- W4312995256 hasConcept C24326235 @default.
- W4312995256 hasConcept C2777887233 @default.
- W4312995256 hasConcept C41008148 @default.
- W4312995256 hasConcept C45374587 @default.
- W4312995256 hasConcept C50644808 @default.
- W4312995256 hasConcept C523214423 @default.
- W4312995256 hasConcept C66938386 @default.
- W4312995256 hasConcept C68801617 @default.
- W4312995256 hasConcept C78519656 @default.
- W4312995256 hasConcept C81363708 @default.
- W4312995256 hasConceptScore W4312995256C11413529 @default.
- W4312995256 hasConceptScore W4312995256C119599485 @default.
- W4312995256 hasConceptScore W4312995256C119857082 @default.
- W4312995256 hasConceptScore W4312995256C127413603 @default.
- W4312995256 hasConceptScore W4312995256C135628077 @default.
- W4312995256 hasConceptScore W4312995256C147789679 @default.
- W4312995256 hasConceptScore W4312995256C154945302 @default.
- W4312995256 hasConceptScore W4312995256C165801399 @default.
- W4312995256 hasConceptScore W4312995256C17525397 @default.
- W4312995256 hasConceptScore W4312995256C185592680 @default.
- W4312995256 hasConceptScore W4312995256C24326235 @default.
- W4312995256 hasConceptScore W4312995256C2777887233 @default.
- W4312995256 hasConceptScore W4312995256C41008148 @default.
- W4312995256 hasConceptScore W4312995256C45374587 @default.
- W4312995256 hasConceptScore W4312995256C50644808 @default.
- W4312995256 hasConceptScore W4312995256C523214423 @default.
- W4312995256 hasConceptScore W4312995256C66938386 @default.
- W4312995256 hasConceptScore W4312995256C68801617 @default.
- W4312995256 hasConceptScore W4312995256C78519656 @default.
- W4312995256 hasConceptScore W4312995256C81363708 @default.
- W4312995256 hasLocation W43129952561 @default.
- W4312995256 hasLocation W43129952562 @default.
- W4312995256 hasOpenAccess W4312995256 @default.
- W4312995256 hasPrimaryLocation W43129952561 @default.
- W4312995256 hasRelatedWork W2037528360 @default.
- W4312995256 hasRelatedWork W2093690982 @default.
- W4312995256 hasRelatedWork W2349056726 @default.
- W4312995256 hasRelatedWork W2353224685 @default.
- W4312995256 hasRelatedWork W2380071827 @default.
- W4312995256 hasRelatedWork W3021430260 @default.
- W4312995256 hasRelatedWork W3027997911 @default.
- W4312995256 hasRelatedWork W4212919912 @default.
- W4312995256 hasRelatedWork W4287776258 @default.
- W4312995256 hasRelatedWork W85028759 @default.
- W4312995256 hasVolume "113" @default.
- W4312995256 isParatext "false" @default.
- W4312995256 isRetracted "false" @default.
- W4312995256 workType "article" @default.