Matches in SemOpenAlex for { <https://semopenalex.org/work/W2893866731> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W2893866731 abstract "In order to facilitate real-time monitoring of accumulated wellhead fatigue damage, it is necessary to measure the wellhead bending moment in real-time. This paper presents a novel method to estimate the wellhead bending moment in realtime using acceleration and inclination data from the motion reference unit (MRU) sensors installed on BOP and LRJ, riser tension data and a trained neural network model. The method proposed in this paper is designed with a Recursive Neural Network (RNN) model to be trained to estimate the wellhead bending moment in real-time with high accuracy based on motion MRU sensor data and riser tension time series of a few previous cycles. In addition to the power of modeling complex nonlinearities, RNNs provide the advantage of better capturing the dynamic effects by learning to recognize the patterns in the sensor data and riser tension time series. The RNN model is trained using virtual sensor data and wellhead bending moment from a finite element (FE) model of the drilling riser subjected to irregular wave time domain analyses based on a training matrix with limited number of significant height (Hs) and peak period (Tp) combinations. Once trained, tested and deployed, the RNN model can make real-time estimation of the wellhead bending moment based on MRU sensor data and riser tension time series. The RNN model can be an efficient and accurate alternative to a physical model based on the indirect method for real-time calculation of wellhead bending moment using real-time sensor data. A case study is presented to explain the training procedures for the RNN model. A set of test cases that are not included in the training dataset are used to demonstrate the accuracy of the RNN model using Root Mean Squared Error (RMSE), Normalized Root Mean Squared Error (NRMSE) and coefficient of determination (R2) as a metrics." @default.
- W2893866731 created "2018-10-05" @default.
- W2893866731 creator A5025309712 @default.
- W2893866731 creator A5051961999 @default.
- W2893866731 creator A5062305210 @default.
- W2893866731 creator A5085213521 @default.
- W2893866731 date "2018-06-17" @default.
- W2893866731 modified "2023-09-26" @default.
- W2893866731 title "Real-Time Wellhead Bending Moment Measurement Using Motion Reference Unit (MRU) Sensors and Machine Learning" @default.
- W2893866731 doi "https://doi.org/10.1115/omae2018-78301" @default.
- W2893866731 hasPublicationYear "2018" @default.
- W2893866731 type Work @default.
- W2893866731 sameAs 2893866731 @default.
- W2893866731 citedByCount "0" @default.
- W2893866731 crossrefType "proceedings-article" @default.
- W2893866731 hasAuthorship W2893866731A5025309712 @default.
- W2893866731 hasAuthorship W2893866731A5051961999 @default.
- W2893866731 hasAuthorship W2893866731A5062305210 @default.
- W2893866731 hasAuthorship W2893866731A5085213521 @default.
- W2893866731 hasConcept C104114177 @default.
- W2893866731 hasConcept C121332964 @default.
- W2893866731 hasConcept C127413603 @default.
- W2893866731 hasConcept C13280743 @default.
- W2893866731 hasConcept C154945302 @default.
- W2893866731 hasConcept C179254644 @default.
- W2893866731 hasConcept C205649164 @default.
- W2893866731 hasConcept C24890656 @default.
- W2893866731 hasConcept C2780424376 @default.
- W2893866731 hasConcept C31972630 @default.
- W2893866731 hasConcept C41008148 @default.
- W2893866731 hasConcept C74650414 @default.
- W2893866731 hasConcept C78519656 @default.
- W2893866731 hasConceptScore W2893866731C104114177 @default.
- W2893866731 hasConceptScore W2893866731C121332964 @default.
- W2893866731 hasConceptScore W2893866731C127413603 @default.
- W2893866731 hasConceptScore W2893866731C13280743 @default.
- W2893866731 hasConceptScore W2893866731C154945302 @default.
- W2893866731 hasConceptScore W2893866731C179254644 @default.
- W2893866731 hasConceptScore W2893866731C205649164 @default.
- W2893866731 hasConceptScore W2893866731C24890656 @default.
- W2893866731 hasConceptScore W2893866731C2780424376 @default.
- W2893866731 hasConceptScore W2893866731C31972630 @default.
- W2893866731 hasConceptScore W2893866731C41008148 @default.
- W2893866731 hasConceptScore W2893866731C74650414 @default.
- W2893866731 hasConceptScore W2893866731C78519656 @default.
- W2893866731 hasLocation W28938667311 @default.
- W2893866731 hasOpenAccess W2893866731 @default.
- W2893866731 hasPrimaryLocation W28938667311 @default.
- W2893866731 hasRelatedWork W1732761558 @default.
- W2893866731 hasRelatedWork W2028453184 @default.
- W2893866731 hasRelatedWork W2078310801 @default.
- W2893866731 hasRelatedWork W2079812322 @default.
- W2893866731 hasRelatedWork W2081325802 @default.
- W2893866731 hasRelatedWork W2092227721 @default.
- W2893866731 hasRelatedWork W2147727300 @default.
- W2893866731 hasRelatedWork W2212368729 @default.
- W2893866731 hasRelatedWork W2598998892 @default.
- W2893866731 hasRelatedWork W2768104711 @default.
- W2893866731 hasRelatedWork W2774670089 @default.
- W2893866731 hasRelatedWork W2783234330 @default.
- W2893866731 hasRelatedWork W2912999147 @default.
- W2893866731 hasRelatedWork W2996640484 @default.
- W2893866731 hasRelatedWork W3034925843 @default.
- W2893866731 hasRelatedWork W768281765 @default.
- W2893866731 hasRelatedWork W2820798990 @default.
- W2893866731 hasRelatedWork W2827906486 @default.
- W2893866731 hasRelatedWork W2968461039 @default.
- W2893866731 hasRelatedWork W3085650513 @default.
- W2893866731 isParatext "false" @default.
- W2893866731 isRetracted "false" @default.
- W2893866731 magId "2893866731" @default.
- W2893866731 workType "article" @default.