An uncertainty approach for Electric Submersible Pump modeling through Deep Neural Network
This work proposes a new methodology to identify and validate deep learning models for artificial oil lift systems that use submersible electric pumps. The proposed methodology allows for obtaining the models and evaluating the prediction's uncertainty jointly and systematically. The methodolog...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-01-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844024000781 |
| _version_ | 1797328706497150976 |
|---|---|
| author | Erbet Almeida Costa Carine de Menezes Rebello Vinicius Viena Santana Galdir Reges Tiago de Oliveira Silva Odilon Santana Luiz de Abreu Marcos Pellegrini Ribeiro Bernardo Pereira Foresti Marcio Fontana Idelfonso Bessa dos Reis Nogueira Leizer Schnitman |
| author_facet | Erbet Almeida Costa Carine de Menezes Rebello Vinicius Viena Santana Galdir Reges Tiago de Oliveira Silva Odilon Santana Luiz de Abreu Marcos Pellegrini Ribeiro Bernardo Pereira Foresti Marcio Fontana Idelfonso Bessa dos Reis Nogueira Leizer Schnitman |
| author_sort | Erbet Almeida Costa |
| collection | DOAJ |
| description | This work proposes a new methodology to identify and validate deep learning models for artificial oil lift systems that use submersible electric pumps. The proposed methodology allows for obtaining the models and evaluating the prediction's uncertainty jointly and systematically. The methodology employs a nonlinear model to generate training and validation data and the Markov Chain Monte Carlo algorithm to assess the neural network's epistemic uncertainty. The nonlinear model was used to overcome the limitations of the need for big datasets for training deep learning models. However, the developed models are validated against experimental data after training and validation with synthetic data. The validation is also performed through the models' uncertainty assessment and experimental data. From the implementation point of view, the method was coded in Python with Tensorflow and Keras libraries used to build the neural Networks and find the hyperparameters. The results show that the proposed methodology obtained models representing both the nonlinear model's dynamic behavior and the experimental data. It provides a most probable value close to the experimental data, and the uncertainty of the generated deep learning models has the same order of magnitude as that of the nonlinear model. This uncertainty assessment shows that the built models were adequately validated. The proposed deep learning models can be applied in several applications requiring a reliable and computationally lighter model. Hence, the obtained AI dynamic models can be employed for digital twin construction, control, and optimization. |
| first_indexed | 2024-03-08T06:55:33Z |
| format | Article |
| id | doaj.art-09f04835a6804cf0918d9f533cb0ce67 |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-03-08T06:55:33Z |
| publishDate | 2024-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-09f04835a6804cf0918d9f533cb0ce672024-02-03T06:36:07ZengElsevierHeliyon2405-84402024-01-01102e24047An uncertainty approach for Electric Submersible Pump modeling through Deep Neural NetworkErbet Almeida Costa0Carine de Menezes Rebello1Vinicius Viena Santana2Galdir Reges3Tiago de Oliveira Silva4Odilon Santana Luiz de Abreu5Marcos Pellegrini Ribeiro6Bernardo Pereira Foresti7Marcio Fontana8Idelfonso Bessa dos Reis Nogueira9Leizer Schnitman10Programa de pós-graduação em Mecatrônica, Universidade Federal da Bahia, Rua Prof. Aristides Novis, n 2., Salvador, 40210-630, Brazil; Chemical Engineering Department of the Norwegian University of Science and Technology, Gløshaugen, Trondheim, 7034, Norway; Corresponding author at: Chemical Engineering Department of the Norwegian University of Science and Technology, Gløshaugen, Trondheim, 7034, Norway.Chemical Engineering Department of the Norwegian University of Science and Technology, Gløshaugen, Trondheim, 7034, NorwayChemical Engineering Department of the Norwegian University of Science and Technology, Gløshaugen, Trondheim, 7034, NorwayPrograma de pós-graduação em Mecatrônica, Universidade Federal da Bahia, Rua Prof. Aristides Novis, n 2., Salvador, 40210-630, BrazilPrograma de pós-graduação em Mecatrônica, Universidade Federal da Bahia, Rua Prof. Aristides Novis, n 2., Salvador, 40210-630, BrazilPrograma de pós-graduação em Mecatrônica, Universidade Federal da Bahia, Rua Prof. Aristides Novis, n 2., Salvador, 40210-630, BrazilCENPES, Petrobras R&D Center, Brazil, Av. Horácio Macedo 950, Cid. Universitária, Ilha do Fundão, Rio de Janeiro, RJ, BrazilCENPES, Petrobras R&D Center, Brazil, Av. Horácio Macedo 950, Cid. Universitária, Ilha do Fundão, Rio de Janeiro, RJ, BrazilPrograma de pós-graduação em Mecatrônica, Universidade Federal da Bahia, Rua Prof. Aristides Novis, n 2., Salvador, 40210-630, BrazilChemical Engineering Department of the Norwegian University of Science and Technology, Gløshaugen, Trondheim, 7034, Norway; Principal corresponding author.Programa de pós-graduação em Mecatrônica, Universidade Federal da Bahia, Rua Prof. Aristides Novis, n 2., Salvador, 40210-630, BrazilThis work proposes a new methodology to identify and validate deep learning models for artificial oil lift systems that use submersible electric pumps. The proposed methodology allows for obtaining the models and evaluating the prediction's uncertainty jointly and systematically. The methodology employs a nonlinear model to generate training and validation data and the Markov Chain Monte Carlo algorithm to assess the neural network's epistemic uncertainty. The nonlinear model was used to overcome the limitations of the need for big datasets for training deep learning models. However, the developed models are validated against experimental data after training and validation with synthetic data. The validation is also performed through the models' uncertainty assessment and experimental data. From the implementation point of view, the method was coded in Python with Tensorflow and Keras libraries used to build the neural Networks and find the hyperparameters. The results show that the proposed methodology obtained models representing both the nonlinear model's dynamic behavior and the experimental data. It provides a most probable value close to the experimental data, and the uncertainty of the generated deep learning models has the same order of magnitude as that of the nonlinear model. This uncertainty assessment shows that the built models were adequately validated. The proposed deep learning models can be applied in several applications requiring a reliable and computationally lighter model. Hence, the obtained AI dynamic models can be employed for digital twin construction, control, and optimization.http://www.sciencedirect.com/science/article/pii/S2405844024000781Electric submersible pumpDeep neural networksUncertainty assessmentMCMC |
| spellingShingle | Erbet Almeida Costa Carine de Menezes Rebello Vinicius Viena Santana Galdir Reges Tiago de Oliveira Silva Odilon Santana Luiz de Abreu Marcos Pellegrini Ribeiro Bernardo Pereira Foresti Marcio Fontana Idelfonso Bessa dos Reis Nogueira Leizer Schnitman An uncertainty approach for Electric Submersible Pump modeling through Deep Neural Network Heliyon Electric submersible pump Deep neural networks Uncertainty assessment MCMC |
| title | An uncertainty approach for Electric Submersible Pump modeling through Deep Neural Network |
| title_full | An uncertainty approach for Electric Submersible Pump modeling through Deep Neural Network |
| title_fullStr | An uncertainty approach for Electric Submersible Pump modeling through Deep Neural Network |
| title_full_unstemmed | An uncertainty approach for Electric Submersible Pump modeling through Deep Neural Network |
| title_short | An uncertainty approach for Electric Submersible Pump modeling through Deep Neural Network |
| title_sort | uncertainty approach for electric submersible pump modeling through deep neural network |
| topic | Electric submersible pump Deep neural networks Uncertainty assessment MCMC |
| url | http://www.sciencedirect.com/science/article/pii/S2405844024000781 |
| work_keys_str_mv | AT erbetalmeidacosta anuncertaintyapproachforelectricsubmersiblepumpmodelingthroughdeepneuralnetwork AT carinedemenezesrebello anuncertaintyapproachforelectricsubmersiblepumpmodelingthroughdeepneuralnetwork AT viniciusvienasantana anuncertaintyapproachforelectricsubmersiblepumpmodelingthroughdeepneuralnetwork AT galdirreges anuncertaintyapproachforelectricsubmersiblepumpmodelingthroughdeepneuralnetwork AT tiagodeoliveirasilva anuncertaintyapproachforelectricsubmersiblepumpmodelingthroughdeepneuralnetwork AT odilonsantanaluizdeabreu anuncertaintyapproachforelectricsubmersiblepumpmodelingthroughdeepneuralnetwork AT marcospellegriniribeiro anuncertaintyapproachforelectricsubmersiblepumpmodelingthroughdeepneuralnetwork AT bernardopereiraforesti anuncertaintyapproachforelectricsubmersiblepumpmodelingthroughdeepneuralnetwork AT marciofontana anuncertaintyapproachforelectricsubmersiblepumpmodelingthroughdeepneuralnetwork AT idelfonsobessadosreisnogueira anuncertaintyapproachforelectricsubmersiblepumpmodelingthroughdeepneuralnetwork AT leizerschnitman anuncertaintyapproachforelectricsubmersiblepumpmodelingthroughdeepneuralnetwork AT erbetalmeidacosta uncertaintyapproachforelectricsubmersiblepumpmodelingthroughdeepneuralnetwork AT carinedemenezesrebello uncertaintyapproachforelectricsubmersiblepumpmodelingthroughdeepneuralnetwork AT viniciusvienasantana uncertaintyapproachforelectricsubmersiblepumpmodelingthroughdeepneuralnetwork AT galdirreges uncertaintyapproachforelectricsubmersiblepumpmodelingthroughdeepneuralnetwork AT tiagodeoliveirasilva uncertaintyapproachforelectricsubmersiblepumpmodelingthroughdeepneuralnetwork AT odilonsantanaluizdeabreu uncertaintyapproachforelectricsubmersiblepumpmodelingthroughdeepneuralnetwork AT marcospellegriniribeiro uncertaintyapproachforelectricsubmersiblepumpmodelingthroughdeepneuralnetwork AT bernardopereiraforesti uncertaintyapproachforelectricsubmersiblepumpmodelingthroughdeepneuralnetwork AT marciofontana uncertaintyapproachforelectricsubmersiblepumpmodelingthroughdeepneuralnetwork AT idelfonsobessadosreisnogueira uncertaintyapproachforelectricsubmersiblepumpmodelingthroughdeepneuralnetwork AT leizerschnitman uncertaintyapproachforelectricsubmersiblepumpmodelingthroughdeepneuralnetwork |