Development of soft sensors for permanent downhole Gauges in deepwater oil wells

Aguirre, Luís A.; Teixeira, Bruno Otávio Soares; Barbosa, Bruno Henrique Groenner; Teixeira, Anne Kayline Soares; Campos, Mário Cesar Mello Massa de; Mendes, Eduardo M. A. M.

doi:10.1016/j.conengprac.2017.06.002

Cited by 19 publications

(11 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Tais equipamentos citados neste paragrafo estão instalados na plataforma de produção offshore. Uma descrição mais detalhada sobre este processoé feita por (Aguirre et al, 2017…”

Section: Processounclassified

Detecção de falhas com Stacked Autoencoders e técnicas de reconhecimento de padrões em poços de petróleo operados por gas lift

Nascimento

Groenner

Vargas

et al. 2020

Anais Do Congresso Brasileiro De Automática 2020

View full text Add to dashboard Cite

A indústria offshore é responsável pela maior parte da produção de petróleo e gás no Brasil. Devido ao elevado nível de complexidade nessa indústria, ela vem sendo a precursora de novas tecnologias ao longo dos últimos anos. O presente trabalho tem como objetivo o desenvolvimento de um sistema para detecção de falhas em poços de produção de petróleo operados com elevação por gas lift. São utilizados autoencoders empilhados para redução de dimensionalidade e diferentes técnicas de reconhecimento de padrões, verificando métricas de desempenho dos modelos em observações reais de operação disponíveis. Após o desenvolvimento dos classificadores, obteve-se valores de recall elevado (boa parte superior a 0,98), o que mostra a grande aplicabilidade do sistema proposto em detectar falhas em poços de produção offshore.

show abstract

“…Tais equipamentos citados neste paragrafo estão instalados na plataforma de produção offshore. Uma descrição mais detalhada sobre este processoé feita por (Aguirre et al, 2017…”

Section: Processounclassified

Detecção de falhas com Stacked Autoencoders e técnicas de reconhecimento de padrões em poços de petróleo operados por gas lift

Nascimento

Groenner

Vargas

et al. 2020

Anais Do Congresso Brasileiro De Automática 2020

View full text Add to dashboard Cite

show abstract

“…To improve model generalizability, researchers have been studying this problem, but no universal scheme has emerged [8]. The artificial neural network (ANN) [9][10][11], support vector machine (SVM) [12][13][14], and deep learning [15,16] have been reported as modern mathematical methods to conduct the overall and regional analyses on data with multiple recognition stages, obtaining good generalization ability.…”

Section: Introductionmentioning

confidence: 99%

A Deep-Learning-Based Oil-Well-Testing Stage Interpretation Model Integrating Multi-Feature Extraction Methods

Feng

Ren

et al. 2020

Energies

View full text Add to dashboard Cite

The interpretation of well-testing data is a key means of decision-making support for oil and gas field development. However, conventional processing methods have many problems, such as the stochastic nature of the data, feature redundancies, the randomness of the initial weights or thresholds, and fluctuations in the generalization ability with slight changes in the network parameters. These result in a poor ability to characterize data features and a low generalization ability of the interpretation models. We propose a new integrated well-testing interpretation model based on a multi-feature extraction method and deep mutual information classifiers (MFE-DMIC). This model can avoid the low model classification accuracy caused by the simple training structures, lacking of redundancy elimination, and the non-optimal classifier configuration parameters. First, we obtained the initial features according to four classical feature extraction methods. Then, we eliminated feature redundancies using a deep belief network and united the maximum information coefficient method to achieve feature purification. Finally, we calculated the interpretation results using a hybrid particle swarm optimization–support vector machine classification system. We used 572 well-testing field samples, including five working stages, for model training and testing. The results show that the MFE-DMIC model had the highest total stage classification accuracy of 98.18% as well as the least of features (nine) compared with the classical feature extraction and classification methods and their combinations. The proposed model can reduce the efforts of oil analysts and allow accurate labeling of samples to be predicted.

show abstract

“…In this wise, the development of soft-sensors to estimate the downhole pressure has become a valuable alternative to provide this important information [8]. Basically, a soft-sensor is a predictive mathematical model that estimates some quantity based on measurements of other process variables [9,33].…”

Section: Introductionmentioning

confidence: 99%

“…It has been argued that the proper use of auxiliary information in the training of neural networks is beneficial in many practical ways [31]. The use of auxiliary information is the central feature of grey-box approaches [3] which have been used in several applications, including chemical processes [47], hydraulic systems [13,34], energy systems [45], fault detection [18], chaotic systems [39] and oil industry [8] to mention but a few.…”

Section: Introductionmentioning

confidence: 99%

Including steady-state information in nonlinear models: an application to the development of soft-sensors

Freitas¹,

Barbosa²,

Aguirre³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

When the dynamical data of a system only convey dynamic information over a limited operating range, the identification of models with good performance over a wider operating range is very unlikely. To overcome such a shortcoming, this paper describes a methodology to train models from dynamical data and steady-state information, which is assumed available. The novelty is that the procedure can be applied to models with rather complex structures such as multilayer perceptron neural networks in a bi-objective fashion without the need to compute fixed points neither analytically nor numerically. As a consequence, the required computing time is greatly reduced. The capabilities of the proposed method are explored in numerical examples and the development of soft-sensors for downhole pressure estimation for a real deep-water offshore oil well. The results indicate that the procedure yields suitable soft-sensors with good dynamical and static performance and, in the case of models that are nonlinear in the parameters, the gain in computation time is about three orders of magnitude considering existing approaches.

show abstract

Development of soft sensors for permanent downhole Gauges in deepwater oil wells

Cited by 19 publications

References 39 publications

Detecção de falhas com Stacked Autoencoders e técnicas de reconhecimento de padrões em poços de petróleo operados por gas lift

Detecção de falhas com Stacked Autoencoders e técnicas de reconhecimento de padrões em poços de petróleo operados por gas lift

A Deep-Learning-Based Oil-Well-Testing Stage Interpretation Model Integrating Multi-Feature Extraction Methods

Including steady-state information in nonlinear models: an application to the development of soft-sensors

Contact Info

Product

Resources

About