Data-driven soft sensor of downhole pressure for a gas-lift oil well

Teixeira, Bruno Otávio Soares; Castro, Walace S.; Teixeira, Anne Kayline Soares; Aguirre, Luís A.

doi:10.1016/j.conengprac.2013.09.005

Cited by 39 publications

(35 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the permanent downhole gauge (PDG) sensor failure often happens (Teixeira et al, 2014). Due to the difficulty in accessing the sensor installation site, soft-sensors are promising alternatives to monitor the downhole pressure when the sensor measurements are no longer available.…”

Section: Introductionmentioning

confidence: 99%

Downhole Pressure Estimation Using Committee Machines and Neural Networks

Barbosa¹,

Gomes²,

Teixeira³

et al. 2015

IFAC-PapersOnLine

Self Cite

View full text Add to dashboard Cite

In gas-lifted oil wells the monitoring of downhole pressure plays an important role. However, the permanent downhole gauge (PDG) sensor often fails. Because maintenance or replacement of PDGs is usually unfeasible, soft-sensors are promising alternatives to monitor the downhole pressure in the case of sensor failure. In this paper, a data-driven soft-sensor is implemented to estimate the downhole pressure using committee machines composed by finite impulse response (FIR) neural networks. Experimental results in three real datasets of the same oil well indicate that the identified soft-sensor is able to predict the downhole pressure with satisfactory accuracy. The model input variables were selected by statistical tests which increased insight concerning such variables. Committee machines outperformed single-model soft-sensors on experimental data.

show abstract

Section: Introductionmentioning

confidence: 99%

Downhole Pressure Estimation Using Committee Machines and Neural Networks

Barbosa¹,

Gomes²,

Teixeira³

et al. 2015

IFAC-PapersOnLine

Self Cite

View full text Add to dashboard Cite

show abstract

“…The desired target outputsŷ[n] are collected row-wise into a matrixŶ. The generated extended states are collected row-wise into a matrix X of size n s × (n r + n i + n o + 1) if using (1) or n s × n r if using (5).…”

Section: Trainingmentioning

confidence: 99%

“…An alternative is to use a tapped delay line with feedforward networks, which provides a finite window of past inputs, but provides no internal state for the network as the RNN does. Most models in literature use this last approach [5] or alternatively NARMAX models [6], since training an RNN with backpropagation-through-time is not trivial due to slow convergence properties and existence of bifurcations during training.…”

Section: Introductionmentioning

confidence: 99%

An Echo State Network-Based Soft Sensor of Downhole Pressure for a Gas-Lift Oil Well

Antonelo

Camponogara

2015

Engineering Applications of Neural Networks

View full text Add to dashboard Cite

Abstract.1 Soft sensor technology has been increasingly used in industry. Its importance is magnified when the process variable to be estimated is key to control and monitoring processes and the respective sensor either has a high probability of failure or is unreliable due to harsh environment conditions. This is the case for permanent downhole gauge (PDG) sensors in the oil and gas industry, which measure pressure and temperature in deepwater oil wells. In this paper, historical data obtained from an actual offshore oil well is used to build a black box model that estimates the PDG downhole pressure from platform variables, using Echo State Networks (ESNs), which are a class of recurrent networks with powerful modeling capabilities. These networks, differently from other neural networks models used by most soft sensors in literature, can model the nonlinear dynamical properties present in the noisy real-world data by using a two-layer structure with efficient training: a recurrent nonlinear layer with fixed randomly generated weights and a linear adaptive readout output layer. Experimental results show that ESNs are a promising technique to model soft sensors in an industrial setting.

show abstract

“…These predictive models, usually called soft-sensors, are important for quality control and production safety and have been extensively developed in the past decades [34]. Some of them use knowledge of the oil well physics [1] to design a nonlinear observer for the states of the multiphase flow in order to estimate the downhole pressure, while others are based on black-box system identification approaches [33,31]. While the first approach can take advantage of the a priori knowledge for a refined analysis and more advanced control schemes [12], the latter approach is quicker, does not require extensive modeling, being well suited to identify unknown models.…”

Section: Introductionmentioning

confidence: 99%

“…Much of the literature in system identification relies on the use of NARMAX models [8] or feedforward artificial neural networks (ANNs) with tapped delayed lines at the input layer [33] to account for dynamic behaviors or temporal processing. Although it is possible to introduce dynamics into the model using a time-window of previous inputs, a more interesting general way is to use Recurrent Neural Networks (RNNs) as universal approximators for dynamical systems [17].…”

Section: Introductionmentioning

confidence: 99%

Echo State Networks for data-driven downhole pressure estimation in gas-lift oil wells

Antonelo¹,

Camponogara²,

Foss

2017

Neural Networks

View full text Add to dashboard Cite

Process measurements are of vital importance for monitoring and control of industrial plants. When we consider offshore oil production platforms, wells that require gas-lift technology to yield oil production from low pressure oil reservoirs can become unstable under some conditions. This undesirable phenomenon is usually called slugging flow, and can be identified by an oscillatory behavior of the downhole pressure measurement. Given the importance of this measurement and the unreliability of the related sensor, this work aims at designing data-driven soft-sensors for downhole pressure estimation in two contexts: one for speeding up first-principle model simulation of a vertical riser model; and another for estimating the downhole pressure using real-world data from an oil well from Petrobras based only on topside platform measurements. Both tasks are tackled by employing Echo State Networks (ESN) as an efficient technique for training Recurrent Neural Networks. We show that a single ESN is capable of robustly modeling both the slugging flow behavior and a steady state based only on a square wave input signal representing the production choke opening in the vertical riser. Besides, we compare the performance of a standard network to the performance of a multiple timescale hierarchical architecture in the second task and show that the latter architecture performs better in modeling both large irregular transients and more commonly occurring small oscillations.

show abstract

Data-driven soft sensor of downhole pressure for a gas-lift oil well

Cited by 39 publications

References 24 publications

Downhole Pressure Estimation Using Committee Machines and Neural Networks

Downhole Pressure Estimation Using Committee Machines and Neural Networks

An Echo State Network-Based Soft Sensor of Downhole Pressure for a Gas-Lift Oil Well

Echo State Networks for data-driven downhole pressure estimation in gas-lift oil wells

Contact Info

Product

Resources

About