Dynamic Well Bottom-Hole Flowing Pressure Prediction Based on Radial Basis Neural Network

Memon, Paras Q.; Yong, Suet-Peng; Pao, William; Pau, Jion Sean

doi:10.1007/978-3-319-14654-6_17

Cited by 6 publications

(6 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They have been successfully applied in several research fields of petroleum engineering to solve various problems, for example, reservoir characterisation, forecasting, risk analysis, history matching, uncertainty analysis, optimisation, production strategy selection, among others. The authors [3,69] present more application of ANNs in the oil and gas industry.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

“…The difficulty in the application of ANNs as a reservoir simulator proxy is for them to be fully trained, which requires a large number of reservoir simulation runs [61]. Otherwise, ANNs have the benefit over other conventional techniques, such as response surface and reduced models, to perform complex and highly non-linear inputs and outputs accurately and rapidly [69]. According to [137], ANNs offer some advantages, including their capacity of inferring highly complex, nonlinear, and possibly uncertain relationships between system variables, requiring practically zero prior knowledge regarding the unknown function.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Development of proxy models for petroleum reservoir simulation: a systematic literature review and state-of-the-art

Silva¹,

Avansi²,

Schiozer³

2020

IJAERS

View full text Add to dashboard Cite

Proxy models are derived mathematical functions developed as substitutes for reservoir flow simulators. Several types of proxy models are reported in the literature, for instance, response surface models, surrogate models, or metamodels. These models are fast methods, recommended for their efficient response time to approximate model responses and, therefore, useful in the decision-making process related to reservoir management. These studies focus on modelling a limited set of factors, applications, and case studies of any technique. A systematic literature review (SLR) is performed to gather the aspects prompting the modelling of proxy models in the literature and state-of-the-art. For this, a set of search keywords with appropriate string were utilised to extract the most important studies that satisfied all the criteria defined and classified under journal and conference paper categories. The papers were condensed after removing redundancy, repetition and similarity through a sequential and iterative process. From the analysis carried out, several gaps were identified, especially during the proxy model construction. Proxy models have already been discussed in petroleum engineering as a representation of the real system of reservoir flow simulator software. However, the proxy model response is faster but has yet to establish the issues of uncertainty in the outputs. There is a need for the integration of fast methods and reservoir simulators which can improve and accelerate results within acceptance criteria and accuracy in decisionmaking processes related to reservoir management.

show abstract

Section: Artificial Neural Networkmentioning

confidence: 99%

Section: Artificial Neural Networkmentioning

confidence: 99%

Development of proxy models for petroleum reservoir simulation: a systematic literature review and state-of-the-art

Silva¹,

Avansi²,

Schiozer³

2020

IJAERS

View full text Add to dashboard Cite

show abstract

“…Their findings indicated that this approach required fewer runs to achieve a global solution in comparison to the PSO algorithm. Memon et al (2014) investigated a surrogate reservoir model based on radial basis neural network (RBNN) in order to predict dynamic bottom-hole pressure in a multilayer reservoir under a set of production and injection constraints. The results reported that RBNN are powerful in replicating the same results as obtained by a dynamic reservoir simulation.…”

Section: Introductionmentioning

confidence: 99%

A field development strategy for the joint optimization of flow allocations, well placements and well trajectories

Dada

Mellal

Makhloufi

et al. 2020

Energy Exploration & Exploitation

View full text Add to dashboard Cite

One of the major goals that field planning engineers and decision makers have to achieve in terms of reservoir management and hydrocarbon recovery optimization is the maximization of return on financial investments. This task yet very challenging due to high number of decision variables and some uncertainties, pushes the engineers and technical advisors to seek for robust optimization methods in order to optimally place wells in the most profitable locations with a focus on increasing the net-present value over a project life-cycle. The quest to deliver a good quality advice is also dependent on how some uncertainties – geologic, economic and flow patterns – have been handled and formulated all along the optimization process. With the enhancement of computer power and the advent of remarkable optimization techniques, the oil and gas industry has at hand a wide range of tools to get an overview on value maximization from petroleum assets. Amongst these tools, genetic algorithms which belong to stochastic optimization methods have become well known in the industry as one the best alternatives to apply when trying to solve well placement and production allocation problems, though computationally demanding. The aim of this work is to present a novel approach in the area of hydrocarbon production optimization where control settings and well placement are to be determined based on a single objective function, in addition to the optimization of wells’ trajectories. Starting from a reservoir dynamic model of a synthetic offshore oil field assisted by water injection, the work consisted in building a data-driven model that was generated using artificial neural networks. Then, we used Matlab’s genetic algorithm toolbox to perform all the needed optimizations; from which, we were able to establish a drilling schedule for the set of wells to be realized, and we made it possible to simultaneously get the well location and configuration (vertical or horizontal), well type (producer or injector), well length, well orientation – in the horizontal plane –, as well as well controls (flow rates) and near wellbore pressure with respect to a set of linear and nonlinear-constraints. These constraints were formulated so as to reproduce real field development considerations, and with the aid of a genetic algorithm procedure written upon Matlab, we were able to satisfy those constraints such as, maximum production and injection rates, optimal wellbore pressures, maximum allowable liquid processing capacity, optimal well locations, wells’ drilling and completion maximum duration, in addition to other considerations. We have investigated some scenarios with the intention of proving the benefits of development strategy that we have chosen to study. It was found the chosen scenario could improve NPV by 3 folds in comparison to a base case scenario. The positioning of the wells was successful as all producers were placed in zones having initial water saturation less than 0.4., and all injectors were placed high water saturation zones. Moreover, we established a procedure regarding well trajectory design and optimization by taking into account, minimum dogleg severity and maximum duration for a well to be drilled and completed with respect to a time threshold. The findings as well as the workflow that will be presented hereafter could be considered as a guideline for subsequent tasks pertaining to the process of decision making, especially when it has to do with the development of green oil and gas fields and will certainly help in the placement of wells in less risky and cost-effective locations.

show abstract

“…Their objective was to test several optimization algorithms to optimize ANN parameters and then compare their results with conventional methods in oil and gas industry. Memon et al (2015) created dynamic well surrogate reservoir models (SRM) to predict flowing well bottom-hole pressure using radial basis function neural network (RBF). The input data of their model were porosity and permeability of different layers in SRM and production rate.…”

Section: Introductionmentioning

confidence: 99%

“…Firstly, previous CI research studies predicted the FBHP using laboratory-dependent inputs, so the first objective is to identify the real-time input parameters that are readily available on the surface to estimate the real-time FBHP with good accuracy. Secondly, previous researchers (Osman et al 2005;Davies and Aggrey 2007;Jahanandish et al 2011;Al-Shammari 2011;Adebayo et al 2013;Bello and Asafa 2014;Memon et al 2014Memon et al , 2015Li et al 2014;Ayoub et al 2015;Ebrahimi and Khamehchi 2015;Awadalla and Yousef 2016;Chen et al 2017) proposed a black box type of CI models. In all these papers, authors only mentioned the approach they have used to train their models.…”

Section: Introductionmentioning

confidence: 99%

Real-time prognosis of flowing bottom-hole pressure in a vertical well for a multiphase flow using computational intelligence techniques

Tariq

Mahmoud

Abdulraheem

2019

J Petrol Explor Prod Technol

View full text Add to dashboard Cite

An accurate prediction of well flowing bottom-hole pressure (FBHP) is highly needed in petroleum engineering applications such as for the field production optimization, cost per barrel of oil reduction, and quantification of workover remedial operations. A good number of empirical correlations and mechanistic models exist in the literature and are frequently used in oil industry to estimate FBHP. But majority of the empirical models were developed under a laboratory scale and are therefore inaccurate when scaled up for the field applications. The objective of this study is to present a new computational intelligence-based model to predict FBHP for a naturally flowing vertical well with multiphase flow. The present study shows that the accuracy of FBHP estimation using PSO-ANN is better than the conventional ANN model. A small average absolute percentage error of less than 2.1% is observed with the proposed model, while comparing the previous empirical correlations and mechanistic models on the same data gives more than 15% error. The new model is trained on a surface production data, which makes the prediction of FBHP in a real time. A group trend analysis tests were also carried out to assure that the proposed model is accurately capturing the underline physics behind the problem.

show abstract

Dynamic Well Bottom-Hole Flowing Pressure Prediction Based on Radial Basis Neural Network

Cited by 6 publications

References 29 publications

Development of proxy models for petroleum reservoir simulation: a systematic literature review and state-of-the-art

Development of proxy models for petroleum reservoir simulation: a systematic literature review and state-of-the-art

A field development strategy for the joint optimization of flow allocations, well placements and well trajectories

Real-time prognosis of flowing bottom-hole pressure in a vertical well for a multiphase flow using computational intelligence techniques

Contact Info

Product

Resources

About