Layer | Fill | Outline |
---|
Map layers
Theme | Visible | Selectable | Appearance | Zoom Range (now: 0) |
---|
Fill | Stroke |
---|---|
Collaborating Authors
Search analysis: production test
Production Optimization Using Integrated Modelling and ESP Survival Analysis Based on Historical Data
Sindi, Wisam (DNO ASA, Oslo, Norway / Department Petroleum Engineering, Montanuniversität Leoben, Leoben, Styria, Austria) | Fruhwirth, Rudolf (Department Petroleum Engineering, Montanuniversität Leoben, Leoben, Styria, Austria) | Gamsjäger, Ernst (Chair of Mechanics, Montanuniversität Leoben, Leoben, Styria, Austria) | Hofstätter, Herbert (Department Petroleum Engineering, Montanuniversität Leoben, Leoben, Styria, Austria)
...2 SPE-216990-MS production model is validated by comparison with field data. Abnormal ESP behavior is predicted correctly in t...on months in advance, facilitating wellworkover preparation and minimizing unnecessary downtime and production loss. This capability leads to significant cost savings. Besides failure prediction, the analytical... production model calculates parameters along the wellbore that can greatly assist in identifying ...
...m, and R.A. Johnson. 1993. "Determining pump wear and remaining life from electric submersible pump test curves." SPE ...Production and Facilities...
...SPE-216990-MS Production Optimization Using Integrated Modelling and ESP Survival Analysis Based on Historical Data Wisam ...resents an integrated approach to model the entire wellbore-ESP system, allowing the computation of production rates and the assessment of equipment health for failure prediction. Historical data logs from two ... used to validate the work and develop a failure detection process using machine learning (ML). The production model utilizes Nodal Analysis, encompassing multiphase flow and accounting for slip and flow patter...
Abstract Most oil wells are converted to artificial lift, such as an electrical submersible pump (ESP), at some point in their lifecycle due to reservoir pressure depletion. This paper presents an integrated approach to model the entire wellbore-ESP system, allowing the computation of production rates and the assessment of equipment health for failure prediction. Historical data logs from two Middle East fields, operating about 100 instrumented wells, are used to validate the work and develop a failure detection process using machine learning (ML). The production model utilizes Nodal Analysis, encompassing multiphase flow and accounting for slip and flow pattern, to determine the in-situ density used for computing the pressure traverse. The temperature traverse is computed from transient heat transfer between the wellbore and formation. Affinity laws are used to describe the ESP performance. Feature selection methods, including the Pearson correlation, Sequential Forward Selection, and Backward Elimination, are employed to determine the most important features. Feedforward neural networks with fully connected (dense) layers are trained on manually labeled subsets of measured and calculated parameters to detect operational statuses, including anomalies. The identified statuses entail pump off, normal operation, electrical wear (including harmonics stemming from poor power supply), and mechanical wear. An analysis is performed for about 20 failure cases from the historical data by reviewing Pull Out Of Hole (POOH) reports, Dismantle, Inspection, and Failure Analysis (DIFA) reports, Teardown Analysis reports, as well as historical high-density field measurements. The observed failure modes include shaft breakage and electrical failure at the ESP cable, the cable penetrator, the Motor Lead Extension (MLE), and any splices located in the system. The root causes of the failures are motor overheating, hydraulically induced mechanical load peaks, degradation of insulation of electrical conductors, and voltage harmonic distortions stemming from poor power supply quality. Using the presented methodology, it is possible to detect wear at the onset, allowing for the prediction of failures like shaft breakage months in advance. The integrated production model is validated by comparison with field data. Abnormal ESP behavior is predicted correctly in the early stage of development with more than 99% accuracy. Data science tools enable the detection of equipment degradation months in advance, facilitating well-workover preparation and minimizing unnecessary downtime and production loss. This capability leads to significant cost savings. Besides failure prediction, the analytical production model calculates parameters along the wellbore that can greatly assist in identifying production problems, such as flow pattern and in-situ along the wellbore parameters, including the black oil model properties. Integrated modeling fills information gaps between rate measurement and serves as a verification tool of physical metering. Combining continuous production surveillance with predictive maintenance leads to reduced production deferment, improved allocation, and better well and reservoir management (WRM). The pump failure prediction methodology can easily be extended to other operational conditions, such as motor overheating situations. The methodology can be integrated into a digital oilfield (DOF) or digital twin process.
- North America > United States (0.93)
- Europe > Austria > Styria (0.16)
...SPE-214967-MS Revisiting Time-Rate-Pressure Production Analysis -- Where Are We Almost 40 Years Later? T. A. Blasingame, Department of Petroleum Enginee...ain conspicuous acknowledgment of SPE copyright. Abstract In the mid-1980s "time-rate-pressure" production analysis was proposed by this author to estimate reservoir properties, as well as in-situ volumes a...asual and the experienced user that by whatever name we call it -- Well Performance Analysis (WPA), Production Analysis (PA), or Rate Transient Analysis (RTA) -- the purpose of these methodologies is to provide...
... variable-rate/variable pressure drop field data. 1973/80 Fetkovich Seminal work in the analysis of production rates using a prescribed reservoir model (the "Decline Curve Analysis using Type Curves" approach)...applications, in particular, the "West Virginia Well A" tight gas case, which became a standard for production data analysis methods for gas wells. 1988 Blasingame and Lee Adaptation of the variable-rate/variab...
... This work provides appropriate definitions and derivations, as well as application cases for both production and injection operations. This work arose from the need for a fractured well model in the portfolio... the "multiwell" material balance time function must be formulated in terms of the field cumulative production and the well ...production rate for applications in multiwell reservoirs. 2002 Bondar and Blasingame Auxiliary application of ...
Abstract In the mid-1980s "time-rate-pressure" production analysis was proposed by this author to estimate reservoir properties, as well as in-situ volumes and EUR. This approach was primarily applied to conventional and tight reservoirs using "material balance decline curves" in the early 1990s and became known as "Well Performance Analysis" (WPA) before being rebranded by a vendor as "Rate Transient Analysis" (RTA) in the early 2000's. This analysis has been extended beyond fixed models (e.g., type curves for an unfractured or fractured well in a simple closed reservoir (e.g., a circle)) into analytical models for almost any case, as well as using numerical models for virtually any well reservoir configuration and complex multiphase fluid flow. The "RTA" methodology has become a mainstay of modern reservoir engineering, but deserves a "look-back" and a "look-forward" in terms of where we can best utilize new modelling approaches (physical and data-defined models) to improve diagnostics and analyses. The primary goal of this work is to emphasize to both the casual and the experienced user that by whatever name we call it — Well Performance Analysis (WPA), Production Analysis (PA), or Rate Transient Analysis (RTA) — the purpose of these methodologies is to provide a diagnostically-driven analysis and interpretation of time-rate-pressure (TPR) data. WPA/PA/RTA are not just data fitting exercises, nor are they limited to simplified analyses (e.g., some sort of straight-line plots), these are fully integrated data diagnostic and analysis tools that warrant care and attention. The present push to provide automated/augmented analyses is actually a noble (and predictable) outcome of the methodologies developed in the 1980s to provide estimates of reservoir properties from data that were not being used for that purpose, but as we develop more comprehensive (and more complex) analyses for TPR data, we must acknowledge that these data are inherently affected by operational aspects as well as measurement capabilities. In short, these are just data, and we need to stay focused on the diagnostic value of the data before attempting any analyses and interpretations — no matter how simple or complex those analyses and interpretations may be.
- North America > United States > Texas > Permian Basin > Yeso Formation (0.99)
- North America > United States > Texas > Permian Basin > Yates Formation (0.99)
- North America > United States > Texas > Permian Basin > Wolfcamp Formation (0.99)
- (22 more...)
- Reservoir Description and Dynamics > Formation Evaluation & Management > Well performance, inflow performance (1.00)
- Reservoir Description and Dynamics > Formation Evaluation & Management > Production forecasting (1.00)
- Reservoir Description and Dynamics > Formation Evaluation & Management > Pressure transient analysis (1.00)
- Reservoir Description and Dynamics > Formation Evaluation & Management > Drillstem/well testing (1.00)
...alysis. Pressure tools must be kept in a high-temperature environment for long periods of time, and production intervals are frequently very small portions of overall well depth. ...Production intervals, which are usually associated with fracture zones, may be at substantially different ther...uctivity of a well prior to completion, injectivity testing is perhaps the most useful kind of well test. In contrast with a ...
Characterizing geothermal reservoirs draws on techniques common to petroleum reservoirs. Key differences create special challenges to gaining a good understanding of geothermal reservoirs. This article covers appropriate approaches and caveats for well testing, drawdown/buildup analyses and decline curve analysis for characterizing geothermal reservoirs. Geothermal well testing is similar in many respects to transient pressure testing of oil/gas wells, with some significant differences. Many geothermal wells induce boiling in the near-well reservoir, giving rise to temperature transients as well as pressure transients. Substantial phase change may also take place in the well, further complicating analysis. Pressure tools must be kept in a high-temperature environment for long periods of time, and production intervals are frequently very small portions of overall well depth. Production intervals, which are usually associated with fracture zones, may be at substantially different thermodynamic conditions.
- Energy > Renewable > Geothermal > Geothermal Resource (1.00)
- Energy > Oil & Gas > Upstream (1.00)
- Information Technology > Knowledge Management (0.40)
- Information Technology > Communications > Collaboration (0.40)
...hange design criteria / load case classification from normal operating to extreme connected but non-production scenarios. Reduce internal pressure from the maximum value used down to the actual values obser...
...ght polyethylene). The material properties for steel and the polymer are defined based on available test data and material datasheets. The coiled tubing material model is based on the stress-strain curve ...for the pipe from test data. Figure 6--Injector-CT Local Model A range of load cases are assessed for the local model. T...
Abstract Coiled tubing (CT) is being increasingly used in open water mode for offshore light well intervention such as subsea hydraulic pumping applications. Traditionally coiled tubing has been popular in land based intervention applications; whereas for offshore applications using a CT deployed through a riser (in-riser mode) is very common. However more recently, light well intervention (LWI) operations with CT deployed in open water mode are gaining traction due to improved efficiencies compared to traditional intervention methods. Coiled tubing systems are an integral part of a LWI system and are used for injection and hydraulic pumping operations. In open water mode coiled tubing pipe is susceptible to direct hydrodynamic loading from waves and currents and vessel motions. The strength response and fatigue performance of the coiled tubing pipe can severely limit operability and increase down time for these operations when compared to riser based operations. In this paper we will present a case study where coiled tubing has been used for LWI and subsea pumping operations. The paper will highlight some of the key challenges in design and operation of open water mode CT systems for offshore applications, from a loading standpoint and will also discuss challenges arising from lack of industry standards and codes. Analysis methodology and outcomes from this study will be presented to demonstrate how the CT strength response limits operations. Multiple mitigation options that were used to enhance operability will be discussed: these include judicious use of operational parameters, field measurement based environmental data and pipe depressurization to attain feasibility in harsh environments. In addition, modeling refinements based on 3 Dimensional (3D) Finite Element Analysis (FEA) of the CT injector guides and strain based design criteria will be discussed. The paper will include recommendations based on experience from these case studies and highlight the need for a common industry standard to better assist Operators and OEMs with future designs.
...3 Points Worth Pondering * 5.4 Resources and Reserves Models * 5.5 Points Worth Pondering * 5.6 Production Forecasts * 6 Engineering and Geoscientific Issues-Avoiding Pitfalls of Deterministic Models * 6...lications of Technologies Monte Carlo simulation models include capital costs, reserve estimates, production forecasts, and cash flow. One application of each type is discussed in enough detail inSec. 10.5 so...statistics become formalized with pioneers like Galton (percentiles, eugenics), Pearson (chi-square test, standard deviation, skewness, correlation) and Spearman (rank correlation, applications in social ...
The oil and gas industry invests money and other resources in projects with highly uncertain outcomes. We drill complex wells and build gas plants, refineries, platforms, and pipelines where costly problems can occur and where associated revenues might be disappointing. We may lose our investment; we may make a handsome profit. We are in a risky business. Assessing the outcomes, assigning probabilities of occurrence and associated values, is how we analyze and prepare to manage risk.
- Europe > United Kingdom (1.00)
- North America > United States > Texas (0.94)
- Asia > Middle East (0.92)
- South America (0.67)
- Research Report > Experimental Study (0.67)
- Overview (0.67)
- Research Report > New Finding (0.45)
- South America > Venezuela (0.99)
- Europe > United Kingdom > North Sea > Northern North Sea > Brent Formation (0.99)
- Asia > Middle East > Turkey > Zonguldak Basin (0.99)
- Africa > Cameroon > Gulf of Guinea > Rio Del Ray Basin > Etinde Block > IF Field (0.99)
Reducing NPT Using a Novel Approach to Real-Time Drilling Data Analysis
Wang, Junzhe (University of Tulsa, Tulsa, Oklahoma, United States) | Sajeev, Shyam Kareepadath (BP, Houston, Texas, United States) | Ozbayoglu, Evren (University of Tulsa, Tulsa, Oklahoma, United States) | Baldino, Silvio (University of Tulsa, Tulsa, Oklahoma, United States) | Liu, Yaxin (University of Tulsa, Tulsa, Oklahoma, United States) | Jing, Haorong (University of Tulsa, Tulsa, Oklahoma, United States)
...s in drilling operations can have severe consequences, such as equipment failure, safety risks, and production delays. Real-time detection and characterization of drilling anomalous events play a crucial role i...nge of similar sophisticated data prediction and anomaly detection models spanning across drilling, production, and reservoir engineering domains. (Huang et al. 2023, Li et al 2023, Liu et al. 2023a, 2023b, Kan...
... published by Equinor (2018). It encompasses a wide range of information, including reservoir data, production data, real-time drilling data, and more. The original real-time drilling data in the Volve dataset ...
...2:48:53). In this research, we divided each dataset into three subsets: training, validation, and test datasets. The distribution percentages used were 70%, 10%, and 20%, respectively (Figure 8). This a... that we have sufficient data for model training, validation to fine-tune the model, and a separate test set for unbiased evaluation of model performance...
Abstract Early detection and characterization of anomalous events during drilling operations are critical to avoid costly downtime and prevent hazardous events, such as a stuck pipe or a well control event. A key aspect of real-time drilling data analysis is the capability to make precise predictions of specific drilling parameters based on past time series information. The ideal models should be able to deal with multivariate time series and perform multi-step predictions. The recurrent neural network with a long short-term memory (LSTM) architecture is capable of the task, however, given that drilling is a long process with high data sampling frequency, LSTMs may face challenges with ultra-long-term memory. The transformer-based deep learning model has demonstrated its superior ability in natural language processing and time series analysis. The self-attention mechanism enables it to capture extremely long-term memory. In this paper, transformer-based deep learning models have been developed and applied to real-time drilling data prediction. It comprises an encoder and decoder module, along with a multi-head attention module. The model takes in multivariate real-time drilling data as input and predicts a univariate parameter in advance for multiple time steps. The proposed model is applied to the Volve field data to predict real-time drilling parameters such as mud pit volume, surface torque, and standpipe pressure. The predicted results are observed and evaluated. The predictions of the proposed models are in good agreement with the ground truth data. Four Transformer-based predictive models demonstrate their applicability to forecast real-time drilling data of different lengths. Transformer models utilizing non-stationary attention exhibit superior prediction accuracy in the context of drilling data prediction. This study provides guidance on how to implement and apply transformer-based deep learning models applied to drilling data analysis tasks, with a specific focus on anomaly detection. When trained on dysfunction-free datasets, the proposed model can predict real-time drilling data with high precision, whereas when a downhole anomaly starts to build, the significant error in the prediction can be used as an alarm indicator. The model can consider extremely long-term memory and serve as the alternative algorithm to LSTM. Furthermore, this model can be extended to a wide range of sequence data prediction problems in the petroleum engineering discipline.
- Asia (0.93)
- North America > United States > Texas (0.47)
- Europe > Norway > North Sea > Central North Sea (0.25)
- Europe > Norway > North Sea > Central North Sea > South Viking Graben > PL 046 > Block 15/9 > Volve Field > Shetland Group > Åsgard Formation (0.99)
- Europe > Norway > North Sea > Central North Sea > South Viking Graben > PL 046 > Block 15/9 > Volve Field > Shetland Group > Svarte Formation (0.99)
- Europe > Norway > North Sea > Central North Sea > South Viking Graben > PL 046 > Block 15/9 > Volve Field > Shetland Group > Sleipner Formation (0.99)
- (17 more...)
Improving 4D Seismic History Matching Through Data Analysis; A Localised Sensitivity Analysis Workflow
Kolajoobi, R. A. (Institute of Geoenergy Engineering, Heriot-Watt University, Edinburgh, Scotland) | MacBeth, C. (Institute of Geoenergy Engineering, Heriot-Watt University, Edinburgh, Scotland) | Landa, J. (Institute of Geoenergy Engineering, Heriot-Watt University, Edinburgh, Scotland)
... 4D seismic history matching (4D SHM) uses 4D seismic data to calibrate reservoir models to reduce production forecast uncertainty and improve reservoir surveillance. 4D seismic becomes very valuable in field ...urations and high areal uncertainty, such as offshore and carbon sequestration projects. Unlike the production data, the conventional uncertainty and sensitivity analysis (SA) with 4D seismic data might return ...
...d missing the important parameters for 4D SHM, hence, improving the reservoir model quality and the production forecasts. Introduction Reservoir flow simulation models are the main tools for reservoir manag...ervoir model parameters are usually constrained by prior geological knowledge, 3D Seismic, and well production measurements, however, the wells are sparsely located over the field and despite having a high temp...uch uncertainty remains in the reservoir flow simulation model even after history matching the well production data. Seismic data deliver valuable areal information about the field which becomes particularly im...
...sible parameter values, and then updating these model parameters using the assimilated data such as production, pressure, and seismic data. This process involves calculating the likelihood of the observed data ...
Abstract 4D seismic history matching (4D SHM) uses 4D seismic data to calibrate reservoir models to reduce production forecast uncertainty and improve reservoir surveillance. 4D seismic becomes very valuable in field developments with sparse well configurations and high areal uncertainty, such as offshore and carbon sequestration projects. Unlike the production data, the conventional uncertainty and sensitivity analysis (SA) with 4D seismic data might return misleading results. Due to the smooth nature of 4D seismic data, it is highly likely that the effects of different model parameters overlap, and low-frequency signals mask the high-frequency signals. Consequently, some significant parameters are wrongly excluded from the 4D SHM process. Our work aims to address this issue by localising the SA of 4D seismic data. The idea is first to identify specific seismic signals on the seismic maps and then perform the SA only at the individual locations rather than the entire map. This way we overcome the overlapping effects of different input parameters. Several approaches to localise the SA are utilized. In one approach we defined sliding windows to scan the seismic maps and then executed an SA inside the windows at each location. Other localisation approaches employ dimensionality reduction and feature extraction tools. We used principal component analysis (PCA) and advanced machine learning (ML) methods such as autoencoders (AE) and variational autoencoders (VAE) to transform the 4D seismic maps into a latent space. The information content (the 4D seismic signals) in the high-dimensional 4D seismic maps is represented by a few features in the latent space. Implementing an SA for each feature in the latent space is equivalent to performing SA with the seismic signals in the original map. The localised SA scheme is coupled with the Ensemble Smoother with Multiple Data Assimilation (ESMAD) algorithm to carry out 4D SHM. Three 4D SHM scenarios were defined: full parameterisation with no SA, conventional SA analysis using the entire map, and localised SA. We ran these scenarios for a complex synthetic reservoir model based on a real field in the North Sea to match to 4D P-wave seismic impedance. The results confirmed the superiority of the localised SA scenario which returned the final ensemble with the lowest error and the best match among the three scenarios. It also turned out that the PCA, for this specific case, is the most suitable methodology to localise the SA. A novel SA workflow for 4D seismic was proposed to select a better set of parameters for 4D SHM. It relies on ML and data analysis solutions to localise the SA and avoid missing the important parameters for 4D SHM, hence, improving the reservoir model quality and the production forecasts.
- North America > United States (0.46)
- Europe > United Kingdom > North Sea (0.25)
- Europe > Norway > North Sea (0.25)
- (2 more...)
- Geophysics > Time-Lapse Surveying > Time-Lapse Seismic Surveying (1.00)
- Geophysics > Seismic Surveying (1.00)
...odels include: * Capital costs/authority for expenditure (AFE) development * Reserve estimates * Production forecasts and cash flow Design of uncertainty models A proper start in risk analysis requires in...tics became formalized with pioneers like: * Galton (percentiles, eugenics) * Pearson (chi-square test, standard deviation, skewness, correlation) * Spearman (rank correlation, applications in social s...AAPG) and Society of Petroleum Engineers (SPE) often emphasized exploration. Oddly, cost models and production forecasting were often given short shrift or treated trivially. By the early 1990s, however, while ...
The oil and gas industry invests significant money and other resources in projects with highly uncertain outcomes. We drill complex wells and build gas plants, refineries, platforms, and pipelines where costly problems can occur and where associated revenues might be disappointing. We may lose our investment; we may make a handsome profit. We are in a risky business. Assessing the outcomes, assigning probabilities of occurrence and associated values, is how we analyze and prepare to manage risk.