Newly Developed Correlations to Predict the Rheological Parameters of High-Bentonite Drilling Fluid Using Neural Networks

High-bentonite mud (HBM) is a water-based drilling fluid characterized by its remarkable improvement in cutting removal and hole cleaning efficiency. Periodic monitoring of the rheological properties of HBM is mandatory for optimizing the drilling operation. The objective of this study is to develop new sets of correlations using artificial neural network (ANN) to predict the rheological parameters of HBM while drilling using the frequent measurements, every 15 to 20 min, of mud density (MD) and Marsh funnel viscosity (FV). The ANN models were developed using 200 field data points. The dataset was divided into 70:30 ratios for training and testing the ANN models respectively. The optimized ANN models showed a significant match between the predicted and the measured rheological properties with a high correlation coefficient (R) higher than 0.90 and a maximum average absolute percentage error (AAPE) of 6%. New empirical correlations were extracted from the ANN models to estimate plastic viscosity (PV), yield point (YP), and apparent viscosity (AV) directly without running the models for easier and practical application. The results obtained from AV empirical correlation outperformed the previously published correlations in terms of R and AAPE.

Download Full-text

Development of New Models to Determine the Rheological Parameters of Water-based Drilling Fluid Using Artificial Intelligence

10.2118/204597-ms ◽

2021 ◽

Author(s):

Farqad Hadi ◽

Ali Noori ◽

Hussein Hussein ◽

Ameer Khudhair

Keyword(s):

Rheological Properties ◽

High Performance ◽

Drilling Fluid ◽

Gel Strength ◽

Solid Content ◽

Rheological Parameters ◽

Water Based ◽

Fluid Properties ◽

Drilling Operations ◽

Marsh Funnel

Abstract It is well known that drilling fluid is a key parameter for optimizing drilling operations, cleaning the hole, and managing the rig hydraulics and margins of surge and swab pressures. Although the experimental works present valid and reliable results, they are expensive and time consuming. On the other hand, continuous and regular determination of the rheological mud properties can perform its essential functions during well construction. More uncertainties in planning the drilling fluid properties meant that more challenges may be exposed during drilling operations. This study presents two predictive techniques, multiple regression analysis (MRA) and artificial neural networks (ANNs), to determine the rheological properties of water-based drilling fluid based on other simple measurable properties. While mud density (MW), marsh funnel (MF), and solid% are key input parameters in this study, the output functions or models are plastic viscosity (PV), yield point (YP), apparent viscosity (AV), and gel strength. The prediction methods were demonstrated by means of a field case in eastern Iraq, using datasets from daily drilling reports of two wells in addition to the laboratory measurements. To test the performance ability of the developed models, two error-based metrics (determination coefficient R2 and root mean square error RMSE) have been used in this study. The current results of this study support the evidence that MW, MF, and solid% are consistent indexes for the prediction of rheological properties. Both mud density and solid content have a relative-significant effect on increasing PV, YP, AV, and gel strength. However, a scattering around each fit curve is observed which proved that one rheological property alone is not sufficient to estimate other properties. The results also reveal that both MRA and ANN are conservative in estimating the fluid rheological properties, but ANN is more precise than MRA. Eight empirical mathematical models with high performance capacity have been developed in this study to determine the rheological fluid properties based on simple and quick equipment as mud balance and marsh funnel. This study presents cost-effective models to determine the rheological fluid properties for future well planning in Iraqi oil fields.

Download Full-text

Real-Time Determination of Rheological Properties of Spud Drilling Fluids Using a Hybrid Artificial Intelligence Technique

Journal of Energy Resources Technology ◽

10.1115/1.4042233 ◽

2019 ◽

Vol 141 (3) ◽

Cited By ~ 14

Author(s):

Khaled Abdelgawad ◽

Salaheldin Elkatatny ◽

Tamer Moussa ◽

Mohamed Mahmoud ◽

Shirish Patil

Keyword(s):

Rheological Properties ◽

Apparent Viscosity ◽

Drilling Fluid ◽

Differential Evolution Algorithm ◽

Percentage Error ◽

Drilling Fluids ◽

Rheological Parameter ◽

Ann Model ◽

Hole Cleaning ◽

Ann Models

The rheological properties of the drilling fluid play a key role in controlling the drilling operation. Knowledge of drilling fluid rheological properties is very crucial for drilling hydraulic calculations required for hole cleaning optimization. Measuring the rheological properties during drilling sometimes is a time-consuming process. Wrong estimation of these properties may lead to many problems, such as pipe sticking, loss of circulation, and/or well control issues. The aforementioned problems increase the non-productive time and the overall cost of the drilling operations. In this paper, the frequent drilling fluid measurements (mud density, Marsh funnel viscosity (MFV), and solid percent) are used to estimate the rheological properties of bentonite spud mud. Artificial neural network (ANN) technique was combined with the self-adaptive differential evolution algorithm (SaDe) to develop an optimum ANN model for each rheological property using 1029 data points. The SaDe helped to optimize the best combination of parameters for the ANN models. For the first time, based on the developed ANN models, empirical equations are extracted for each rheological parameter. The ANN models predicted the rheological properties from the mud density, MFV, and solid percent with high accuracy (average absolute percentage error (AAPE) less than 5% and correlation coefficient higher than 95%). The developed apparent viscosity model was compared with the available models in the literature using the unseen dataset. The SaDe-ANN model outperformed the other models which overestimated the apparent viscosity of the spud drilling fluid. The developed models will help drilling engineers to predict the rheological properties every 15–20 min. This will help to optimize hole cleaning and avoid pipe sticking and loss of circulation where bentonite spud mud is used. No additional equipment or special software is required for applying the new method.

Download Full-text

Hole-Cleaning Fibers Improve Cuttings-Carrying Capacity

Journal of Petroleum Technology ◽

10.2118/0521-0063-jpt ◽

2021 ◽

Vol 73 (05) ◽

pp. 63-64

Author(s):

Chris Carpenter

Keyword(s):

Flow Regime ◽

Carrying Capacity ◽

Rheological Model ◽

Drilling Fluid ◽

Test Method ◽

Abu Dhabi ◽

Rheological Parameters ◽

Cleaning Efficiency ◽

Hole Cleaning ◽

Drilling Operations

This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 203147, “Investigating Hole-Cleaning Fibers’ Mechanism To Improve Cutting Carrying Capacity and Comparing Their Effectiveness With Common Polymeric Pills,” by Mohammad Saeed Karimi Rad, Mojtaba Kalhor Mohammadi, SPE, and Kourosh Tahmasbi Nowtarki, International Drilling Fluids, prepared for the 2020 Abu Dhabi International Petroleum Exhibition and Conference, Abu Dhabi, held virtually 9–12 November. The paper has not been peer reviewed. Hole cleaning in deviated wells is more challenging than in vertical wells because of the boycott effect or the eccentricity of the drillpipe. Poor hole cleaning can result in problems such as borehole packoff or excessive equivalent circulating density. The complete paper investigates a specialized fibrous material (Fiber 1) for hole-cleaning characteristics. The primary goal is to identify significant mechanisms of hole-cleaning fibers and their merits compared with polymeric high-viscosity pills. Hole-Cleaning Indices Based on a review of the literature, most effective parameters regarding hole cleaning in different well types were investigated. These parameters can be classified into the following five categories: - Well design (e.g., hole angle, drillpipe eccentricity, well trajectory) - Drilling-fluid properties (e.g., gel strength, mud weight) - Formation properties (e.g., lithology, cutting specific gravity, cuttings size and shape) - Hydraulic optimizations (e.g., flow regime, nozzle size, number of nozzles) - Drilling practices (e.g., drillpipe rotation speed, wellbore tortuosity, bit type, rate of penetration, pump rate) In this research, rheological parameters and parameters of the Herschel-Bulkley rheological model are considered to be optimization inputs to increase hole-cleaning efficiency of commonly used pills in drilling operations. The complete paper offers a detailed discussion of both the importance of flow regime and the role of the Herschel-Bulkley rheological model in reaching a better prognosis of drilling-fluid behavior at low shear rates. The properties of the fibrous hole-cleaning agent used in the complete paper are provided in Table 1. Test Method Two series of tests were performed. The medium of the first series is drilling water, with the goal of evaluating the efficiency of Fiber 1 in fresh pills. The second series of tests was per-formed with a simple polymeric mud as a medium common in drilling operations. Formulations and rheological properties of both test series are provided in Tables 4 and 5 of the complete paper, respectively.

Download Full-text

Comparative Analysis of the Effect of Barite and Hematite on the Rheology of Water-Based Drilling Mud

10.53902/tpe.2021.01.000508 ◽

2021 ◽

Vol 1 (2) ◽

Author(s):

Osei H

Keyword(s):

Rheological Properties ◽

Drilling Fluid ◽

Attrition Rate ◽

Drilling Mud ◽

Cleaning Efficiency ◽

Drilling Operation ◽

Water Based ◽

Petroleum Resources ◽

Drilling Muds ◽

The Impact

High demand for oil and gas has led to exploration of more petroleum resources even at remote areas. The petroleum resources are found in deeper subsurface formations and drilling into such formations requires a well-designed drilling mud with suitable rheological properties in order to avoid or reduce associated drilling problems. This is because rheological properties of drilling muds have considerable effect on the drilling operation and cleaning of the wellbore. Mud engineers therefore use mud additives to influence the properties and functions of the drilling fluid to obtain the desired drilling mud properties especially rheological properties. This study investigated and compared the impact of barite and hematite as weighting agents for water-based drilling muds and their influence on the rheology. Water-based muds of different concentrations of weighting agents (5%, 10%, 15% and 20% of the total weight of the drilling mud) were prepared and their rheological properties determined at an ambient temperature of 24ᵒC to check their impact on drilling operation. The results found hematite to produce higher mud density, plastic viscosity, gel strength and yield point when compared to barite at the same weighting concentrations. The higher performance of the hematite-based muds might be attributed to it having higher specific gravity, better particle distribution and lower particle attrition rate and more importantly being free from contaminants. The water-based muds with hematite will therefore be more promising drilling muds with higher drilling and hole cleaning efficiency than those having barite.

Download Full-text

Data-Driven Framework to Predict the Rheological Properties of CaCl2 Brine-Based Drill-in Fluid Using Artificial Neural Network

Energies ◽

10.3390/en12101880 ◽

2019 ◽

Vol 12 (10) ◽

pp. 1880 ◽

Cited By ~ 4

Author(s):

Ahmed Gowida ◽

Salaheldin Elkatatny ◽

Emad Ramadan ◽

Abdulazeez Abdulraheem

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Rheological Properties ◽

Calcium Chloride ◽

Drilling Fluid ◽

Flow Behavior ◽

Percentage Error ◽

Flow Behavior Index ◽

Hole Cleaning ◽

Artificial Neural

Calcium chloride brine-based drill-in fluid is commonly used within the reservoir section, as it is specially formulated to maximize drilling experience, and to protect the reservoir from being damaged. Monitoring the drilling fluid rheology including plastic viscosity, P V , apparent viscosity, A V , yield point, Y p , flow behavior index, n , and flow consistency index, k , has great importance in evaluating hole cleaning and optimizing drilling hydraulics. Therefore, it is very crucial for the mud rheology to be checked periodically during drilling, in order to control its persistent change. Such properties are often measured in the field twice a day, and in practice, this takes a long time (2–3 h for taking measurements and cleaning the instruments). However, mud weight, M W , and Marsh funnel viscosity, M F , are periodically measured every 15–20 min. The objective of this study is to develop new models using artificial neural network, ANN, to predict the rheological properties of calcium chloride brine-based mud using M W and M F measurements then extract empirical correlations in a white-box mode to predict these properties based on M W and M F . Field measurements, 515 points, representing actual mud samples, were collected to build the proposed ANN models. The optimized parameters of these models resulted in highly accurate results indicated by a high correlation coefficient, R, between the predicted and measured values, which exceeded 0.97, with an average absolute percentage error, AAPE, that did not exceed 6.1%. Accordingly, the developed models are very useful for monitoring the mud rheology to optimize the drilling operation and avoid many problems such as hole cleaning issues, pipe sticking and loss of circulation.

Download Full-text

Potential of Neural Networks for Structural Damage Localization

10.36227/techrxiv.12672194.v1 ◽

2020 ◽

Author(s):

Abambres M ◽

Marcy M ◽

Doz G

Keyword(s):

Structural Damage ◽

Structural Engineering ◽

Dynamic Properties ◽

Structural Safety ◽

Damage Localization ◽

Proposed Model ◽

Data Points ◽

Ann Models ◽

Artificial Neural Network Ann

<p>Fabrication technology and structural engineering states-of-art have led to a growing use of slender structures, making them more susceptible to static and dynamic actions that may lead to some sort of damage. In this context, regular inspections and evaluations are necessary to detect and predict structural damage and establish maintenance actions able to guarantee structural safety and durability with minimal cost. However, these procedures are traditionally quite time-consuming and costly, and techniques allowing a more effective damage detection are necessary. This paper assesses the potential of Artificial Neural Network (ANN) models in the prediction of damage localization in structural members, as function of their dynamic properties – the three first natural frequencies are used. Based on 64 numerical examples from damaged (mostly) and undamaged steel channel beams, an ANN-based analytical model is proposed as a highly accurate and efficient damage localization estimator. The proposed model yielded maximum errors of 0.2 and 0.7 % concerning 64 numerical and 3 experimental data points, respectively. Due to the high-quality of results, authors’ next step is the application of similar approaches to entire structures, based on much larger datasets.</p>

Download Full-text

Modelling and Forecasting Inbound Tourism Demand to Croatia using Artificial Neural Networks: A Comparative Study

Journal of Tourism and Services ◽

10.29036/jots.v11i21.171 ◽

2020 ◽

Vol 11 (21) ◽

pp. 55-70

Author(s):

Murat Cuhadar

Keyword(s):

Demand Forecasting ◽

Tourism Industry ◽

Percentage Error ◽

Accurate Estimation ◽

Tourism Demand ◽

Tourist Flows ◽

Ann Models ◽

Optimal Forecasting ◽

Artificial Neural ◽

Artificial Neural Network Ann

Tourism demand is the basis on which all commercial decisions concerning tourism ultimately depend. Accurate estimation of tourism demand is essential for the tourism industry because it can help reduce risk and uncertainty as well as effectively provide basic information for better tourism planning. The purpose of this study is to develop the optimal forecasting model that yields the highest accuracy when compared to the forecast performances of three different methods, namely Artificial Neural Network (ANN), Exponential Smoothing, and Box-Jenkins methods for forecasting monthly inbound tourist flows to Croatia. Prior studies have been applied to forecast tourism demand to Croatia based on time series models and casual methods. However, the monthly and comparative tourism demand forecasting studies using ANNs are still limited, and this paper aims to fill this gap. The number of monthly foreign tourist arrivals to Croatia covers the period between January 2005-December 2019 data were used to build optimal forecasting models. Forecasting performances of the models were measured by Mean Absolute Percentage Error (MAPE) statistics. As a result of the experiments carried out, when compared to the forecasting performances of various models, 12 lagged ANN models, which have [4-3-1] architecture, were seen to perform best among all models applied in this study. Considering both the empirical findings obtained from this study and previous studies on tourism forecasting, it can be seen that ANN models that do not have any negativities (such as over-training, faulty architecture, etc.) produce successful forecasting results when compared with results generated by conventional statistical methods.

Download Full-text

Potential of neural networks for structural damage localization

Avances en Ciencias e Ingeniería ◽

10.18272/aci.v11i2.1305 ◽

2019 ◽

Vol 11 (2) ◽

Cited By ~ 3

Author(s):

Miguel Abambres ◽

Marilia Marcy ◽

Graciela Doz

Keyword(s):

Structural Damage ◽

Structural Engineering ◽

Dynamic Properties ◽

Structural Safety ◽

Damage Localization ◽

Proposed Model ◽

Data Points ◽

Ann Models ◽

Artificial Neural Network Ann

Fabrication technology and structural engineering states-of-art have led to a growing use of slender structures, making them more susceptible to static and dynamic actions that may lead to some sort of damage. In this context, regular inspections and evaluations are necessary to detect and predict structural damage and establish maintenance actions able to guarantee structural safety and durability with minimal cost. However, these procedures are traditionally quite time-consuming and costly, and techniques allowing a more effective damage detection are necessary. This paper assesses the potential of Artificial Neural Network (ANN) models in the prediction of damage localization in structural members, as function of their dynamic properties – the three first natural frequencies are used. Based on 64 numerical examples from damaged (mostly) and undamaged steel channel beams, an ANN-based analytical model is proposed as a highly accurate and efficient damage localization estimator. The proposed model yielded maximum errors of 0.2 and 0.7 % concerning 64 numerical and 3 experimental data points, respectively. Due to the high-quality of results, authors’ next step is the application of similar approaches to entire structures, based on much larger datasets.

Download Full-text

Incorporation of Fe3O4 Nanoparticles as Drilling Fluid Additives for Improved Drilling Operations

Volume 8: Polar and Arctic Sciences and Technology; Petroleum Technology ◽

10.1115/omae2016-54071 ◽

2016 ◽

Cited By ~ 8

Author(s):

Zisis Vryzas ◽

Omar Mahmoud ◽

Hisham Nasr-El-Din ◽

Vassilis Zaspalis ◽

Vassilios C. Kelessidis

Keyword(s):

Electron Microscope ◽

Rheological Properties ◽

Fe3o4 Nanoparticles ◽

Filter Cake ◽

Drilling Fluid ◽

Filter Press ◽

Rheological Parameters ◽

Fluid Loss ◽

Fluid System ◽

Custom Made

A successful drilling operation requires an effective drilling fluid system. Due to the variety of downhole conditions across the globe, the fluid system should be designed to meet complex challenges such as High-Pressure/High-Temperature (HPHT) environments, while promoting better productivity with a minimum interference for completion operations. This study aims to improve the rheological and fluid loss properties of water-bentonite suspensions by using both commercial (C-NP) and custom-made (CM-NP) iron oxide (Fe3O4) nanoparticles (NP) as drilling fluid additives. Superparamagnetic Fe3O4 NP were synthesized by the co-precipitation method. Both types of nanoparticles were characterized by a High Resolution Transmission Electron Microscope (TEM) and X-ray Diffraction (XRD). Base fluid (BF), made of deionized water and bentonite at 7wt%, was prepared according to American Petroleum Institute (API) procedures and nanoparticles were added at 0.5wt%. A Couette-type viscometer was used to analyze the rheological characteristics of these fluids at different shear rates and various temperatures (up to 158°F). The rheological parameters were obtained from analysis of viscometric data using non-linear regression. The API Low-Pressure/Low-Temperature (LPLT) and HPHT fluid filtrate volumes were measured, using a standard API LPLT static filter press (100 psi, 77°F) and an API HPHT filter press (300 psi, 250°F). Observation of the porous matrix morphology of the produced filter cakes was done with Scanning Electron Microscope (SEM). TEM showed that the mean diameter of the CM-NP was 7–8 nm, with measured surface areas between 100–250 m2/g. The C-NP had an average diameter of <50 nm, as per manufacturer specifications. The XRD of the CM-NP revealed peaks corresponding to pure crystallites of magnetite (Fe3O4) with no impurities. Rheological analysis showed very good fitting by the Herschel-Bulkley model with coefficient of determination (R2) greater than 0.99. Rheological properties of all samples were affected by higher temperatures, with increase in yield stress, decrease in flow consistency index (K) and slight increase in flow behavior index (n). Fluid filtration results indicated a decrease in the LPLT fluid loss and an increase in the filter cake thickness compared to the BF upon addition of higher concentrations of C-NP, because of a decrease in filter cake permeability. At HPHT conditions, samples with 0.5wt% C-NP had a smaller fluid loss by 34.3%, compared to 11.9% at LPLT conditions. CM-NP exhibited even higher reduction in the fluid loss at HPHT conditions of 40%. Such drilling fluids can solve difficult drilling problems and aid in achieving the reservoir’s highest potential by eliminating the use of aggressive, potentially damaging chemicals. Exploitation of the synergistic interaction of the utilized components can produce a water-based system with excellent fluid loss characteristics while maintaining optimal rheological properties.

Download Full-text

Estimation of semolina dough rheological parameters by inversion of a finite elements model

Journal of Agricultural Engineering ◽

10.4081/jae.2015.469 ◽

2015 ◽

Vol 46 (3) ◽

pp. 95

Author(s):

Angelo Fabbri ◽

Chiara Cevoli

Keyword(s):

Finite Elements ◽

Rheological Properties ◽

Inverse Method ◽

Rheological Parameters ◽

Percentage Error ◽

Food Material ◽

Food Engineering ◽

Traditional Procedure ◽

The Difference ◽

Finite Elements Model

The description of the rheological properties of food material plays an important role in food engineering. Particularly for the optimisation of pasta manufacturing process (extrusion) is needful to know the rheological properties of semolina dough. Unfortunately characterisation of non-Newtonian fluids, such as food doughs, requires a notable time effort, especially in terms of number of tests to be carried out. The present work proposes an alternative method, based on the combination of laboratory measurement, made with a simplified tool, with the inversion of a finite elements numerical model. To determine the rheological parameters, an objective function, defined as the distance between simulation and experimental data, was considered and the well-known Levenberg-Marqard optimisation algorithm was used. In order to verify the feasibility of the method, the rheological characterisation of the dough was carried also by a traditional procedure. Results shown that the difference between measurements of rheological parameters of the semolina dough made with traditional procedure and inverse methods are very small (maximum percentage error equal to 3.6%). This agreement supports the coherence of the inverse method that, in general, may be used to characterise many non-Newtonian materials.

Download Full-text