A Real-Time Friction Prediction Model for in Service Drill String Based on Machine Learning Methods Coupling with Mechanical Mechanism Analysis

2021 ◽  
Author(s):  
Huijuan Guo ◽  
Huaidong Luo ◽  
Guodong Zhan ◽  
Baodong Wang ◽  
Shuo Zhu
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Horizontal Wells ◽  
Drill String ◽  
Mechanism Analysis ◽  
Analysis Model ◽  
Machine Learning Methods ◽  
Weight On Bit ◽  
Friction Prediction ◽  
Independent Parameters

Abstract With highly deviated wells and horizontal wells are widely used in the oil industry. The large slope well sections and long horizontal well sections will lead to a sharp increase of the drill string torque and friction, which may reduce the drilling efficiency, and even lead to accidents. Therefore, real-time and accurate analysis of drill string’s torque and friction is an urgent problem facing by the modern drilling technology. The paper established a real-time friction prediction model that combines machine learning methods with drill string mechanical mechanism analysis model. Based on 84000 sets of field monitoring data obtained on-site, a regular data training set for weight on bit (WOB) and torque prediction was constructed with 23 types of time-series related parameters and 10 types of timing independent parameters. Relationships between time-series related parameters and timing independent parameters with the weight on bit and torque were trained to utilize long and short-term memory (LSTM) neural network and muti-layer back propagation (BP) network respectively. The new developed LSTM-BP neural network achieves high-precision prediction results of WOB and torque with a relative error of less than 14%. Based on derived WOB and torque prediction results, a theoretical mechanical analysis model of the entire drill string was adopted in this paper to develop the quantitative relation between WOB and torque with the friction coefficient of the drill string and oil casing. Suitable friction coefficients along the drill string can be finally obtained by solving the equilibrium function between predicted WOB, torque and measured hook load, rotary-table torque via an iteration algorithm. A case study was performed finally using the proposed intelligent analysis method to calculate the friction coefficients. This proposed methodology can be referenced to decrease the sticking risks and improve the drilling efficiency, which can finally increase the extension limit of horizontal wells in complex strata.

Real-Time Software to Estimate Friction Coefficient and Downhole Weight on Bit During Drilling of Horizontal Wells

2014 ◽  
Author(s):  
Mazeda Tahmeen ◽  
Geir Hareland ◽  
Bernt S. Aadnoy
Keyword(s):  
Friction Coefficient ◽  
Real Time ◽  
Information Transfer ◽  
Horizontal Wells ◽  
Drill String ◽  
Surface Measurement ◽  
Drilling Process ◽  
Drilling Data ◽  
Weight On Bit ◽  
Drag Analysis

The increasing complexity and higher drilling cost of horizontal wells demand extensive research on software development for the analysis of drilling data in real-time. In extended reach drilling, the downhole weight on bit (WOB) differs from the surface seen WOB (obtained from on an off bottom hookload difference reading) due to the friction caused by drill string movement and rotation in the wellbore. The torque and drag analysis module of a user-friendly real-time software, Intelligent Drilling Advisory system (IDAs) can estimate friction coefficient and the effective downhole WOB while drilling. IDAs uses a 3-dimensional wellbore friction model for the analysis. Based on this model the forces applied on a drill string element are buoyed weight, axial tension, friction force and normal force perpendicular to the contact surface of the wellbore. The industry standard protocol, WITSML (Wellsite Information Transfer Standard Markup Language) is used to conduct transfer of drilling data between IDAs and the onsite or remote WITSML drilling data server. IDAs retrieves real-time drilling data such as surface hookload, pump pressure, rotary RPM and surface WOB from the data servers. The survey data measurement for azimuth and inclination versus depth along with the retrieved drilling data, are used to do the analysis in different drilling modes, such as lowering or tripping in and drilling. For extensive analysis the software can investigate the sensitivity of friction coefficient and downhole WOB on user-defined drill string element lengths. The torque and drag analysis module, as well as the real-time software, IDAs has been successfully tested and verified with field data from horizontal wells drilled in Western Canada. In the lowering mode of drilling process, the software estimates the overall friction coefficient when the drill bit is off bottom. The downhole WOB estimated by the software is less than the surface measurement that the drillers used during drilling. The study revealed verification of the software by comparing the estimated downhole WOB with the downhole WOB recorded using a downhole measuring tool.

scholarly journals Multiclass ECG Signal Analysis Using Global Average-Based 2-D Convolutional Neural Network Modeling

Electronics ◽  
2021 ◽  
Vol 10 (2) ◽  
pp. 170
Author(s):  
Muhammad Wasimuddin ◽  
Khaled Elleithy ◽  
Abdelshakour Abuzneid ◽  
Miad Faezipour ◽  
Omar Abuzaghleh
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Signal Analysis ◽  
Neural Network Modeling ◽  
Ecg Signal ◽  
Analysis Model ◽  
Learning Methods ◽  
Machine Learning Methods

Cardiovascular diseases have been reported to be the leading cause of mortality across the globe. Among such diseases, Myocardial Infarction (MI), also known as “heart attack”, is of main interest among researchers, as its early diagnosis can prevent life threatening cardiac conditions and potentially save human lives. Analyzing the Electrocardiogram (ECG) can provide valuable diagnostic information to detect different types of cardiac arrhythmia. Real-time ECG monitoring systems with advanced machine learning methods provide information about the health status in real-time and have improved user’s experience. However, advanced machine learning methods have put a burden on portable and wearable devices due to their high computing requirements. We present an improved, less complex Convolutional Neural Network (CNN)-based classifier model that identifies multiple arrhythmia types using the two-dimensional image of the ECG wave in real-time. The proposed model is presented as a three-layer ECG signal analysis model that can potentially be adopted in real-time portable and wearable monitoring devices. We have designed, implemented, and simulated the proposed CNN network using Matlab. We also present the hardware implementation of the proposed method to validate its adaptability in real-time wearable systems. The European ST-T database recorded with single lead L3 is used to validate the CNN classifier and achieved an accuracy of 99.23%, outperforming most existing solutions.

scholarly journals Drilling Vibration Modes and Penetration Rate Modeling using Artificial Neural Network and Multiple Linear Regression Analysis in Khoman Formation at the Egyptian Western Desert

2021 ◽  
Author(s):  
Sherif A. Ezz ◽  
Mohamed S. Farahat ◽  
Said Kamel ◽  
Ahmed Z. Nouh
Keyword(s):  
Neural Network ◽  
Regression Analysis ◽  
Penetration Rate ◽  
Drill String ◽  
Western Desert ◽  
Circulation Rate ◽  
Vibration Level ◽  
Stick Slip ◽  
Weight On Bit ◽  
Rotary Speed

Abstract Drill string vibrations are one of the most serious problems encountered while drilling as the bit and drill string interaction with formations under certain drilling conditions usually induces complex shocks and vibrations into the drill string components resulting in premature failure of the equipment and reduced drilling penetration rate. In severe cases where shocks and vibrations accumulated into drill string till exceeded its maximum yield or torsional strength, fatigue will occur and thereby increase the field development costs associated with replacing damaged components, fishing jobs, lost-in-hole situations, and sidetracks. Thus, real-time monitoring for downhole generated vibrations and accordingly adjusting drilling parameters including weight on bit, rotary speed, and circulation rate play a vital role in reducing the severity of these undesirable conditions. Vibration optimization must be done incorporation with the penetration rate, as a minimum economical penetration rate is required by the operator. In this study, three penetration rate and vibration level models were developed for axial, lateral, and stick-slip drilling modes using both MATLAB™ Software neural network and multiple regression analysis. It is found that the three models' results for vibration level and penetration rate; as compared with those recorded drilling data; showed an excellent match within an acceptable error of average correlation coefficient (R) over 0.95. The prediction of penetration rate and vibration level is thoroughly investigated in different axial, lateral, and stick-slip vibration drilling modes to be able to best select the optimum safe drilling zone. It is found that the axial vibration could be dampened by gradually increasing the weight on bit and increasing rotary speed while both the lateral and torsional vibrations are enhanced by increasing the rotary speed and decreasing the weight on bit.

scholarly journals Mechanism Analysis of Roadway Rockbursts Induced by Dynamic Mining Loading and Its Application

Energies ◽  
2018 ◽  
Vol 11 (9) ◽  
pp. 2313 ◽  
Author(s):  
Zheng-yi Wang ◽  
Lin-ming Dou ◽  
Gui-feng Wang
Keyword(s):  
Real Time ◽  
Failure Process ◽  
Impact Resistance ◽  
Mechanism Analysis ◽  
Dynamic Failure ◽  
Analysis Model ◽  
Effective Prevention ◽  
Safety Production ◽  
Ultimate Resistance

Roadway rockbursts seriously restrict the safety production of coal mines; however, the interaction between dynamic loads and roadway surrounding rocks has not been fully considered in existing studies. A dynamic failure analysis model of anchoring supporting structures was established to analyze dynamic effects of stress waves. Taking a rockburst in LW402103 of the Hujiahe coal mine as the case, the theoretical model was well applied and verified. The static cumulative resistance Qs (210.5 kN) which was incurred by deformation of rocks provided the basis (81.93% in the overall real-time resistance Q) of dynamic failures. However, the additional impact resistance Qd (46.43 kN) brought about by the energy release in the failure process of elastic zones triggered impact failures. As a result, under conditions that the overall real-time resistance Q (256.93 kN) exceeded the ultimate resistance [Q] (250.8 kN), the dynamic failure of supports occurred. The in situ application was implemented by taking pressure-relief measures and parameter optimizations of roadway supports, which achieved an effective prevention of rockbursts.

scholarly journals Toward the use of neural networks for influenza prediction at multiple spatial resolutions

2021 ◽  
Vol 7 (25) ◽  
pp. eabb1237
Author(s):  
Emily L. Aiken ◽  
Andre T. Nguyen ◽  
Cecile Viboud ◽  
Mauricio Santillana
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Real Time ◽  
The United States ◽  
Network Approach ◽  
Internet Search ◽  
Learning Methods ◽  
Neural Network Approach ◽  
Machine Learning Methods ◽  
Search Data

Mitigating the effects of disease outbreaks with timely and effective interventions requires accurate real-time surveillance and forecasting of disease activity, but traditional health care–based surveillance systems are limited by inherent reporting delays. Machine learning methods have the potential to fill this temporal “data gap,” but work to date in this area has focused on relatively simple methods and coarse geographic resolutions (state level and above). We evaluate the predictive performance of a gated recurrent unit neural network approach in comparison with baseline machine learning methods for estimating influenza activity in the United States at the state and city levels and experiment with the inclusion of real-time Internet search data. We find that the neural network approach improves upon baseline models for long time horizons of prediction but is not improved by real-time internet search data. We conduct a thorough analysis of feature importances in all considered models for interpretability purposes.

scholarly journals Intelligent Prediction for Rock Porosity While Drilling Complex Lithology in Real Time

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Hany Gamal ◽  
Salaheldin Elkatatny ◽  
Ahmed Alsaihati ◽  
Abdulazeez Abdulraheem
Keyword(s):  
Real Time ◽  
Drill String ◽  
Coefficient Of Determination ◽  
Reservoir Modeling ◽  
Percentage Error ◽  
Reserve Estimation ◽  
Well Drilling ◽  
Rock Porosity ◽  
Weight On Bit ◽  
Data Points

Rock porosity is an important parameter for the formation evaluation, reservoir modeling, and petroleum reserve estimation. The conventional methods for determining the rock porosity are considered costly and time-consuming operations during the well drilling. This paper aims to predict the rock porosity in real time while drilling complex lithology using machine learning. In this paper, two intelligent models were developed utilizing the random forest (RF) and decision tree (DT) techniques. The drilling parameters include weight on bit, torque, standpipe pressure, drill string rotation speed, rate of penetration, and pump rate. Two datasets were employed for building the models (3767 data points) and for validating the developed models (1676 data points). Both collected datasets have complex lithology of carbonate, sandstone, and shale. Sensitivity and optimization on different parameters for each technique were conducted to ensure optimum prediction. The models’ performance was checked by four performance indices which are coefficient of determination (R2), average absolute percentage error (AAPE), variance account for (VAF), and a20 index. The results indicated the strong porosity prediction capability for the two models. DT model showed R2 of 0.94 and 0.87 between the predicted and actual porosity values with AAPE of 6.07 and 9% for training and testing, respectively. Generally, RF provided a higher level of strong prediction than DT as RF achieved R2 of 0.99 and 0.90 with AAPE of 1.5 and 7% for training and testing, respectively. The models’ validation proved a high prediction performance as DT achieved R2 of 0.88 and AAPE of 8.58%, while RF has R2 of 0.92 and AAPE of 6.5%.

Sign in / Sign up

Export Citation Format

Share Document