Early Anomaly Detection Model Using Random Forest while Drilling Horizontal Wells with a Real Case Study

2021 ◽  
Author(s):  
Ahmed AlSaihati ◽  
Salaheldin Elkatatny ◽  
Ahmed Mahmoud ◽  
Abdulazeez Abdulraheem
Keyword(s):  
Random Forest ◽  
Horizontal Section ◽  
Detection Model ◽  
Actual Observation ◽  
Load Rate ◽  
Weight On Bit ◽  
D Values ◽  
Normal Trend ◽  
Metric Distance ◽  
Operational Issues

Abstract There has been discrepancy between the pre-calculated and actual T&D values, because of the dependence of the model’s predictability on assumed inputs. Therefore, to have a reliable model, the users must adjust the model inputs; mainly friction coefficient in order to match the actual T&D. This, however, can mask downhole conditions such as cutting beds, tight holes and sticking tendencies. This paper aims to introduce a machine learning model to predict the continuous profile of the surface drilling torque to detect the operational issues in advance. Actual data of Well-1, starting from the time of drilling a 5-7/8-inch horizontal section until one day prior to the stuck pipe event, was used to train and test a random forest (RF) model with an 80/20 split ratio, to predict the surface drilling torque. The input variables for the model are the drilling surface parameters, namely: flow rate, hook load, rate of penetration, rotary speed, standpipe pressure, and weight-on-bit. The developed model was used to predict the surface drilling torque, which represents the normal trend for the last day leading up to the stuck pipe incident in Well-1. Then the model was integrated with a multivariate metric distance, Mahalanobis, to be used as a classifier to measure how close an actual observation is from the predictive normal trend. Based on a pre-determined threshold, each actual observation was labeled as "NORMAL" or "ANOMAL".

Use of Machine Learning and Data Analytics to Detect Downhole Abnormalities While Drilling Horizontal Wells, With Real Case Study

2020 ◽  
Vol 143 (4) ◽  
Author(s):  
Ahmed Alsaihati ◽  
Salaheldin Elkatatny ◽  
Ahmed Abdulhamid Mahmoud ◽  
Abdulazeez Abdulraheem
Keyword(s):  
Oil And Gas ◽  
Intelligent System ◽  
Oil And Gas Industry ◽  
Absolute Error ◽  
Horizontal Section ◽  
Actual Observation ◽  
Weight On Bit ◽  
D Values ◽  
Metric Distance ◽  
Classification Tool

Abstract The standard torque and drag (T&D) modeling programs have been extensively used in the oil and gas industry to predict and monitor the T&D forces. In the majority of cases, there has been variability in the accuracy between the pre-calculated (based on a T&D model) and actual T&D values, because of the dependence of the model’s predictability on guessed inputs (matching parameters) which may not be correctly predicted. Therefore, to have a reliable model, program users must alter the model inputs and mainly the friction coefficient to match the actual T&D. This, however, can conceal downhole conditions such as cutting beds, tight holes, and sticking tendencies. The objective of this study is to develop an intelligent machine to predict the continuous profile of the surface drilling torque to enable the detection of operational problems ahead of time. This paper details the development and evaluation of an intelligent system that could promote safer operation and extend the response time limit to prevent undesired events. Actual field data of Well-1, starting from the time of drilling a 5-7/8-in. horizontal section until 1 day prior to the stuck pipe incident, were used to train and test three models: random forest, artificial neural network, and functional network, with an 80/20 training-to-testing data ratio, to predict the surface drilling torque. The independent variables for the model are the drilling surface parameters, namely: flow rate (Q), hook load (HL), rate of penetration (ROP), rotary speed (RS), standpipe pressure (SPP), and weight-on-bit (WOB). The prediction capability of the models was evaluated in terms of correlation of coefficient (R) and average absolute error percentage (AAPE). The model with the highest R and lowest AAPE was selected to continue with the analysis to detect downhole abnormalities. The best-developed model was used to predict the surface drilling torque on the last day leading up to the incident in Well-1, which represents the normal and healthy trend. Then, the model was coupled with a multivariate metric distance called “Mahalanobis” to be used as a classification tool to measure how close an actual observation is to the predictive normal and healthy trend. Based on a pre-determined threshold, each actual observation was labeled “NORMAL” or “ANOMAL.” Well-2 with a stuck pipe incident was used to assess the capability of the developed system in detecting downhole abnormalities. The results showed that in Well-1, where a stuck pipe incident was reported, a continuous alarm was detected by the developed system 9 h before the drilling crew observed any abnormality, while the alarm was detected 7 h prior to any observation by the crew in Well-2. The developed intelligent system could help the drilling crew to detect downhole abnormalities in real-time, react, and take corrective action to mitigate the problem promptly.

Drilling Dynamics, Mechanical Specific Energy Data Help Drill Record Extended-Reach Well

2021 ◽  
Vol 73 (05) ◽  
pp. 59-60
Author(s):  
Chris Carpenter
Keyword(s):  
Specific Energy ◽  
Response Times ◽  
Oil Field ◽  
Abu Dhabi ◽  
Horizontal Section ◽  
Horizontal Drilling ◽  
Actual Weight ◽  
Mechanical Specific Energy ◽  
Weight On Bit ◽  
Extended Reach Well

This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 203335, “Using MSE and Downhole Drilling Dynamics in Achieving a Record Extended-Reach Well Offshore Abu Dhabi,” by Nashat Abbas and Jamal Al Nokhatha, ADNOC, and Luis Salgado, Halliburton, et al., 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. Complex extended-reach-drilling (ERD) wells often present challenges with regard to geological aspects of data requirement and transmittal, reactive geosteering response times, and accuracy of well placement. Such scenarios may require innovative approaches in Middle East carbonate reservoirs. The objective of the complete paper is to illustrate that, by assessing the details of reservoir geology and key operational markers relevant for best practices, drilling approaches can be customized for each reservoir or scenario. Reservoir Background and Geology The planned reservoir section is a single horizontal of approximately 25,000-ft lateral length at a spacing of 250 m from adjacent injectors. The well was drilled from an artificial island. Field A, a shallow-water oil field, is the second-largest offshore field and the fourth-largest field in the world. Horizontal drilling was introduced in 1989, and an extensive drilling campaign has been implemented since then using steerable drilling technologies. This study is concerned only with wells drilled to develop Reservoir B in Field A, which contributes to the main part of initial oil in place and production. The thick limestone reservoir is subdivided into six porous layers, labeled from shallow to deep as A, B, C, D, E, and F. Each porous layer is separated by thin, low-porosity stylolites. The reservoir sublayer B, consisting of approximately 18-ft-thick calcareous limestones, was selected as the target zone for the 25,420-ft horizontal section. ERD, constructed on artificial islands, began on 2014 with a measured depth (MD)/true vertical depth (TVD) ratio approaching 2.2:1 or 2.4:1. A recent ERD well, Well A, was drilled at the beginning of 2020 with a MD/TVD ratio of 5:1. This value is a clear indication of progressively increasing challenges since the start of the project. Mechanical specific energy (MSE) has long been used to evaluate and enhance the rate of penetration (ROP); however, its use as an optimization tool in ERD wells has not been equally significant. This may have been mostly because of historical use of surface-measured parameters, which do not necessarily indicate the energy required to destroy the rock, particularly in ERD wells. Using optimization tools as part of the bottomhole assembly (BHA) downhole close to the bit provides actual weight-on-bit (WOB) and torque-on-bit (TOB) applied to the drilling bit to destroy the rock and, thus, results in more-representative MSE measurements to optimize drilling parameters and ROP in ERD wells.

scholarly journals Emerging Approach for Detection of Financial Frauds Using Machine Learning

2021 ◽  
pp. 9-22
Author(s):  
Upasana Mukherjee ◽  
Vandana Thakkar ◽  
Shawni Dutta ◽  
Utsab Mukherjee ◽  
Samir Kumar Bandyopadhyay
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Decision Tree ◽  
Credit Card ◽  
Fraud Detection ◽  
Loan Default ◽  
Credit Card Fraud ◽  
Detection Model ◽  
Default Prediction ◽  
Automated Process

The growth of regularly generated data from many financial activities has significant implications for every corner of financial modelling. This study has investigated the utilization of these continuous growing data by a means of an automated process. The automated process can be developed by using Machine learning based techniques that analyze the data and gain experience from the underlying data. Different important domains of financial fields such as Credit card fraud detection, bankruptcy detection, loan default prediction, investment prediction, marketing and many more can be modelled by implementing machine learning methods. Among several machine learning based techniques, the use of parametric and non-parametric based methods are approached by this research. Two parametric models namely Logistic Regression, Gaussian Naive Bayes models and two non-parametric methods such as Random Forest, Decision Tree are implemented in this paper. All the mentioned models are developed and implemented in the field of Credit card fraud detection, bankruptcy detection, loan default prediction. In each of the aforementioned cases, the comparative study among the classification techniques is drawn and the best model is identified. The performance of each classifier on each considered domain is evaluated by various performance metrics such as accuracy, F1-score and mean squared error. In the credit card fraud detection model the decision tree classifier performs the best with an accuracy of 99.1% and, in the loan default prediction and bankruptcy detection model, the random forest classifier gives the best accuracy of  97% and 96.84% respectively.

scholarly journals Development of Bot Detection Applications on Twitter Social Media Using Machine Learning with a Random Forest Classifier Algorithm

2020 ◽  
Vol 4 (2) ◽  
pp. 66
Author(s):  
Aqilah Aini Zahra ◽  
Widyawan Widyawan ◽  
Silmi Fauziati
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Social Order ◽  
Web Application ◽  
Negative Influence ◽  
Random Forest Classifier ◽  
Training Data ◽  
Feature Sets ◽  
Detection Model ◽  
Bot Detection

A Twitter bot is a Twitter account programmed to automatically do social activities by sending tweets through a scheduling program. Some bots intend to disseminate useful information such as earthquake and weather information. However, not a few bots have a negative influence, such as broadcasting false news, spam, or become a follower to increase an account's popularity. It can change public sentiments about an issue, decrease user confidence, or even change the social order. Therefore, an application is needed to distinguish between a bot and non-bot accounts. Based on these problems, this paper develops bot detection systems using machine learning for multiclass classification. These classes include human classes, informative, spammers, and fake followers. The model training used guided methods based on labeled training data. First, a dataset of 2,333 accounts was pre-processed to obtain 28 feature sets for classification. This feature set came from analysis of user profiles, temporal analysis, and analysis of tweets with numeric values. Afterward, the data was partitioned, normalized with scaling, and a random forest classifier algorithm was implemented on the data. After that, the features were reselected into 17 feature sets to obtain the highest accuracy achieved by the model. In the evaluation stage, bot detection models generated an accuracy of 96.79%, 97% precision, 96% recall, and an f-1 score of 96%. Therefore, the detection model was classified as having high accuracy. The bot detection model that had been completed was then implemented on the website and deployed to the cloud. In the end, this machine learning-based web application could be accessed and used by the public to detect Twitter bots.

Sign in / Sign up

Export Citation Format

Share Document