TY - BOOK

T1 - Mitigation of Non-productive Time Events by Continuously Monitoring the Drilling Parameters

AU - Elmgerbi, Asad

N1 - embargoed until 22-06-2028

PY - 2023

Y1 - 2023

N2 - Enhancing safety and minimizing the costs of drilling operations involves implementing measures to optimize the efficiency of the drilling process and minimize the impact of undesirable drilling events. To effectively implement these measures, it is necessary to focus on two interconnected areas: the improvement of surface measurements and the early detection of downhole drilling problems. Although current technology has made significant strides compared to the past, it still falls short in addressing these two aspects. To address this gap, this thesis proposes a comprehensive methodology that employs advanced sensor technology and artificial intelligence techniques to improve the detection of downhole drilling problems, reduce non-productive time, and enhance the operational safety and efficiency of drilling operations. The developed method focuses on three key areas to enable the successful real-time application of the ultimate goals of the methodology: a) evaluating the available sensors and determining the optimal locations for their installation within the rig structure to improve problem detection and drilling efficiency, b) assessing the use of the Internet of Things (IoT) for collecting, aggregating, and transmitting real-time sensor data to enable faster and more accurate decision-making, c) developing an autonomous and intelligent data analysis and diagnostic system to enhance the detection of symptoms, classification of incidents, and reduction of invisible downtime. The thesis is structured in three main parts. The ¿rst part covers state-of-the-art regarding flow measurement sensor technology and the methods of detecting downhole problems. The second part of the thesis discusses the development steps of the proposed drilling optimization and incident detection and classification models. In the third part, the detailed design of the large-scale lab prototype and the result of the conducted experiments are provided. The last part of this thesis discusses the suggested field scale design of the developed methodology. The empirical investigation of the developed methodology through case studies and experimental work demonstrated its success in improving drilling efficiency and the real-time detection and classification of impending downhole problems. These investigations showed that the methodology was highly effective at identifying and addressing potential issues as they arose, allowing for timely and efficient intervention. Overall, the success of the developed methodology in improving drilling efficiency and detecting and classifying impending downhole problems in real-time highlights its potential for practical application in the field.

AB - Enhancing safety and minimizing the costs of drilling operations involves implementing measures to optimize the efficiency of the drilling process and minimize the impact of undesirable drilling events. To effectively implement these measures, it is necessary to focus on two interconnected areas: the improvement of surface measurements and the early detection of downhole drilling problems. Although current technology has made significant strides compared to the past, it still falls short in addressing these two aspects. To address this gap, this thesis proposes a comprehensive methodology that employs advanced sensor technology and artificial intelligence techniques to improve the detection of downhole drilling problems, reduce non-productive time, and enhance the operational safety and efficiency of drilling operations. The developed method focuses on three key areas to enable the successful real-time application of the ultimate goals of the methodology: a) evaluating the available sensors and determining the optimal locations for their installation within the rig structure to improve problem detection and drilling efficiency, b) assessing the use of the Internet of Things (IoT) for collecting, aggregating, and transmitting real-time sensor data to enable faster and more accurate decision-making, c) developing an autonomous and intelligent data analysis and diagnostic system to enhance the detection of symptoms, classification of incidents, and reduction of invisible downtime. The thesis is structured in three main parts. The ¿rst part covers state-of-the-art regarding flow measurement sensor technology and the methods of detecting downhole problems. The second part of the thesis discusses the development steps of the proposed drilling optimization and incident detection and classification models. In the third part, the detailed design of the large-scale lab prototype and the result of the conducted experiments are provided. The last part of this thesis discusses the suggested field scale design of the developed methodology. The empirical investigation of the developed methodology through case studies and experimental work demonstrated its success in improving drilling efficiency and the real-time detection and classification of impending downhole problems. These investigations showed that the methodology was highly effective at identifying and addressing potential issues as they arose, allowing for timely and efficient intervention. Overall, the success of the developed methodology in improving drilling efficiency and detecting and classifying impending downhole problems in real-time highlights its potential for practical application in the field.

KW - Drilling non-productive time Drilling invisible lost time Real-Time Drilling hydraulic Optimization Real-Time Rate of Penetration Optimization Probabilistic Model Downhole Drilling Problem Identification Uncertainty Window internet-of-things (IoT)

KW - Drilling non-productive time Drilling invisible lost time Real-Time Drilling hydraulic Optimization Real-Time Rate of Penetration Optimization Probabilistic Model Downhole Drilling Problem Identification Uncertainty Window internet-of-things (IoT)

M3 - Doctoral Thesis

ER -