Digitalization in Drilling: Automated back pressure drilling (MPD) for controlling and keeping BHP constant

The digitalization of drilling processes has revolutionized the oil and gas industry, leading to significant advancements in drilling techniques and technologies. One of the key areas of focus in this digitalization is the development of automated back pressure drilling, also known as Managed Pressure Drilling (MPD), for controlling and maintaining the Bottom Hole Pressure (BHP) constant. This approach has been facilitated by the integration of digital twin frameworks, artificial intelligence methods, and advanced hydraulic models, which have collectively enhanced the accuracy and drilling operations efficiency. The digitalization of hydraulic rotary drilling processes has enabled the continuous mechanical profiling of siliciclastic sedimentary rocks, leading to the identification of variations in drilling speed that are consistent with the properties of different geomaterials and ground conditions (1). This digitalization has provided factual drilling data that are crucial for understanding the behavior of different formations and optimizing drilling parameters. Furthermore, the development of a digital twin framework for robotic drilling processes has facilitated real-time monitoring and control of drilling operations, allowing for the virtual assessment of dynamic drilling behaviors such as speed and feed irregularities (2, 3). This has significantly enhanced the ability to maintain BHP constant during drilling operations. Artificial intelligence methods have also played a pivotal role in the digitalization of drilling processes, particularly in the context of MPD. These methods have been successfully applied in various aspects of the oil and gas industry, including reservoir characterization, prediction of PVT properties, and optimization of well production (4). Moreover, the integration of a hybrid neural network model has provided valuable insights for predicting BHP in MPD, offering guidance for fine pressure control in complex formations (5). This demonstrates the potential of artificial intelligence in optimizing drilling processes and ensuring the stability of BHP. In addition to digital twin frameworks and artificial intelligence, advanced hydraulic models have been instrumental in the development of automated MPD control systems. These models have been used to intelligently estimate downhole pressure, thereby enhancing the accuracy of pressure control systems in MPD operations (6, 7). Furthermore, the comparison of latero-medial versus dorso-palmar/plantar drilling approaches has highlighted the usefulness of digital fluoroscopy in assessing the percentages of articular cartilage removed during drilling, emphasizing the role of digital technologies in enhancing precision and control during drilling procedures (8). The digitalization of drilling processes, facilitated by digital twin frameworks, artificial intelligence methods, and advanced hydraulic models, has significantly advanced the capabilities of automated back pressure drilling for controlling and maintaining BHP constant. These technological advancements have not only enhanced the accuracy and efficiency of drilling operations but have also paved the way for the development of automated drilling algorithms and tools, ultimately revolutionizing the oil and gas industry. In this thesis, the focus is on Automated back pressure drilling (MPD) for controlling and keeping BHP constant using Python.