SHAREOK Repository
Not a member yet
49261 research outputs found
Sort by
Application of Machine Learning and Deep Learning to Predict Production Rate of Sucker Rod Pump Wells
Get PDFSucker rod pump (SRP) systems must be designed, optimized, and operated with the aid of production data. This work seeks to create machine learning-driven models that can forecast fluid flow rate at the surface of SRP artificially lifted wells because traditional separators and multiphase flowmeters (MPFMs) may not be available in all wells. Nine machine learning models were developed using real data from 598 wells over three years, with 8,372 data points randomly split into 80% (6,697 data points) for training and 20% (1,675 data points) for testing. These models include Gradient Boosting, AdaBoost, Random Forest, Support Vector Machines (SVMs), Tree, K-Nearest Neighbor (KNN), Linear Regression, Neural Network, and Stochastic Gradient Descent (SGD). Each data set contained readings for the parameters that are easily accessible during any SRP well lifting process, including wellhead flowing pressure, casing pressure, inferred bottom hole fluid production rate, inferred bottom hole oil production rate, net liquid above pump, pump size, stroke length, pump running speed (SPM), pump depth, temperature at pump depth, oil gravity, water viscosity, and pump clearance. The performance of machine learning models is evaluated using two methods (K-fold cross-validation and repeated random sampling), and the results of the top five models (Gradient Boosting, Random Forest, AdaBoost, Linear Regression, Random Forest, and stochastic gradient descent) show that the mean absolute percent error (MAPE) between the predicted fluid rate at the surface and the actual measurements is 3.6, 3.4, 3.4, 4, and 4.4%, respectively. The correlation coefficients (R2) are also 0.937, 0.935, 0.934, 0.921, and 0.915, respectively. Additionally, an oil well in Egypt's Western Desert had its fluid flow rate at the surface predicted using machine learning models. The outcomes were contrasted with the data from the separator test itself. The actual fluid rate and the model's predictions were in perfect accord. Within a wide range of pumping circumstances and completion configurations, the machine learning models are helpful for forecasting the production rates of particular wells. This should make it possible to continuously monitor, optimize, and analyze the performance of SRP wells and to respond more quickly to operational problems. The application of the proposed machine learning models is easy, quick, and affordable when compared to conventional separators and multiphase flowmeters (MPFMs).N
Everyperson's Cookbook : One Pot Cooking Done
No full textCookbook produced by the Wichita Chapter of the National Organization for Women
Virtuelle Forschungsumgebungen (German translation of "Virtual Research Environments")
Get PDFVirtuelle Forschungsumgebungen in den theologischen Studien (und v. a. in den frühchristlichen Studien und den damit verbundenen Altertumswissenschaften) können eine wertvolle Infrastruktur für die Erstellung digitaler Editionen von Primärquellen und für andere Formen der digitalen und computergestützten Forschung bieten. Die Schaffung und Aufrechterhaltung dieser Umgebungen ist mit Herausforderungen verbunden. In diesem Beitrag werden die Vorteile der projektübergreifenden Zusammenarbeit sowie der gemeinsamen Nutzung und Wiederverwendung digitaler Ressourcen untersucht. Es werden auch einige Überlegungen zur Arbeit mit unsauberen oder sauberen digitalen Daten und zur Übernahme bestehender technischer Standards vorgestellt. In Bezug auf all diese Themen beinhaltet der Aufbau und die Nutzung von VREs die Entwicklung einer entsprechenden tech- nischen Infrastruktur. Genauso wichtig wie die Technik sind jedoch die geisteswissenschaftlichen Fragen und die persönlichen Beziehungen, die einer erfolgreichen digitalen Initiative zugrunde liegenYe
THE EXAMINATION OF SCHOOL SAFETY IN OKLAHOMA PUBLIC SCHOOLS
No full textThis research study examines the current Oklahoma school safety laws and policies. This research focuses on three core areas: Bullying Prevention, Illegal Substance Prevention, and Dangerous Weapons Restrictions. By implementing these three areas, this research identifies common trends of Oklahoma public school safety, frequency of safety incidents, and disciplinary actions taken as a result of the incidents. This research aims to identify problems within the current safety laws, and identify implications to enhance the safety of Oklahoma public schools
POST–DRILLING SIMULATION USING UTAH FORGE DATA ON THE DRILLING SIMULATOR AS WELL AS IN-DEPTH ANALYSIS OF DRILLING VIBRATION USING DRILLSCAN TECHNOLOGY
No full textAbstractGeothermal energy extracted from the heat in the Earth’s crust has emerged as one of the sustainable and reliable sources of power. Drilling for exploration and exploitation of Geothermal energy resources is key to affordable and independent energy. However, the inherent complexities of drilling in geothermal formations pose notable challenges to operational efficiency, safety, and cost-effectiveness. Drilling to exploit geothermal resources like all drilling activities is destructive and therefore problems such as equipment wear and tear, shorter tool life span, and Non-Performing Time (NPT) are inevitable. While there have been attempts to apply conventional oil and gas knowledge to geothermal drilling, it still poses unique challenges. Simulation of the drilling processes, challenges, and mitigating measures are required to ensure operational efficiency, cost-effectiveness, and safety in harnessing the resource. The study delves into a post-drilling simulation of Utah Forge data using a drilling simulator (DrillSim50) and DrillScan technology. This is to assess the drilling processes, the impact of drilling vibrations on equipment wear, and failure, and the mitigation of such vibrations in the drilling industry. By leveraging Utah Forge data, the study highlights the drilling difficulties in post-drilling simulations, providing valuable insights into real-world scenarios. The research will allow for a comprehensive investigation into vibration dynamics, shed light on potential challenges, and propose strategies for enhanced drilling efficiency. The major topics included in the study are: A. Geothermal Drilling B. Utah Forge well 16A-78-32 drilling overview C. Post-drilling vibrations Analysis. D. Categories of drilling and well control simulators E. Strength, limitations, and future design opportunities F. Vibration mitigation G. Post-Drilling processes on DrillSim50 H. Impact of Conventional Well Control on Geothermal Drilling and Construction With the above-mentioned topics, the study can comprehensively devise a tool for identifying a suitable simulator for specific training when embarking on challenging well operations. In addition, investigation into the drilling dynamics, and vibrations, may highlight the potential challenges, and propose strategies for enhanced drilling efficiency. One of the critical factors that impacts the success of geothermal well construction is the application of effective well control measures. Conventional well control principles, which encompass techniques for maintaining wellbore integrity and controlling formation fluid influx, are fundamental to ensuring safe and efficient drilling operations in geothermal reservoirs. However, the unique geological and operational challenges associated with geothermal drilling necessitate the adaptation and customization of conventional well control methodologies. By studying the impact of the application of conventional well control on geothermal, the techniques and technologies directed at managing subsurface pressures to prevent blowouts can be investigated. After successfully identifying the complexities of geothermal well control, appropriate well control measures unique to geothermal will be proffered. Overall, a comprehensive understanding of post-drilling processes, vibration analysis, and geothermal well control has been gained in this study which can be used in the field for better drilling process, effective well control, and mitigation of drilling vibration
Investigation of Special Problems in Electromagnetics with the Finite-Difference Time-Domain Method
No full textThe Finite-Difference Time-Domain(FDTD) method is a robust numerical time-domain technique capable of handling a broad range of electromagnetic problems. This work explores the application of FDTD method to two special problems in electromagnetics: the modeling of antennas loaded with time-varying components, and the modeling of the human head at microwave frequencies. A recent surge in interest for non-LTI antennas -- driven by a desire to circumvent the performance bounds of their LTI counterparts -- has made apparent the need for modeling techniques capable of handling nonlinear or time-variant behavior on antenna structures. Modeling of time-varying components in FDTD will be demonstrated through direct implantation in the FDTD algorithm with a modified update equation, and through SPICE co-simulation. There is currently a large body of work studying the impact of microwave and radio frequency radiation on human tissue. The effects of prolonged exposure to non-ionizing radiation is typically characterized using specific absorption rate (SAR), and research has often been conducted in the context of wireless communication devices. Many papers in open literature involve simulations with a source antenna in close proximity to the head, excited by a single tone continuous wave or narrow-band gaussian pulses. Using relaxation models to account for the frequency dependent behavior of tissue, this work investigates the interactions of plane waves excited by linear-frequency modulated pulses incident upon the human head in FDTD
EVALUATION OF MOVING TARGET DOH SERVER DETECTION USING MACHINE LEARNING MODELS
No full textThe rapid adoption of DNS over HTTPS (DoH) has introduced significant challenges in balancing privacy, security, and resistance to censorship. This thesis explores the feasibility of developing a censorship-resistant DoH service, named NinjaDoH, which leverages hyperscalers and the InterPlanetary File System (IPFS) to enhance accessibility and resilience against censorship efforts. The study investigates two core research questions: first, the development and implementation of NinjaDoH , a dynamic, censorship-resistant DoH service utilizing hyperscalers and IPFS; and second, the efficiency of existing firewall solutions in targeting NinjaDoH, a moving DoH service, using various machine learning models. By evaluating firewall responses and the success of advanced machine learning techniques in identifying NinjaDoH traffic, this research highlights the strengths and weaknesses of current detection methods. The findings demonstrate the potential of IPFS as a robust, censorship-resistant solution for secure DoH communication, offering a novel framework for safeguarding internet access against state-level and organizational censorship
Motor Thermal Model for Aging Control Applications
No full textDeeper integration of renewable energy sources on the electric grid has increased flexibility requirements across power systems, from generation to transmission/distribution and consumer equipment. On the consumer end, the use of variable-speed electric motors in commercial and residential heating, ventilation, and air-conditioning (HVAC) applications is becoming widespread due to their energy and cost-saving benefits compared to single-speed motors. However, the enhanced features and operational flexibility of these modern motors may come at the cost of increased thermal stress on the motor components, particularly the stator winding insulation. To address this challenge, this thesis presents the development of a generic Lumped Parameter Thermal Network (LPTN) model that can accurately capture the thermal behavior of induction motors under dynamic and varying speed and load conditions. The LPTN model parameters are systematically tuned and calibrated using test data from laboratory tests covering different speed and load settings, achieving a maximum error of 4.8°C between the model predictions and experimental measurements for a 3 HP test motor. The dynamic, modulating control of the motor leads to winding temperatures 7.3°C higher than that under constant-speed control, showing significant aging effect of dynamic operation of motors due to flexibility provision. The calibrated thermal model and the physical 3 HP motor are tested under constant and modulation speed control cases. The thermal model is able to predict the hot spot temperature difference between these two test cases for the test motor with an accuracy of 0.2°C, validating the model’s capability to accurately replicate the change in the thermal behavior of the case study motor. This generic, calibrated LPTN model can serve as a powerful tool to facilitate faster and more cost-effective development of control strategies and maintenance plans for variable-speed electric motors, ultimately improving their reliability and energy efficiency in a wide range of commercial and residential applications