An experimental flow loop was designed and constructed to perform the wax deposition tests under the oil/gas twophase flow conditions in a horizontal pipe. The oil sample came from the Daqing Oilfield of China, which was characterized by high wax content. A particular local sampler was designed and installed at the outlet of the test section in the flow loop to make up for the drawback of no visual observation during the course of flow pattern verification, which is a good device to help verify the flow pattern by analyzing the inner flow situations at different circumferential and vertical positions. Using the local sampler in combination with analyzing the changes in pressure drop and liquid holdup, which is defined as the fraction of an element of pipe occupied by liquid at the same instant, flow patterns were identified and divided into two main categories, namely, the stratified flow and slug flow. Wax deposition tests were selected in the definite flow pattern regions instead of flow pattern transition regions. The effects of flow pattern characteristics on wax deposition were experimentally studied under the oil/gas two-phase flow conditions. The results show that liquid superficial velocity, gas superficial velocity, shear stress at the liquidÀdeposit interface, liquid holdup, and slug frequency do play an important role in wax deposition in the oil/gas two-phase flow. The wax deposition characteristics were experimentally obtained for stratified flow and slug flow. The experimental results in this study provide an experimental reference and insight for further study on wax deposition in multiphase flow, especially under the conditions that the oil sample is characterized by high wax content.' EXPERIMENTAL SECTION Experimental Sample. The experimental oil sample used in the study was a typical waxy crude oil characterized by high wax content and
Interpretation of production logging in multi-phase flow wells is challenging, especially for highly deviated wells or horizontal wells. Flow regime-dependent flow conditions strongly affect the measurements of production logging tools. Segregation and possible back flow of denser phases result in misinterpretation of the inflow distribution. To assess the downhole flow conditions more accurately, logging tools have been developed to overcome the flow regime related issues. Multiple-sensor array tools measure the fluid properties at multiple locations around the cross-sectional area of the wellbore, providing a distributed measurement array that helps to relate the measurements to flow regime and translate the measurement to inflow distribution. This paper present a methodology for using array data from production logging tools to interpret downhole flow conditions. The study uses an example logging tool that consists of 12 resistivity, 12 capacitance probes, and six spinners around the wellbore circumference. The method allows interpretation of phase volumetric flow rates in sub-divided crosssectional areas based on sensor locations. The sub-divided area method divides the wellbore cross-sectional area into several layers depending on the number and arrangement of the sensors with each layer containing at least one sensor. Holdup and velocity outputs from sensors in each wellbore area segment are combined to calculate the volumetric flow rates of each phase in each segment. These results yield a profile of flow of each phase from the high side to the low side of the wellbore, and the overall flow rates of each phase at every location along the well where the interpretation method is applied.The method developed was used to interpret the flow profile of an Eagle Ford well producing gas and water at downhole conditions. A reasonable profile of gas inflow was obtained and the profile was similar to that interpreted with a commercial production log interpretation software package. The interpretation of the water flow profile was complicated by low total water production rate and variations in wellbore inclination.
With the coming of increasingly large databases, the growing amount of computational resources and latest algorithmic advancements, data driven and machine learning techniques are considered as potential game changers in traditional Oil and Gas industry. Unconventional oil and gas formations, including basin central gas/oil, shale gas/oil, tight gas/oil, and coalbed methane formations, are abundant, which have become an increasingly important part of global energy supply and attracted increasing attention from the industry. In the development of unconventional hydrocarbon exploration, the high well placement density leads to more data and provides the condition to use data-driven methods for engineering parameters on well production could not be easily considered by traditional simulation methods. The objective of this study is to optimize of completion parameters by data mining and ensemble machine learning methodologies which are essential for the development of the Montney Formation. Firstly, all the data with more than 80 variables over Canada Wapiti-Montney Tight gas formation have been collected and used for determining the most important engineering parameters by the sensitivity test. In additional, the time series analysis is used to identify the turning time when stimulation dominated effects disappeared in the entire production period. Based on the sensitive test and data mining results, multiple key parameters have been recognized and used as independent variables for the machine learning analysis, such as liner regression, support vector machine, neural networks, Gauss regression, etc. The corresponding assumptions for each learning methods are analyzed, benchmarked and discussed in this paper. In addition, a stacking model which ensemble top 3 best accuracy Machine Learning models is carried out to enhance the accuracy of production forecast ability in Montney Shale formation. During the model training, several feature engineering methods are used to lowering the difficulty for models to obtain knowledge in big data. Based on the sensitivity analysis results, the following matrices, Stimulated Length (SL), Total Stage Count (TSC), Pumped Proppant per Length (PPL), Pumped Fluid Per Length (PFL) and Injection Rate (IR), are recognized as the most important and sensitive independent variables for production prediction in Wapiti-Montney tight gas formation. The final ensemble model is established by stacking three best individual machine learning algorithms of this study. They are random forest, XGBoost, and Light GBM respectively. The accuracy of prediction by ensemble model could reach as high as 90%, which is much higher than predictions before stacking process. The application results were encouraging. Three Wapiti horizontal gas well was optimized by the proposed data driven workflow and the cumulative production were improved by 20% around the turning time point. Such new quick evaluation using Ensemble Machine Learning model could optimize the accuracy of prediction and provide simple rules of engagement for Well completion Design Optimization and decision-making throughout the entire development of Montney Tight formation in Wapiti field.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.