The objectives of this study are to collect data of high-viscosity oil-gas flow in upward vertical pipe and assess the performance of existing mechanistic models developed based on low viscosity liquid experimental results. In this study, oil with viscosity between 0.1 and 0.5 Pa·s (100 and 500 cP) corresponding to temperatures from 37.8 to 15.6 °C (100 to 60 °F) and natural gas at 2.515 MPa (350 psig) pressure are used as the two phases. Superficial oil velocity lies in the range from 0.1 to 1.0 m/s and superficial gas velocity is in the range from 0.5 to 4.0 m/s. The internal diameter of the pipe is 52.5 mm (2.067 in). The experimental measurements include pressure gradient and liquid holdup. The flow pattern and slug characteristics are observed and the images are recorded with a high definition video system through a sapphire window. The experimental results are compared with the predictions of unified model and other models, and the gaps are identified.

Pipeline integrity is an important area of concern for the oil and gas, refining, chemical, hydrogen, carbon sequestration, and electric-power industries, due to the safety risks associated with pipeline failures. Regular monitoring, inspection, and maintenance of these facilities is therefore required for safe operation. Large standoff magnetometry (LSM) is a non-intrusive, passive magnetometer-based mea- surement technology that has shown promise in detecting defects (anomalies) in regions of elevated mechanical stresses. However, analyzing the noisy multi-sensor LSM data to clearly identify regions of anomalies is a significant challenge. This is mainly due to the high frequency of the data collection, mis-alignment between consecutive inspections and sensors, as well as the number of sensor measurements recorded. In this paper we present LSM defect identification approach based on ma- chine learning (ML). We show that this ML approach is able to successfully detect anomalous readings using a series of methods with increasing model complexity and capacity. The methods start from unsupervised learning with "point" methods and eventually increase complexity to supervised learning with sequence methods and multi-output predictions. We observe data leakage issues for some methods with randomized train/test splitting and resolve them by specific non-randomized splitting of training and validation data. We also achieve a 200x acceleration of support-vector classifier (SVC) method by porting computations from CPU to GPU leveraging the cuML RAPIDS AI library. For sequence methods, we develop a customized Convolutional Neural Network (CNN) architecture based on 1D convolutional filters to identify and characterize multiple properties of these defects. In the end, we report the scalability of the best-performing methods and compare them, for viability in field trials.

No abstract

No abstract

No abstract