Optimal design for real-time quantitative monitoring of sand in gas flowline using computational intelligence assisted design framework

Abstract

Global demand for oil and gas is still increasing rapidly. The direct consequence of this is the increased operating pressure amid concerns over increasing sand production. According to the Society of Petroleum Engineers (SPE), 70% of the world's hydrocarbon reserves are contained in reservoirs situated on unconsolidated formations. Given the reality of these formations, sand production will certainly be a problem of significant concern particularly during the later life of the fields when they become more 'mature'. However, to monitor sand and optimise its production for improved recovery and safety, life extension and economy of the fields and ensured reliability, the automatic detection and prediction of sand flow characteristic measurements; sand flow rate (SFR), sand concentration (SC), line pressure drop (PD), and gas velocity (GV), has become an important research topic of great interest. Despite this importance, discussion of the topic is still lacking in the literature. This paper proposes a novel and robust architecture of intelligent real-time sand flow characteristic measurement using an acoustic sensor and computational intelligence assisted design (CIAD) framework. It fully incorporates acoustic signal processing and analysis, prediction algorithms and optimisation algorithms in the design. Acoustic features based on acoustic signal processing techniques are extracted to reduce the dimensionality of the acoustic signals. A classical Artificial Neural Network (ANN) is used to model the non-linear relationships between the acoustic signal characteristics and the flow characteristics measurands. In addition, the ANN algorithm adapts its weights and biases using the Grey Wolf Optimiser (GWO) through minimisation of the cost function during the training phase. Preliminary results obtained on a laboratory test rig demonstrate that an acoustic sensor coupled with CIAD may provide simple and robust practical solution to the measurement problem of particle-laden gas flow characteristics in real-time.

Prediction of CO2 diffusivity in brine using white-box machine learning

“…The database was divided randomly into a training set with 80% of the whole experimental data points and a testing set which covers the remaining 20%. This dataset partitioning exhibits usually very satisfactory results (Aminu et al, 2019;Benamara et al, 2019;Dargahi-Zarandi et al, 2017;Hemmati-Sarapardeh et al, 2018;Mirjalili, 2015;Yan et al, 2006). Besides, in order to substantiate the better performance and robustness of applied techniques, sensitive analysis of the latter on database were performed.…”

Understanding AI Application Dynamics in Oil and Gas Supply Chain Management and Development: A Location Perspective

“…In the area of production, ML models and its hybrids are mainly used for the monitoring, prediction, forecasting, selection and detection of various characteristics and components critical for optimal production. This includes, choke valve flow-rates, production at ultra-high water cut stages, precipitation of asphaltene, sand production, separator selection, faulty events, production forecasting and predictive maintenance [20][21][22][23][24][25][26][27][28][29].…”