Underwater Gas Leak Quantification by Convolutional Neural Network using Images
Preprint
- 2 December 2024
- preprint
- Published by MDPI AG in Preprints.org
Abstract
Exploration and production activities in deep-water oil and gas reservoirs can directly impact the surrounding ecosystems. Thus, a tool capable of measuring oil and gas leaks based on surveillance images, especially in pre-mature stages, is of great importance for risk assessment. In the present work, a convolutional neural network (U-Net) is applied to leak images using transfer learning and hyperparameter optimization, aiming to predict bubble diameter and flow rate. The data was extracted from a reduced model leak experiment, with a total of 77,676 frames processed, indicating a Big Data context. The results agreed with the data obtained in the laboratory: for the flow rate prediction, coefficients of determination by transfer learning and hyperparameter optimization were, respectively, 0.938 and 0.941. Therefore, the novel methodology has potential applications in the Oil & Gas Industry, in which leaks captured by remotely operated vehicles can be measured by an artificial intelligence agent.Keywords
All Related Versions
- Version 1, 2024-12-02, Preprints
- Published version: Processes, 13 (1), 118.
This publication has 71 references indexed in Scilit:
- Enhancing fault detection and diagnosis systems for a chemical process: a study on convolutional neural networks and transfer learningEvolving Systems, 2023
- Monitoring of the Drilling Region in Oil Wells Using a Convolutional Neural Network2023
- Quantifying Subsea Gas Leakages using Machine Learning: a CFD-based study2022
- Experimental study on the influence of the orifice size on hydrodynamic characteristics and bubble size distribution of an external loop airlift reactorThe Canadian Journal of Chemical Engineering, 2020
- Measuring Particle Size Distributions in Multiphase Flows Using a Convolutional Neural NetworkChemie Ingenieur Technik, 2019
- Hyperparameter Optimization2019
- Convolution Neural Network based Chemical Leakage Identification2018
- Observations of bubbles in natural seep flares at MC 118 and GC 600 using in situ quantitative imagingJournal of Geophysical Research: Oceans, 2016
- Current understanding of subsea gas release: A reviewThe Canadian Journal of Chemical Engineering, 2015
- Bubble formation in quiescent liquids under constant flow conditionsChemical Engineering Science, 1986