Search

In this study, 13 machine learning (ML) models were employed to predict the phase equilibrium temperatures of the CO2hydrate in systems with salts and organic inhibitors: Multiple Linear Regression (MLR), Support Vector Regression (SVR), k-Nearest Neighbors (KNN), Multi-Layer Perceptron (MLP), Decision Tree (DT), Random Forest (RF), Extra Trees (ET), Adaptive Boosting (AdaBoost), Categorical Boosting (CatBoost), Gradient Boosting Machine (GBM), Light Gradient Boosting Machine (LGBM), Histogram-Based Gradient Boosting (HistGB), and eXtreme Gradient Boosting (XGBoost). A dataset consisting of 1801 experimentally measured equilibrium data points was gathered, which included both pure water systems and systems with thermodynamic inhibitors. After data preprocessing, 1402 data points were selected for ML training and validation. Boosting algorithms generally yielded high predictive accuracy, with the MLP demonstrating notably superior accuracy. The predicted equilibrium temperatures for complex systems containing both salts and organic inhibitors were also compared with those calculated by the widely used CSMGem software. With the exception of SVR, KNN, and DT, all models outperformed CSMGem, in terms of statistical assessment. Specifically, the CatBoost model accurately predicted equilibrium temperatures for most test sets of combinations of salts and organic inhibitors. This study underscores the viability of ML models for predicting the phase equilibria of the CO2hydrate in the presence of single and mixed thermodynamic inhibitors.

This research addresses the challenges of gas hydrate formation in subsea flowlines, focusing on the investigation of antiagglomerants (AAs): Vitamin E derivative (d-alpha tocopherol succinate, Vitamin E-TS), sorbitan monostearate (Span-60), and dodecyl trimethylammonium bromide (DTAB), and their synergistic interactions with monoethylene glycol (MEG). Through an in-depth examination of hydrate onset time, growth rate, and torque change under varying pH values, this study offers comprehensive insights into the performance of the selected AAs and their combined efficacy with MEG in hydrate inhibition. The experimental results reveal notable variations in hydrate formation and inhibition characteristics, highlighting the influence of different AAs and their interactions with MEG. The study demonstrates the potential of Vitamin E-TS in altering hydrate formation kinetics, Span-60 in maintaining hydrate particle dispersion, and DTAB in mitigating hydrate agglomeration. These findings contribute to a nuanced understanding of hydrate dynamics and provide valuable insights for the development of more effective and cost-efficient hydrate management strategies in the industry. The research enriches the ongoing dialogue on hydrate inhibition and presents a thorough exploration of methodologies, results, and their implications in this critical field of study.

The quest for environmentally sustainable solutions for CO2recovery and purification has led to the development of innovative separation techniques, which are crucial for carbon capture, utilization, and storage (CCUS) applications. Moreover, refrigerant recovery techniques have been widely developed after the implementation of stringent global regulations on hydrofluorocarbon (HFC) emissions. This study explores the separation of R134a, a well-known HFC, from carbon dioxide (CO2), focusing on the feasibility of hydrate-based processes for the recovery of high-purity CO2. Phase equilibrium measurements, spectroscopic analysis, and process simulation studies were systematically performed to evaluate the operation conditions and energy requirements of the hydrate-based separation processes. Phase equilibrium measurements for R134a + CO2mixtures at various concentrations were performed along with the structural analysis of mixed hydrates using low-temperature powder X-ray diffraction (PXRD). The experiments demonstrated the preferential occupation of R134a into hydrate cages, enriching CO2in the vapor phase and achieving target purity levels of 99.0 mol % CO2. The PXRD patterns confirmed the formation of structure II hydrates with a lattice parameter of 17.2 Å with inclusions of R134a in large cages, resulting in a higher exothermic heat of formation compared with that of structure I hydrates. Process simulations were performed to further extend these findings, highlighting the favorable operation conditions and the exothermic nature of hydrate formation, which suggested heat integration into other process units. This study represents a pioneering effort in modeling hydrate-based CO2recovery processes, providing a significant contribution to the development of sustainable industrial practices and the advancement of CCUS technologies.