Intelligent prediction of hydrate induction time in oil–water emulsion system based on data-driven and driving force

• Published in: Chemical engineering science Vol. 307; p. 121305
• Main Authors: Lv, Xiao-Fang, Chen, Shu-Kai, Liu, Yang, Peng, Ming-Guo, Duan, Ji-Miao, Wang, Chuan-Shuo, Ma, Qian-Li, Zhou, Shi-Dong, Li, Xiao-Yan, Shi, Bo-Hui, Song, Shang-Fei
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 15.03.2025
• Subjects: Data augmentation; Driving force; Hydrate induction time; Machine learning; Oil-water emulsion; Small sample; Driving force; Data augmentation; Oil-water emulsion; Small sample; Hydrate induction time; Machine learning
• ISSN: 0009-2509
• DOI: 10.1016/j.ces.2025.121305

•A data augmentation method is proposed for hydrate induction time.•A GBRT model for hydrate induction time prediction based on data augmentation is proposed.•The model has good accuracy and overcomes the disadvantages caused by small samples.•An empirical equation for hydrate induction time based on driving force is proposed.•The empirical equation has good physical consistency and can be used as a reference for field production. The prevention of natural gas hydrates is critical to oil and gas flow assurance. The nucleation process of hydrates has always been a research hotspot, yet its randomness makes the induction time of hydrates difficult to predict. To address this issue, this paper uses a Noise Injection Target Autoencoder (NITAE) to augment data, followed by a GBRT model for predicting hydrate induction time. Finally, the gplearn method is employed to generate an empirical equation for the hydrate induction time. The GBRT model achieves an R2 of 0.9858, with an absolute error within ±0.02, addressing poor prediction performance due to data scarcity. The gplearn-based empirical equation achieves an R2 of 0.8353, with an error within ±20 %. These results provide a new direction for predicting the hydrate formation induction time in actual field conditions and the prevention of hydrate formation in oil and gas pipelines.