Machine Learning in Asphaltenes Mitigation
The issue of Asphaltenes formation inside the pipeline is a major concern in flow assurance industry. These are complex polar molecules with high molecÂular weights. Asphaltenes mitigation is required as they disrupt the normal operÂation of the pipeline. Industry employs mechanical, ultrasonic, t...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Book |
| Published: |
Springer Nature
2023
|
| Online Access: | http://scholars.utp.edu.my/id/eprint/38046/ https://www.scopus.com/inward/record.uri?eid=2-s2.0-85174771837&doi=10.1007%2f978-3-031-24231-1_5&partnerID=40&md5=e838d18c33e97deb738b9f509b8bd38e |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The issue of Asphaltenes formation inside the pipeline is a major concern in flow assurance industry. These are complex polar molecules with high molecÂular weights. Asphaltenes mitigation is required as they disrupt the normal operÂation of the pipeline. Industry employs mechanical, ultrasonic, thermal, bacterial and chemical treatments to mitigate asphaltenes deposition. For asphaltenes predicÂtion, preceding studies have used thermodynamic solubility technique, colloidal based models. Currently researchers have focused on machine learning techniques to predict the conditions of asphaltenes formation. The machine and deep learning methods included Bayesian belief network (BBN), Least-squares support vector machine (LSSVM), Support vector regression (SVR) and Genetic algorithm-support vector regression (GA-SVR). It was found that the use machine learning and deep learning approaches predicted accurately about the onset of asphaltenes precipitation and deposition. In future, the utilisation of machine learning approaches in the field of asphaltenes mitigation can be studied further. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2023. |
|---|