แจ้งเอกสารไม่ครบถ้วน, ไม่ตรงกับชื่อเรื่อง หรือมีข้อผิดพลาดเกี่ยวกับเอกสาร ติดต่อที่นี่ ==>
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
Phantisa Limleamthong. Machine learning for predictive modelling of hydrogen production from biomass gasification. (). King Mongkut's University of Technology North Bangkok. Central Library. : , 2024.
Machine learning for predictive modelling of hydrogen production from biomass gasification
Name: Kitti Kamolram
Organization :
Kasetsart University. Faculty of Engineering
Name: Kanawat Tariyo
Organization :
Kasetsart University. Faculty of Engineering
Name: Phantisa Limleamthong
Organization :
Kasetsart University. Faculty of Engineering
Email :
phantisa.l@ku.th
keyword:
Hydrogen production
LCSH:
Machine learning
LCSH:
Predictive control
LCSH:
Biomass gasification
LCSH:
Renewable energy sources
Abstract:
Biomass gasification has been studied widely as one of the most suitable approaches to
recover energy from biomass feedstocks. However, the process typically relies on a complex
mix of interacting variables, traditional models such as thermodynamic equilibrium and kinetics
often struggle to achieve an accurate prediction. This research, therefore, focuses on a more
powerful alternative that can handle complex input-output relationships, i.e., machine learning
techniques, to develop predictive models of syngas from biomass gasification, including
Hydrogen. The inputs of machine learning models include different key variables affecting
product yield which cover different feedstocks and operating conditions, while the effect of
cross-validation was also explored. The results showed that the most accurate model for
hydrogen prediction was the Gradient Boosting Regressor, having the coefficient of
determination or an R-squared of 0.9576 with 10-fold cross-validation. It can be observed that
the model with cross-validation exhibited a lower performance than the model without crossvalidation.
This could be attributed to the step of hyperparameter tuning with cross-validation
which gives a more generalized set of hyperparameters that leads to a slightly less accurate
model but could be more reliable to handle unseen data. SHapley Additive exPlanations analysis
was implemented to the highest performance model to determine the important factors
influencing the gasification process. It was found that gasifying agents are the most influential
factor for hydrogen production. This information can be used as a valuable guideline for further
process optimization
King Mongkut's University of Technology North Bangkok. Central Library
Address:
BANGKOK
Email:
library@kmutnb.ac.th
Created:
2024
Modified:
2025-03-11
Issued:
2025-03-11
บทความ/Article
application/pdf
BibliograpyCitation :
In Thai Institute of Chemical Engineering and Applied Chemistry. The 33st Thai Institute of Chemical Engineering and Applied Chemistry International Conference (TIChE 2024) (pp.513-520). Bangkok : Thai Institute of Chemical Engineering And Applied Chemistry
eng
©copyrights King Mongkut's University of Technology North Bangkok
RightsAccess:
ใช้เวลา
-0.974496 วินาที
Kitti Kamolram
| Title | Contributor | Type |
|---|---|---|
| Machine learning for predictive modelling of hydrogen production from biomass gasification
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Kitti Kamolram;Kanawat Tariyo;Phantisa Limleamthong | บทความ/Article | |
| Enhancing low-carbon hydrogen production from biomass gasification via machine-learning-aided multi-objective optimization with TOPSIS
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Kitti Kamolram;Phantisa Limlaemthong | บทความ/Article |
Kanawat Tariyo
| Title | Contributor | Type |
|---|---|---|
| Machine learning for predictive modelling of hydrogen production from biomass gasification
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Kitti Kamolram;Kanawat Tariyo;Phantisa Limleamthong | บทความ/Article |
Phantisa Limleamthong
| Title | Contributor | Type |
|---|---|---|
| Assessing sustainability performance of Thailand provinces via super efficiency data envelopment analysis
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Narawit Yingyong;Satawat Thumwong;Phantisa Limleamthong | บทความ/Article | |
| Machine learning for predictive modelling of hydrogen production from biomass gasification
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Kitti Kamolram;Kanawat Tariyo;Phantisa Limleamthong | บทความ/Article | |
| Travelling salesman problem considering traffic data and IoTs for smart waste collection system : case study of a university
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Lwin, Hnin Sandar;Saowanit Lekhavat;Phantisa Limleamthong | บทความ/Article | |
| Enhancing non-catalytic biomass pyrolysis yield predictions using machine learning and data augmentation
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Anchalee Chaichanavongsaroj;Dasakorn Rungrampan;Phantisa Limleamthong | บทความ/Article | |
| A LSTM-based utility consumption prediction for a process with performance degradation : a case study of a vinyl chloride monomer plant
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Chutithep rochpuang;Chanin Panjapornpon;Phantisa Limleamthong | บทความ/Article |