Escalante, Jamin Jamir and Chen, Wei-Hsin and Daud, Wan Mohd Ashri Wan and Su, Chien-Yuan and Li, Po-Han (2025) Prediction construction for biomass and high-density polyethylene co-gasification via statistical method and machine learning. Fuel, 391. p. 134828. ISSN 0016-2361, DOI https://doi.org/10.1016/j.fuel.2025.134828.
Full text not available from this repository.Abstract
This study delves into the intricate interplay of six key parameters, focusing on their impact on gasification characteristics, particularly cold gas efficiency (CGE) and carbon conversion (CC). Employing the Taguchi method for experimental design, the study achieves the highest CGE value of 65.67 %, while the peak CC is 86.78 %. Subsequent signal-to-noise (S/N) ratio analysis reveals that temperature and catalyst are the most influential factors, with 850 degrees C and the PN2 catalyst showing significantly better performance for CGE and CC. Higher temperatures increase gas formation and reduce tar and char yields. Additionally, hydrocarbon steam reforming, carbon gasification, and water-gas shift reactions are catalyzed by nickel-based catalysts, which improve syngas generation in gasification. The influence hierarchy for CGE is temperature > catalyst type > equivalence ratio > oxygen concentration > biomass type > high-density polyethylene (HDPE) ratio. Conversely, for CC, the hierarchy is temperature > catalyst type > equivalence ratio > HDPE ratio > biomass type > oxygen concentration. Experimental verification of the optimal case of CGE yields a value of 66.40 %, surpassing the highest value of 64.67 % in the Taguchi design. Artificial Neural Network (ANN) models are developed to predict CGE and CC. The CGE model, featuring one hidden layer with 24 neurons, achieved an R-2 of 0.9976, while the CC model, with one hidden layer and 12 neurons, demonstrates a robust R-2 of 0.9916. Successfully forecasting all 729 combinations, these models pinpointed optimal conditions. The best combination (A1-B1-C3-D3-E3-F1) predicts a CGE of 70.96 %, while CC (A2-B1-C3-D3-E3-F1) forecasts a 99.61 % conversion. This study showcases the effective utilization of the Taguchi method for experimental design and the construction of ANN prediction models. Such optimization efforts are pivotal for advancing syngas production, enhancing efficiency, ensuring economic viability, and promoting environmental sustainability within gasification.
| Item Type: | Article |
|---|---|
| Funders: | Energy Administration, Ministry of Economic Affairs, ROC (113-S0106) |
| Uncontrolled Keywords: | Co-gasification; Taguchi method; Cold gas efficiency (CGE); Carbon conversion (CC); Artificial neural network (ANN) |
| Subjects: | T Technology > TP Chemical technology |
| Divisions: | Faculty of Engineering > Department of Chemical Engineering |
| Depositing User: | Ms. Juhaida Abd Rahim |
| Date Deposited: | 05 May 2025 08:18 |
| Last Modified: | 05 May 2025 08:18 |
| URI: | http://eprints.um.edu.my/id/eprint/47850 |
Actions (login required)
 |
View Item |
