Prediction of Gasification Process via Random Forest Regression Model Optimized with Meta-Heuristic Algorithms
This research presents an innovative predictive modeling approach for estimating Hydrogen and Nitrogen quantities in gasification processes, vital for converting carbonaceous feedstocks into valuable gases with minimal environmental impact. It addresses the pressing need for cost-effective and preci...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Bilijipub publisher
2024-03-01
|
| Series: | Journal of Artificial Intelligence and System Modelling |
| Subjects: | |
| Online Access: | https://jaism.bilijipub.com/article_193317_15b39d9b201fff259fe95018a33c4640.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849762719797870592 |
|---|---|
| author | Eunsung Oh |
| author_facet | Eunsung Oh |
| author_sort | Eunsung Oh |
| collection | DOAJ |
| description | This research presents an innovative predictive modeling approach for estimating Hydrogen and Nitrogen quantities in gasification processes, vital for converting carbonaceous feedstocks into valuable gases with minimal environmental impact. It addresses the pressing need for cost-effective and precise solutions in gasification, streamlining estimation processes across various operational conditions, enhancing safety, and enabling data-driven optimization. The current study involves organizing input data into eighteen distinct variables, comprising cellulose, hemicellulose, lignin, lower heating value, particle size, oxygen content, nitrogen content, volatile matter content, carbon content, hydrogen content, sulfur content, SB, moisture, temperature, ash content, equivalence ratio, residence time, and fixed carbon. This study leverages Random Forest Regression (RFR) to analyze gas generation outputs based on historical data. It enhances RFR's predictive accuracy by integrating advanced optimization techniques like Snake Optimization and Equilibrium Optimizer. This approach marks a significant step forward in optimizing gasification processes, promoting more efficient and sustainable conversion of carbonaceous feedstock. The results demonstrate the superior predictive performance of the RFSO model, achieving a remarkable R2 value of 99.7% in training for both Hydrogen (H_2) and Nitrogen (N_2). The optimized models, RFEO and RFSO, consistently outperform the baseline RFR model in forecasting accuracy metrics such as MSE and RMSE, emphasizing their reliability and effectiveness in predicting gasification outcomes. |
| format | Article |
| id | doaj-art-be1185c1d2a24425916a9ffcc8376752 |
| institution | DOAJ |
| issn | 3041-850X |
| language | English |
| publishDate | 2024-03-01 |
| publisher | Bilijipub publisher |
| record_format | Article |
| series | Journal of Artificial Intelligence and System Modelling |
| spelling | doaj-art-be1185c1d2a24425916a9ffcc83767522025-08-20T03:05:39ZengBilijipub publisherJournal of Artificial Intelligence and System Modelling3041-850X2024-03-010201456510.22034/jaism.2024.445930.1026193317Prediction of Gasification Process via Random Forest Regression Model Optimized with Meta-Heuristic AlgorithmsEunsung Oh0HANSEO University, Seosan-Si, Chungcheongnam-do, 31962, South KoreaThis research presents an innovative predictive modeling approach for estimating Hydrogen and Nitrogen quantities in gasification processes, vital for converting carbonaceous feedstocks into valuable gases with minimal environmental impact. It addresses the pressing need for cost-effective and precise solutions in gasification, streamlining estimation processes across various operational conditions, enhancing safety, and enabling data-driven optimization. The current study involves organizing input data into eighteen distinct variables, comprising cellulose, hemicellulose, lignin, lower heating value, particle size, oxygen content, nitrogen content, volatile matter content, carbon content, hydrogen content, sulfur content, SB, moisture, temperature, ash content, equivalence ratio, residence time, and fixed carbon. This study leverages Random Forest Regression (RFR) to analyze gas generation outputs based on historical data. It enhances RFR's predictive accuracy by integrating advanced optimization techniques like Snake Optimization and Equilibrium Optimizer. This approach marks a significant step forward in optimizing gasification processes, promoting more efficient and sustainable conversion of carbonaceous feedstock. The results demonstrate the superior predictive performance of the RFSO model, achieving a remarkable R2 value of 99.7% in training for both Hydrogen (H_2) and Nitrogen (N_2). The optimized models, RFEO and RFSO, consistently outperform the baseline RFR model in forecasting accuracy metrics such as MSE and RMSE, emphasizing their reliability and effectiveness in predicting gasification outcomes.https://jaism.bilijipub.com/article_193317_15b39d9b201fff259fe95018a33c4640.pdfgasificationbiomassmachine learningrandom forestsnake optimizationequilibrium optimizer |
| spellingShingle | Eunsung Oh Prediction of Gasification Process via Random Forest Regression Model Optimized with Meta-Heuristic Algorithms Journal of Artificial Intelligence and System Modelling gasification biomass machine learning random forest snake optimization equilibrium optimizer |
| title | Prediction of Gasification Process via Random Forest Regression Model Optimized with Meta-Heuristic Algorithms |
| title_full | Prediction of Gasification Process via Random Forest Regression Model Optimized with Meta-Heuristic Algorithms |
| title_fullStr | Prediction of Gasification Process via Random Forest Regression Model Optimized with Meta-Heuristic Algorithms |
| title_full_unstemmed | Prediction of Gasification Process via Random Forest Regression Model Optimized with Meta-Heuristic Algorithms |
| title_short | Prediction of Gasification Process via Random Forest Regression Model Optimized with Meta-Heuristic Algorithms |
| title_sort | prediction of gasification process via random forest regression model optimized with meta heuristic algorithms |
| topic | gasification biomass machine learning random forest snake optimization equilibrium optimizer |
| url | https://jaism.bilijipub.com/article_193317_15b39d9b201fff259fe95018a33c4640.pdf |
| work_keys_str_mv | AT eunsungoh predictionofgasificationprocessviarandomforestregressionmodeloptimizedwithmetaheuristicalgorithms |