Application of Machine Learning Models for Carbon Monoxide and Nitrogen Oxides Emission Prediction in Gas Turbines
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929692048621568 |
|---|---|
| author | Zeinalipour, Kamyar Barriere, Laure Ghelardi, David Gori, Marco |
| author_facet | Zeinalipour, Kamyar Barriere, Laure Ghelardi, David Gori, Marco |
| contents | This paper addresses the environmental impacts linked to hazardous emissions from gas turbines, with a specific focus on employing various machine learning (ML) models to predict the emissions of Carbon Monoxide (CO) and Nitrogen Oxides (NOx) as part of a Predictive Emission Monitoring System (PEMS). We employ a comprehensive approach using multiple predictive models to offer insights on enhancing regulatory compliance and optimizing operational parameters to reduce environmental effects effectively. Our investigation explores a range of machine learning models including linear models, ensemble methods, and neural networks. The models we assess include Linear Regression, Support Vector Machines (SVM), Decision Trees, XGBoost, Multi-Layer Perceptron (MLP), Long Short-Term Memory networks (LSTM), Gated Recurrent Units (GRU), and K-Nearest Neighbors (KNN). This analysis provides a comparative overview of the performance of these ML models in estimating CO and NOx emissions from gas turbines, aiming to highlight the most effective techniques for this critical task. Accurate ML models for predicting gas turbine emissions help reduce environmental impact by enabling real-time adjustments and supporting effective emission control strategies, thus promoting sustainability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_17865 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Application of Machine Learning Models for Carbon Monoxide and Nitrogen Oxides Emission Prediction in Gas Turbines Zeinalipour, Kamyar Barriere, Laure Ghelardi, David Gori, Marco Signal Processing Applications This paper addresses the environmental impacts linked to hazardous emissions from gas turbines, with a specific focus on employing various machine learning (ML) models to predict the emissions of Carbon Monoxide (CO) and Nitrogen Oxides (NOx) as part of a Predictive Emission Monitoring System (PEMS). We employ a comprehensive approach using multiple predictive models to offer insights on enhancing regulatory compliance and optimizing operational parameters to reduce environmental effects effectively. Our investigation explores a range of machine learning models including linear models, ensemble methods, and neural networks. The models we assess include Linear Regression, Support Vector Machines (SVM), Decision Trees, XGBoost, Multi-Layer Perceptron (MLP), Long Short-Term Memory networks (LSTM), Gated Recurrent Units (GRU), and K-Nearest Neighbors (KNN). This analysis provides a comparative overview of the performance of these ML models in estimating CO and NOx emissions from gas turbines, aiming to highlight the most effective techniques for this critical task. Accurate ML models for predicting gas turbine emissions help reduce environmental impact by enabling real-time adjustments and supporting effective emission control strategies, thus promoting sustainability. |
| title | Application of Machine Learning Models for Carbon Monoxide and Nitrogen Oxides Emission Prediction in Gas Turbines |
| topic | Signal Processing Applications |
| url | https://arxiv.org/abs/2501.17865 |