(42b) Hybrid Predictive Emissions Monitoring System (HPEMS) for NOx Emissions from Natural Gas Fired Boilers

The accurate monitoring of NO_x and O₂ emissions is critical for ensuring compliance with environmental regulations and optimizing boiler performance. Traditional Continuous Emission Monitoring Systems (CEMS) are widely used but can be costly and complex to maintain. This study presents a hybrid modeling (HPEMS) approach that integrates fundamental principles with advanced machine learning techniques to predict NO_x and O₂ emissions, offering a promising alternative to CEMS.

The proposed model leverages well-established fundamental principles from classical literature [1, 2], which provide a robust theoretical foundation. These principles are combined with modern machine learning algorithms, which enhance the model’s predictive capabilities by learning from historical emission data. This hybrid approach [3, 4] addresses the limitations of existing predictive emissions modelling systems models (PEMS) that are typically constrained to narrow operating windows, by extending applicability across a wide range of boiler loads.

Preliminary results indicate that while the hybrid model does not yet surpass the accuracy of traditional CEMS, it shows significant promise. Ongoing work aims to refine the model and improve its performance. This comprehensive modeling framework represents a significant advancement in emission monitoring technology, providing a scalable solution that can adapt to varying operational conditions and regulatory requirements.

References

[1] T.W. Chien, H. Chu, W.C. Hsu, T.K. Tseng, C.H. Hsu & K.Y. Chen (2003) A Feasibility Study on the Predictive Emission Monitoring System Applied to the Hsinta Power Plant of Taiwan Power Company, Journal of the Air & Waste Management Association, 53:8, 1022-1028, DOI: 10.1080/10473289.2003.10466241

[2] Timo Korpela, Pekka Kumpulainen, Yrjö Majanne, Anna Häyrinen, Model based NOx emission monitoring in natural gas fired hot water boilers, IFAC-PapersOnLine, Volume 48, Issue 30, 2015, Pages 385-390, ISSN 2405-8963, https://doi.org/10.1016/j.ifacol.2015.12.409.

[3] Joel Sansana, Mark N. Joswiak, Ivan Castillo, Zhenyu Wang, Ricardo Rendall, Leo H. Chiang, Marco S. Reis, Recent trends on hybrid modeling for Industry 4.0, Computers & Chemical Engineering, Volume 151, 2021, 107365, ISSN 0098-1354, https://doi.org/10.1016/j.compchemeng.2021.107365.

[4] Chen, Yingjie & Ierapetritou, Marianthi. (2020). A framework of hybrid model development with identification of plant‐model mismatch. AIChE Journal. 66. 10.1002/aic.16996.