Neural network approach for predicting drum pressure and level in coal-fired subcritical power plant

Oko, Eni; Wang, Meihong; Zhang, Jie

Abstract

There is increasing need for tighter controls of coal-fired plants due to more stringent regulations and addition of more renewable sources in the electricity grid. Achieving this will require better process knowledge which can be facilitated through the use of plant models. Drum-boilers, a key component of coal-fired subcritical power plants, have complicated characteristics and require highly complex routines for the dynamic characteristics to be accurately modelled. Development of such routines is laborious and due to computational requirements they are often unfit for control purposes. On the other hand, simpler lumped and semi empirical models may not represent the process well. As a result, data-driven approach based on neural networks is chosen in this study. Models derived with this approach incorporate all the complex underlying physics and performs very well so long as it is used within the range of conditions on which it was developed. The model can be used for studying plant dynamics and design of controllers. Dynamic model of the drum-boiler was developed in this study using NARX neural networks. The model predictions showed good agreement with actual outputs of the drum-boiler (drum pressure and water level).

Citation

Oko, E., Wang, M., & Zhang, J. (2015). Neural network approach for predicting drum pressure and level in coal-fired subcritical power plant. Fuel, 151, 139-145. https://doi.org/10.1016/j.fuel.2015.01.091

• Acceptance Date: Jan 27, 2015
• Online Publication Date: Feb 7, 2015
• Publication Date: Jul 1, 2015
• Deposit Date: Mar 7, 2016
• Publicly Available Date: Mar 7, 2016
• Journal: Fuel
• Print ISSN: 0016-2361
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 151
• Pages: 139-145
• DOI: https://doi.org/10.1016/j.fuel.2015.01.091
• Keywords: NARX neural networks; Subcritical coal-fired power plant; Drum-boiler; gPROMS modelling and simulation
• Public URL: https://hull-repository.worktribe.com/output/412398
• Publisher URL: http://www.sciencedirect.com/science/article/pii/S0016236115001118
• Additional Information: Author's accepted manuscript of article published in: Fuel, 2015, v.151 : The 10th European Conference on Coal Research and its Applications