Skip to main content

A flame imaging based online deep learning model for predicting NOx emissions from an oxy-biomass combustion process

Qin, Li, Lu, Gang, Hossain Md Moinul, Hossain Md Moinul, Morris, Andy, Yan, Yong (2021) A flame imaging based online deep learning model for predicting NOx emissions from an oxy-biomass combustion process. IEEE Transactions on Instrumentation and Measurement, . ISSN 0018-9456. (doi:10.1109/TIM.2021.3132998) (KAR id:91751)

PDF Author's Accepted Manuscript
Language: English
Download (1MB) Preview
[thumbnail of Manuscript with bios-Ms. No. TIM-21-02881R2[1].pdf]
Preview
This file may not be suitable for users of assistive technology.
Request an accessible format
Official URL
http://dx.doi.org/10.1109/TIM.2021.3132998

Abstract

To reduce NOx (Nitrogen Oxide) emissions from fossil fuel and biomass fired power plants, online prediction of NOx emissions is important in the plant operation. Data-driven models have been developed to predict NOx emissions from various combustion processes with good accuracy. However, such models have initially been built based on known combustion conditions, which are historically ‘seen’. For new conditions, which are ‘unseen’, these models usually perform unwell. In this study, an ODL (Online Deep Learning) model is proposed to predict NOx emissions from an oxy-biomass combustion process for ‘seen’ and ‘unseen’ combustion conditions based on source deep learning and condition recognition models. The ODL model is mainly built based on ‘unseen’ combustion conditions. A new objective function that consists of regression loss and distillation loss is introduced in the ODL model to improve the prediction accuracy. The ODL model is examined using boiler operation data, flame temperature maps and NOx data obtained under a range of oxy-biomass combustion conditions on an Oxy-fuel Combustion Test Facility. Flame images acquired using a dedicated imaging system are used for computing the temperature distribution of the flame through two-colour pyrometry. The results demonstrate that the proposed model is capable of predicting NOx emissions under ‘seen’ and ‘unseen’ conditions with a mean absolute percentage error of less than 3%, for the 1st, 2nd, and 3rd updates.

Item Type: Article
DOI/Identification number: 10.1109/TIM.2021.3132998
Projects: [UNSPECIFIED] A Condition-based Monitoring and Advisory Tool for Utility Boilers
Uncontrolled keywords: NOx prediction, online deep learning, flame temperature map, condition monitoring, oxy-biomass combustion
Subjects: T Technology > TA Engineering (General). Civil engineering (General) > TA165 Engineering instruments, meters etc. Industrial instrumentation
Divisions: Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Engineering and Digital Arts
Funders: Organisations -1 not found.
Depositing User: Gang Lu
Date Deposited: 28 Nov 2021 17:17 UTC
Last Modified: 13 Jan 2022 15:48 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/91751 (The current URI for this page, for reference purposes)
Lu, Gang: https://orcid.org/0000-0002-9093-6448
Hossain Md Moinul, Hossain Md Moinul: https://orcid.org/0000-0003-4184-2397
Morris, Andy: https://orcid.org/0000-0001-9908-0431
Yan, Yong: https://orcid.org/0000-0001-7135-5456
  • Depositors only (login required):