Data-driven multi-objective optimisation of coal-fired boiler combustion systems
- Submitting institution
-
Swansea University / Prifysgol Abertawe
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 52254
- Type
- D - Journal article
- DOI
-
10.1016/j.apenergy.2018.07.101
- Title of journal
- Applied Energy
- Article number
- -
- First page
- 446
- Volume
- 229
- Issue
- -
- ISSN
- 0306-2619
- Open access status
- Compliant
- Month of publication
- November
- Year of publication
- 2018
- URL
-
https://ore.exeter.ac.uk/repository/handle/10871/33710
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
-
- Research group(s)
-
-
- Citation count
- 10
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- In a coal-fired power plant, selecting operating parameters to reduce emissions without reducing efficiency is a challenging problem. Recently, a few methods for optimising these multiple objectives simultaneously using data-driven models of efficiency and emissions have emerged. However, the uncertainty arising from data paucity or measurement errors has never been addressed. For the first time, we show how to quantify such uncertainties. The novel approach enables operators to select parameters that are most likely to achieve a desired level of emissions without sacrificing performance. We demonstrated this on real data collected from a live power plant in Jianbi province, China.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -