Modeling for the bed temperature 2D-interval prediction of CFB boilers based on long-short term memory network

Feng Hong, Dongteng Long, Jiyu Chen and Mingming Gao

Energy, 2020, vol. 194, issue C

Abstract: Circulating fluidized bed (CFB) units play an important role in thermal power generation system in China. Because of advantages of wide fuel flexibility and low pollutant emissions, the proportion of CFB units is increasing constantly. For an accurate bed temperature changing trend prediction in advance, sequence prediction is needed, and accurate bed temperature change interval prediction is also required, a sequence-interval prediction indicates the 2D-interval prediction. This paper presents a bed temperature sequence interval prediction model for typical 300 MW CFB unit using long-short term memory network (LSTM) based on actual operation unit, and the coal feed rate, primary air rate and secondary air rate are selected as input variables using grey relational analysis. Previous bed temperature and automatic generation control instruction are introduced to the prediction models, and the length of input variables sequences are optimized using genetic algorithm. Several model patterns are compared and discussed, and the effect of introducing of automatic generation control instruction is investigated. The results reveal that the model structure could effectively described the characteristic of bed temperature of CFB unit and the model could achieve an accurate 2D-interval trend prediction of bed temperature.

Keywords: CFB boilers; 2D-interval prediction; Bed temperature; Dynamic modeling; LSTM (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (10)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544219324284
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:194:y:2020:i:c:s0360544219324284

DOI: 10.1016/j.energy.2019.116733

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().