Skip to main content

Prediction of combustion state through a semi-supervised learning model and flame imaging

Han, Zhezhe, Li, Jian, Zhang, Biao, Hossain, Md. Moinul, Xu, Chuanlong (2020) Prediction of combustion state through a semi-supervised learning model and flame imaging. Fuel, . Article Number 119745. ISSN 0016-2361. (doi:10.1016/j.fuel.2020.119745) (KAR id:85330)

PDF Author's Accepted Manuscript
Language: English
Download (8MB) Preview
[thumbnail of 1-s2.0-S0016236120327411-main.pdf]
Preview
This file may not be suitable for users of assistive technology.
Request an accessible format
Official URL
http://www.sciencedirect.com/science/article/pii/S...

Abstract

Accurate prediction of combustion state is crucial for an in-depth understanding of furnace performance and optimize operation conditions. Traditional data-driven approaches such as artificial neural networks and support vector machine incorporate distinct features which require prior knowledge for feature extraction and suffers poor generalization for unseen combustion states. Therefore, it is necessary to develop an advanced and accurate prediction model to resolve these limitations. This study presents a novel semi-supervised learning model integrating denoising autoencoder (DAE), generative adversarial network (GAN) and Gaussian process classifier (GPC). The DAE network is established to extract representative features of flame images and the network trained through the adversarial learning mechanism of the GAN. Structural similarity (SSIM) metric is introduced as a novel loss function to improve the feature learning ability of the DAE network. The extracted features are then fed into the GPC to predict the seen and unseen combustion states. The effectiveness of the proposed semi-supervised learning model, i.e., DAE-GAN-GPC was evaluated through 4.2 MW heavy oil-fired boiler furnace flame images captured under different combustion states. The averaged prediction accuracy of 99.83% was achieved for the seen combustion states. The new states (unseen) were predicted accurately through the proposed model by fine-tuning of GPC without retraining the DAE-GAN and averaged prediction accuracy of 98.36% was achieved for the unseen states. A comparative study was also carried out with other deep neural networks and classifiers. Results suggested that the proposed model provides better prediction accuracy and robustness capability compared to other traditional prediction models.

Item Type: Article
DOI/Identification number: 10.1016/j.fuel.2020.119745
Additional information: Unmapped bibliographic data: DA - 2020/11/30/ [EPrints field already has value set] JO - Fuel [Field not mapped to EPrints]
Uncontrolled keywords: Combustion state prediction, Novel loss function, Denoising autoencoder, Generative adversarial network, Gaussian process classifier
Subjects: Q Science
Divisions: Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Engineering and Digital Arts
Depositing User: Moinul Hossain
Date Deposited: 05 Jan 2021 22:42 UTC
Last Modified: 16 Feb 2021 14:17 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/85330 (The current URI for this page, for reference purposes)
Hossain, Md. Moinul: https://orcid.org/0000-0003-4184-2397
  • Depositors only (login required):

Downloads

Downloads per month over past year