Research on NOx emission of coal-fired unit based on multi-model clustering ensemble
by Chenggang Zhen; Huaiyuan Liu; Hanyong Hao
International Journal of Simulation and Process Modelling (IJSPM), Vol. 15, No. 1/2, 2020

Abstract: The predictive control of NOx emission generated by coal-fired units has an important impact on economic benefits of power station and control of environmental pollution. In order to enhance the accuracy of prediction model, a modelling method of boiler NOx emission based on voting multi-model soft clustering ensemble (VMSC) is proposed. The data space is divided into three sub-space according to the level of NOx emission, and the variables that participate in clustering are determined by using variable weight based on relevant analysis and hierarchical clustering utilised information entropy. The proposed algorithm VMSC is used to obtain new membership degree matrix of each sub-space. The multiple least squares support vector machine (LSSVM) models of each subspace are compromised by the least-squares method fused membership degree. The simulation results show that the VMSC algorithm which merges soft fuzzy C-means clustering (SFCM) and genetic algorithm-soft fuzzy C-means clustering (GA-SFCM) improve the accuracy of clustering, and the simulation performance is better than other selected models. The integrated model VMSC-LSSVM can achieve accurate prediction for NOx emission of utility boiler and effectively solve the problem that the model used single method to modelling is weak generalisation.

Online publication date: Wed, 29-Apr-2020

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Simulation and Process Modelling (IJSPM):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?


Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com