Hybrid Selection Method of Feature Variables and Prediction Modeling for Municipal Solid Waste Incinerator Temperature
Open Access
Abstract
It is difficult to establish an accurate mechanism model for prediction incinerator temperatures due to the comprehensive complexity of the municipal solid waste (MSW) incineration process. In this paper, feature variables of incineration temperature are selected by combining with mutual information (MI), genetic algorithms (GAs) and stochastic configuration networks (SCNs), and the SCN-based incinerator temperature model is obtained simultaneously. Firstly, filter feature selection is realized by calculating the MI value between each feature variable and the incinerator temperature from historical data. Secondly, the fitness function of GAs is defined by the root mean square error of the incinerator temperature obtained by training SCNs, and features obtained by MI methods are searched iteratively to complete the wrapper feature selection, where the SCN-based incinerator temperature prediction model is obtained. Finally, the proposed model is verified by MSW incinerator temperature historical data. The results show that the SCN-based prediction model using the hybrid selection method can better predict the change trend of incinerator temperature, which proves that the SCNs has great development potential in the field of prediction modeling.Keywords
Funding Information
- National Natural Science Foundation of China (61873009)
- Beijing Natural Science Foundation of China (4192009)
This publication has 27 references indexed in Scilit:
- Hybrid filter–wrapper feature selection for short-term load forecastingEngineering Applications of Artificial Intelligence, 2015
- An overview of characteristics of municipal solid waste fuel in China: Physical, chemical composition and heating valueRenewable and Sustainable Energy Reviews, 2014
- A survey on feature selection methodsComputers and Electrical Engineering, 2014
- Efficient semi-supervised feature selection with noise insensitive trace ratio criterionNeurocomputing, 2013
- Survey on data-driven industrial process monitoring and diagnosisAnnual Reviews in Control, 2012
- Feature extraction and selection based on vibration spectrum with application to estimating the load parameters of ball mill in grinding processControl Engineering Practice, 2012
- Mathematical modeling of combustion in a grate-fired boiler burning straw and effect of operating conditions under air- and oxygen-enriched atmospheresRenewable Energy, 2010
- A diffusion model for particle mixing in a packed bed of burning solidsFuel, 2005
- Characterization of municipal solid waste combustion in a grate furnaceWaste Management, 2003
- Wrappers for feature subset selectionArtificial Intelligence, 1997