An introduction to support Vector Machines: and other kernel-based learning methods
An introduction to support Vector Machines: and other kernel-based learning methods
A Simple Decomposition Method for Support Vector Machines
Machine Learning
Ant colony optimization theory: a survey
Theoretical Computer Science
A hybrid approach for feature subset selection using neural networks and ant colony optimization
Expert Systems with Applications: An International Journal
Application of support vector machines to corporate credit rating prediction
Expert Systems with Applications: An International Journal
Environmental Modelling & Software
Expert Systems with Applications: An International Journal
Neural Computing and Applications
Application of ACO in continuous domain
ICNC'06 Proceedings of the Second international conference on Advances in Natural Computation - Volume Part II
A comparative study of the multi-objective optimization algorithms for coal-fired boilers
Expert Systems with Applications: An International Journal
Engineering Applications of Artificial Intelligence
Hi-index | 12.05 |
NOx emissions from power plants pose terrible threat to the surrounding environment. The aim of this work is to achieve low NOx emissions form a coal-fired utility boiler by using combustion optimization. Support vector regression (SVR) was proposed in the first stage to model the relation between NOx emissions and operational parameters of the utility boiler. The grid search method, by comparing with GA, was preferably chosen as the approach for the selection of SVR's parameters. A mass of NOx emissions data from the utility boiler was employed to build the SVR model. The predicted NOx emissions from SVR model were in good agreement with the measured. In the second stage, two variants of ant colony optimization (ACO) as well as genetic algorithm (GA) and particle swarm optimization (PSO) were employed to find the optimum operating parameters to reduce the NOx emissions. The results show that the hybrid algorithm by combining SVR and optimization algorithms with the exception of PSO can effectively reduce NOx emissions of the coal-fired utility boiler below the legislation requirement of China. Comparison among various algorithms shows the performance of the well-designed ACO outperforms those of classical GA and PSO in terms of the quality of solution and the convergence rate.