Combining Support Vector Regression and Ant Colony Optimization to Reduce NOx Emissions in Coal-Fired Utility Boilers

Abstract

Combustion optimization has recently demonstrated its potential to reduce NOx emissions in high capacity coal-fired utility boilers. In the present study, support vector regression (SVR), as well as artificial neural networks (ANN), was proposed to model the relationship between NOx emissions and operating parameters of a 300 MW coal-fired utility boiler. The predicted NOx emissions from the SVR model, by comparing with that of the ANN-based model, showed better agreement with the values obtained in the experimental tests on this boiler operated at different loads and various other operating parameters. The mean modeling error and the correlation factor were 1.58% and 0.94, respectively. Then, the combination of the SVR model with ant colony optimization (ACO) to reduce NOx emissions was presented in detail. The experimental results showed that the proposed approach can effectively reduce NOx emissions from the coal-fired utility boiler by about 18.69% (65 ppm). A time period of less than 6 min was required for NOx emissions modeling, and 2 min was required for a run of optimization under a PC system. The computing times are suitable for the online application of the proposed method to actual power plants.

Predicting the net heat of combustion of organic compounds from molecular structures based on ant colony optimization

“…This algorithm is inspired by the behavior of real ant colonies, and the advantages of which are simple and few parameters to be adjusted. As a novel computational approach, ACO algorithm have been successfully used in many fields (Atabati, Zarei, & Borhani, 2010;Jin & Ma, 2009;Schluter, Egea, Antelo, Alonso, & Banga, 2009;T'kindt, Monmarché, Tercinet, & Laugt, 2002;Zheng, Zhou, Wang, & Cen, 2008). The basic idea in the ACO algorithm is simulation of the natural metaphor of real ant colonies' behavior.…”

Prediction and reduction of diesel engine emissions using a combined ANN–ACO method

“…The optimization capability of ACO algorithm in different applications has been elaborately reviewed in [14,15]. Zheng et al [16] used the combination of the support vector regression model and ACO algorithm to optimize the operating parameters of a power plant boiler, thereby decreasing the NO x emissions. Moreover, the combination of ANN model and genetic algorithm (GA) has been employed by Alonso et al [17] to predict and reduce the emissions from a diesel engine.…”

Optimization of Coal-fired Boiler on LS-SVM Model and PSO Algorithms

“…Combustion optimization has been proved to be an effective way to reduce the Nox emissions [3] and unburned carbon in fly ash [4] by carefully setting the operational parameters. Ken Stuck Meyer [5] took Sioux Boiler Plant II (500MW) as the object and reduced Nox emissions.…”