Conference Paper

Use of differential evolution in low NOx combustion optimization of a coal-fired boiler

DOI: 10.1109/ICNC.2010.5583524 Conference: Natural Computation (ICNC), 2010 Sixth International Conference on, Volume: 8
Source: IEEE Xplore


The present work focuses on low NOx emissions combustion modification of a 300MW dual-furnaces coal-fired utility boiler through a combination of support vector regression (SVR) and a novel and modern differential evolution optimization technique (DE). SVR, used as a more versatile type of regression tool, was employed to build a complex model between NOx emissions and operating conditions by using available experimental results in a case boiler. The trained SVR model performed well in predicting the NOx emissions with an average relative error of less than 1.14% compared with the experimental results in the case boiler. The optimal ten inputs (namely operating conditions to be optimized by operators of the boiler) of NOx emissions characteristics model were regulated by DE so that low NOx emissions were achieved, given that the boiler load is determined. Two cases were optimized in this work to check the possibility of reducing NOx emissions by DE under high and low boiler load. The time response of DE was typical of 20 sec, at the same time with the better quality of optimized results. Remarkable good results were obtained when DE was used to optimize NOx emissions of this boiler, supporting its applicability for the development of an advanced on-line and real-time low NOx emissions combustion optimization software package in modern power plants.

Download full-text


Available from: Ligang Zheng, Sep 08, 2015
  • Source
    • "In the past decades, artificial intelligent approaches have been extensively studied and applied to complex process modeling, prediction and optimization, such as emissions prediction and control, water quality improvement and optimization of system performance [1] [2] [3] [4] [5] [6] [7] [8] [9] [10]. As an important application, combustion optimization has also been investigated based on diverse techniques [11], including Genetic Algorithms (GA) [12] [13] [14] [15], Data Mining (DM) [16], Artificial Immune Algorithms (AIA) [17], Estimation of Distribution Algorithms (EDA) [18] and Differential Evolution [19]. Biomimetic optimization is a class of optimization technique that simulates behaviors of natural creatures. "
    [Show abstract] [Hide abstract]
    ABSTRACT: A combustion optimization framework for on-line applications is proposed based on improved Artificial Bee Colony (ABC) algorithm. First, an enhanced General Regression Neural Network (Enhanced-GRNN) is designed with Gaussian Adaptive Resonance Theory (GART) learning and polynomial extrapolation to get better on-line performance and extreme value extraction. Then two improvements to classical ABC algorithm are proposed: a multi-segment method for evaluating the quality of food sources in employed bee phase based on an analysis of probability distribution of foods in different iteration segments; and a memory-based strategy for onlooker bees to find new foods and evaluate their quality considering better moving directions and steps. A cost function was also designed in this study, considering the factors of coal consumption, NOX emissions and the recycling potential of fly ash. Experiments with data samples from a 600 MW utility boiler show that the proposed framework is fast and flexible, and that the on-line optimization results can provide reasonable optimal advices to operating engineers at coal-fired power plants.
    Full-text · Article · Feb 2016
  • Source
    • "Up to now, several global optimization algorithms were employed to optimize NO x emission from coal combustion process such as genetic algorithm (GA) [1] [2], particle swarm optimization (PSO) [3] [4], ant colony optimization (ACO) [5], estimation of distribution algorithm (EDA) [6], simulated annealing (SA) [7], and differential evolution (DE) [8]. However, the slow convergence speed and the poor solution quality are two unresolved problems of above mentioned global optimization algorithms. "
    [Show abstract] [Hide abstract]
    ABSTRACT: This study presents a new approach based on a pattern search algorithm to solve combustion optimization problem (i.e. achieving expected goals by optimizing the parameters of the combustion process). In the optimization problem, the objective function was implicitly expressed by a surrogate model, which was illustrated by a support vector machine. Ten inputs for this “black box” surrogate model were chosen as design variables of the pattern search algorithm. Then, the proposed method was applied to a coal combustion process, aiming at reducing the nitrogen oxides (NOx). The outcome is very encouraging and suggests that PS methods may be very efficient when solving low NOx combustion optimization problem.
    Full-text · Conference Paper · Jul 2011