Modified Non-Dominated Sorting Genetic Algorithm (MNSGA-II) Applied in Multi-Objective Optimization of a Coal-Fired Boiler Combustion

Abstract:

This paper discussed application of modified non-dominated sorting genetic algorithm-II (MNSGA-II) to multi-objective optimization of a coal-fired boiler combustion, the two objectives considered are minimization of overall heat loss and NOx emissions from coal-fired boiler. In the first step, BP neural network was proposed to establish a mathematical model predicting the NOx emissions & overall heat loss from the boiler. Then, BP model and the non-dominated sorting genetic algorithm II (NSGA-II) were combined to gain the optimal operating parameters. According to the problems such as premature convergence and uneven distribution of Pareto solutions exist in the application of NSGA-II, corresponding improvements in the crowded-comparison operator and crossover operator were performed. The optimal results show that MNSGA-II can be a good tool to solve the problem of multi-objective optimization of a coal-fired combustion, which can reduce NOx emissions and overall heat loss effectively for the coal-fired boiler. Compared with NSGA-II, the Pareto set obtained by the MNSGA-II shows a better distribution and better quality.

• Periodical: Advanced Materials Research (Volumes 694-697)
• Pages: 2850-2855
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.694-697.2850
• Online since: May 2013
• Authors: Ting Fang Yu, Xia Wang, Chun Hua Peng
• Keywords: BP Neural Network (BPNN), Coal-Fired Boiler Combustion, MNSGA-Ii, Multi-Objective Optimization (MOP), Pareto Solutions Set

References

[1] Liu M., Yi B., Gao X.J., et al. Nitrogen oxide emissions status of thermal power plants in China and corresponding suggestion [J]. Environmental Protection, 2008(8), vol.402：7-10

[2] Xu, C., Lu J.H. ,Zhen, Y., An Experiment and analysis for a Boiler Combustion Optimization on Efficiency and NOx Emissions[J].Boiler Technology, 2006,37 (5) ：69-74

[3] Wang ,P.,H., Li, L., Chen ,Q., et al. Research on applications of artificial intelligence to combustion optimization in a coal-fried boiler[J] . Proceedings of the CSEE , 2004 , 24(4): 184-188(in Chinese).

[4] Gao, Z.,Y., Guo, Zhen, Hu,J.,Q.,et al．Multi-objective combustion optimization and flame reconstruction for W shaped boiler based on support vector regression and numerical simulation[J]. Proceedings of the CSEE, 2011,31(5):13-19

[5] Wu, F., Zhou, H., Zhao, J.,P., etal. A comparative study of the multi-objective optimization algorithms for coal-fired boilers[J]. Expert Systems with Applications, 2011, 21:7179-7185

DOI: 10.1016/j.eswa.2010.12.042

[6] Knowles, J. and Corne, D. The Pareto archived evolution strategy: a new baseline algorithm for multi-objective optimization[C]. Proceedings of the 1999 Congress on Evolutionary Computation, IEEE Press, New Jersy, 1999, 98–105

DOI: 10.1109/cec.1999.781913

[7] Kim, M., Hiroyasu, T., Miki, M., and Watanabe, S. SPEA2+: improving the performance of the strength Pareto evolutionary algorithm 2. Computer Science, 3242, 2004, 742–751

DOI: 10.1007/978-3-540-30217-9_75

[8] Kaylynmoy Deb, Amrit Partap, Sameer Agarwal, et al. A fast and elitist multi-objective genetic algorithm：NSGA-II[J]. IEEE Transactions on Evolutionary Computation, 2002, 6(22):182-197.

DOI: 10.1109/4235.996017

[9] Srinivas,N. and Deb, K. Multi-objective optimization using non-dominated sorting in genetic algorithms. Evolutionary Computation, 1994, 2(3), 221–248

DOI: 10.1162/evco.1994.2.3.221

[10] Elson Agastra, Leonardo Lucci, etal. Modified NSGA-II algorithm for multiobjective optimization of compact high-efficiency square horns[J], International Journal of RF and Microwave Computer-Aided Engineering,2011, 21(2):174-181

DOI: 10.1002/mmce.20501

[11] Luo, B.,Zheng, J. H., Xie, J. L., and Wu, J. Dynamic crowding distance — a new diversity maintenance strategy for MOEAs[C]. Proceedings of the IEEE International Conference on Natural Computation, IEEE Press, New Jersy, 2008:580–585

DOI: 10.1109/icnc.2008.532