Low NOx combustion optimization based on partial dimension opposition-based learning particle swarm optimization. (15th February 2022)

• Record Type: Journal Article
• Authors: Li, Qingwei; He, Qingfeng; Liu, Zhi
• Is Part Of: Fuel. Volume 310:Part A(2022)
• Publication Date: 2022-02-15
• Subjects: Combustion optimization -- Partial dimension -- Opposition-based learning -- PSO -- NOx; Fuel -- Periodicals; Coal -- Periodicals; Coal; Fuel; Periodicals; 662.6
• DOI: 10.1016/j.fuel.2021.122352
• Languages: English
• ISSNs: 0016-2361

Abstract

Highlights: This paper studied the low NOx combustion optimization based on PDOBLPSO. Opposition-based learning is carried out with some learning probability. The optimized NOx emissions are lower when the learning probability is in [0.1 0.3]. Optimized NOx emissions based on PDOBLPSO are lowest among the studied algorithms. Low NOx combustion optimization based on PDOBLPSO is most stable among the studied algorithms. Abstract: NOx emissions emitted from coal-fired power plants are threatening human beings. Combustion optimization is an important technology to reduce NOx emissions. However, this technology is troubled with premature when swarm algorithms are employed. This paper studied low NOx combustion optimization based on partial dimension opposition-based learning particle swarm optimization. In this algorithm, opposition-based learning is carried out with some learning probability for each dimension of global best particle. The proposed algorithm was applied to the combustion optimization of some 600 MW boiler. Results show that median optimized NOx emissions and mean optimized NOx emissions are lower when the learning probability is located between 0.1 and 0.3. Median optimized NOx emissions and mean optimized NOx emissions based on partial dimension opposition-based learning particle swarm optimization are lowest among the studied algorithms in most cases with limited iterations. Up to 37.72 mg/Nm 3 median NOx emissions can be further reduced by partial dimension opposition-based learning particle swarm optimization compared with the optimized result provided by particle swarm optimization in some case. Besides, low NOx combustion optimization based on partial dimension opposition-based learning particle swarm optimization is most stable among the studied algorithms.