A combined NOx emission prediction model based on semi-empirical model and black box models. (1st February 2023)

• Record Type: Journal Article
• Authors: Li, Shicheng; Ma, Suxia; Wang, Fang
• Is Part Of: Energy. Volume 264(2023)
• Publication Date: 2023-02-01
• Subjects: Combined model -- NOx emission -- 1D model -- Artificial intelligence; Power resources -- Periodicals; Power (Mechanics) -- Periodicals; Energy consumption -- Periodicals; 333.7905
• DOI: 10.1016/j.energy.2022.126130
• Languages: English
• ISSNs: 0360-5442

Abstract

Abstract: Coal fired power plants account for a large part of China's NOx emission. A precise prediction of the NOx emission can effectively improve the pollutant control level and operation ability. In this study, a novel combined model based on 1D semi-empirical model and three black box models is proposed to predicted the dynamics of NOx emission of a 350 MW circulating fluidized bed (CFB) boiler. In addition, an improved differential evolution algorithm based on non-negative constraint theory is used to determine the optimal weight coefficient of the combined model. Three different working condition datasets of the CFB boiler are acquired to evaluate the performance of combined model. The results of the experiments and discussions show that the combined model overcomes the limitation of the single model and achieves better prediction results. Highlights: A combined model based on semi-empirical model and black box models is proposed. An improved differential evolution is applied to the combined model. Dynamic prediction of NOx emission of CFB boiler under different operating conditions. The proposed model performs better than single models.