Work

Flue Gas Oxygen Content Model Based on Bayesian Optimization Main–Compensation Ensemble Algorithm in Municipal Solid Waste Incineration Process

Year: 2025

Type: article

Abstract: Flue gas oxygen content is one of the important parameters in municipal solid waste incineration (MSWI) process. And its stable control is closely related to the incineration efficiency and pollutant emission. The construction of a high-precision and interpretable flue gas oxygen content model is the basis for achieving its optimal control. However, the existing methods have problems such as poor interpretability, low model accuracy, and complex manual hyperparameter adjustment. In view of the above problems, the article proposes a flue gas oxygen content model based on Bayes-ian optimization (BO) main-complement ensemble algorithm. Firstly, the ensemble TS fuzzy re-gression tree (EnTSFRT) is used to construct the main model. Then, the long short term memory network (LSTM) is used to construct the compensation model with the error of the EnTSFRT model as the true value. The weighted value of the main and compensation models is used as the output. Finally, based on the BO algorithm, the hyperparameters of the constructed main-complement ensemble model are optimized to achieve high performance model. Experi-mental results based on real MSWI process data show that the proposed method has good per-formance.

Source: Sustainability

DOI: 10.3390/su17073048

Authors: Weiwei Yang, Jian Tang, Hao Tian, Tianzheng Wang

Institution: Beijing University of Technology

Language: English

Topic: Municipal Solid Waste Management

Subfield: Waste Management and Disposal

Field: Environmental Science

Domain: Physical Sciences

SDGs: Responsible consumption and production, Affordable and clean energy

Open Access status: gold

Estimated APC paid: $2,896