An ensemble deep learning model for exhaust emissions prediction of heavy oil-fired boiler combustion

• Published in: Fuel (Guildford) 2022-01, Vol.308, p.121975, Article 121975
• Main Authors: Han, Zhezhe, Li, Jian, Hossain, Md. Moinul, Qi, Qi, Zhang, Biao, Xu, Chuanlong
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Boilers; Carbon dioxide; Carbon dioxide emissions; Combustion; Confidence intervals; Deep learning; Emission prediction; Emissions; Engines; Ensemble method; Environmental protection; Exhaust emissions; Feature extraction; Flame image; Forecasting; Gaussian process; Gaussian process regression; Learning algorithms; Machine learning; Mathematical models; Neural networks; Nitrogen oxides; Optimization; Predictions; Stacked denoising autoencoder; Statistical analysis; Support vector machines
• ISSN: 0016-2361; 1873-7153
• DOI: 10.1016/j.fuel.2021.121975

•An ensemble deep learning model is established for predicting NOx and CO2 emissions.•Effects of image features and feature forecasters on the prediction performance are investigated.•Different machine learning engines are combined in a nonlinear way.•The model is evaluated through heavy oil-fired boiler combustion.•Accurate point prediction and confidence interval of NOx and CO2 emissions can be provided simultaneously. Accurate and reliable prediction of exhaust emissions is crucial for combustion optimization control and environmental protection. This study proposes a novel ensemble deep learning model for exhaust emissions (NOx and CO2) prediction. In this ensemble learning model, the stacked denoising autoencoder is established to extract the deep features of flame images. Four forecasting engines include artificial neural network, extreme learning machine, support vector machine and least squares support vector machine are employed for preliminary prediction of NOx and CO2 emissions based on the extracted image deep features. After that, these preliminary predictions are combined by Gaussian process regression in a nonlinear manner to achieve a final prediction of the emissions. The effectiveness of the proposed ensemble deep learning model is evaluated through 4.2 MW heavy oil-fired boiler flame images. Experimental results suggest that the predictions are achieved from the four forecasting engines are inconsistent, however, an accurate prediction accuracy has been achieved through the proposed model. The proposed ensemble deep learning model not only provides accurate point prediction but also generates satisfactory confidence interval.