Auto-Encoder-Extreme Learning Machine Model for Boiler NOx Emission Concentration Prediction

TL;DR

This paper introduces an integrated AE-ELM model that combines mutual information, auto-encoders, and extreme learning machines to accurately predict boiler NOx emission concentrations, demonstrating improved performance over existing models.

Contribution

The paper presents a novel AE-ELM framework that incorporates variable importance analysis and feature extraction for enhanced NOx emission prediction.

Findings

The proposed model outperforms state-of-the-art models in predicting NOx emissions.

Feature extraction via AE improves model accuracy.

Variable importance analysis effectively selects relevant input variables.

Abstract

An automatic encoder (AE) extreme learning machine (ELM)-AE-ELM model is proposed to predict the NOx emission concentration based on the combination of mutual information algorithm (MI), AE, and ELM. First, the importance of practical variables is computed by the MI algorithm, and the mechanism is analyzed to determine the variables related to the NOx emission concentration. Then, the time delay correlations between the selected variables and NOx emission concentration are further analyzed to reconstruct the modeling data. Subsequently, the AE is applied to extract hidden features within the input variables. Finally, an ELM algorithm establishes the relationship between the NOx emission concentration and deep features. The experimental results on practical data indicate that the proposed model shows promising performance compared to state-of-art models.