Feature Selection and Uncertainty Analysis for Bubbling Fluidized Bed Oxy-Fuel Combustion Data

Katerina Marzova,Ivo Bukovsky

doi:10.3390/pr9101757

Abstract

This paper presents a novel feature extraction and validation technique for data-driven prediction of oxy-fuel combustion emissions in a bubbling fluidized bed experimental facility. The experimental data were analyzed and preprocessed to minimize the size of the data set while preserving patterns and variance and to find an optimal configuration of the feature vector. The Boruta Feature Selection Algorithm (BFSA) finds feature vector’s configuration and the Multiscale False Neighbours Analysis (MSFNA) is newly extended and proposed to validate the BFSA’s design for emission prediction to assure minimal uncertainty in mapping between feature vectors and corresponding outputs. The finding is that the standalone BFSA does not reflect various sampling period setups that appeared significantly influencing the false neighborhood in the design of feature vectors for possible emission prediction, and MSFNA resolves that.

Highlights

Two additional variables X[:,3] and X[:,4] were added to test the Boruta Feature Selection Algorithm (BFSA), these columns are a combination of a sine, resp. cosine curve and white noise
The major outcome of the feature selection by BFSA and its newly proposed validation of Multiscale False Neighbours Analysis (MSFNA) is demonstrated via Figures 6–9, where the different sampling periods
Primary airflow Vair,prim, recirculation flow Vrec, and secondary air velocity v air,sec were selected by BFSA less often and differently for each sampling frequency that indicates their lower importance for emission prediction

Summary

Introduction

This paper presents a novel feature extraction and validation technique for data-driven prediction of oxy-fuel combustion emissions in a bubbling fluidized bed experimental facility. The experimental data were analyzed and preprocessed to minimize the size of the data set while preserving patterns and variance and to find an optimal configuration of the feature vector. The. False Neighbours Analysis (MSFNA) is newly extended and proposed to validate the BFSA’s design for emission prediction to assure minimal uncertainty in mapping between feature vectors and corresponding outputs. The finding is that the standalone BFSA does not reflect various sampling period setups that appeared significantly influencing the false neighborhood in the design of feature vectors for possible emission prediction, and MSFNA resolves that.

Methods

Results

Discussion

Conclusion