Accurate determination of homogeneous ignition of single solid fuel particles enabled by machine learning

This work presents an experimental investigation of solid fuel combustion in a laminar flow reactor with high-speed laser diagnostics. The main focus lays on the development of image evaluation approaches for accurate determination of single-particle ignition based on optical measurement data. Homogeneous ignition of individual bituminous coal particles is visualized by simultaneous planar laser-induced fluorescence of OH radicals (OH-LIF) and diffuse backlight-illumination (DBI) techniques at 10kHz. Two coal particle sizes of 90–125μm and 160–200μm are investigated in conventional air and oxy-fuel conditions with increasing oxygen concentrations. A comprehensive experimental data set is established, containing in total 1518 single-particle events and high-quality ground truth labels of ignition delay times. The previously proposed structure and signal (SAS) analysis is evaluated. Errors and uncertainties are evaluated in a sensitivity analysis with variation in the threshold selection, implying inherent restrictions of conventional image processing methods. An improved blob detection approach is applied, enabling feature detection at various scales and higher accuracy in predicting ignition delay times. Moreover, two deep learning architectures, namely residual network (ResNet) and feature pyramid network (FPN) are implemented. Both networks are capable of detecting ignition with significantly higher accuracy and precision than other algorithms in this study. Influences of training data and depth of networks on the prediction performance of a trained model are examined. The current study shows that the hierarchical feature extraction of the convolutions networks clearly facilitates data evaluation for high-speed optical measurements and could be transferred to other solid fuel experiments with similar boundary conditions.