A Machine Learning Based Approach for Statistical Analysis of Detonation Cells from Soot Foils

Abstract

This study presents a novel algorithm based on machine learning (ML) for the precise segmentation and measurement of detonation cells from soot foil images, addressing the limitations of manual and primitive edge detection methods prevalent in the field. Using advances in cellular biology segmentation models, the proposed algorithm is designed to accurately extract cellular patterns without a training procedure or dataset, which is a significant challenge in detonation research. The algorithm's performance was validated using a series of test cases that mimic experimental and numerical detonation studies. The results demonstrated consistent accuracy, with errors remaining within 10%, even in complex cases. The algorithm effectively captured key cell metrics such as cell area and span, revealing trends across different soot foil samples with uniform to highly irregular cellular structures. Although the model proved robust, challenges remain in segmenting and analyzing highly complex or irregular cellular patterns. This work highlights the broad applicability and potential of the algorithm to advance the understanding of detonation wave dynamics.

Figures (12)

• Figure 1: (Left) Time sequence of temperature contours ($\tau_0$ to $\tau_5$) showing the evolution of a planar detonation wave front with triple point collisions at A and B. (Right) Numerical soot foil showing triple point trajectories through space.
• Figure 2: UNet architecture for cell segmentation task adapted from cellpose_stringer-2020
• Figure 3: Manufactured data shown on the left with metrics marked in yellow and the right plot shows the diffused image.
• Figure 4: Case 4 cellular pattern shown in the left plot and cells detected (red) by cyto2 model in the right plot.
• Figure 5: Detected cells marked with red outlines overlaid on figures from Fig. 5 in smirnov2024modelling.