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

TL;DR

This paper introduces a machine learning algorithm for automatic, accurate segmentation of detonation cells from soot foil images, overcoming manual methods' limitations and enabling better analysis of detonation wave structures.

Contribution

The study develops a dataset-free ML-based segmentation algorithm for detonation cells, improving accuracy and efficiency over traditional manual and primitive edge detection techniques.

Findings

Consistent segmentation accuracy within 10% error margin.

Effective extraction of key cell metrics such as area and span.

Robust performance across various cellular structures.

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.