arXiv subjects

Mhedine Alicherif

Publications and source records attributed to Mhedine Alicherif.

3 recordsLinked to original sources

arXiv2026

Deep Learning-Based Characterization of Detonation-Cell Size Distributions in Soot-Foil Records

The geometric size and regularity of detonation cells are key physical parameters for characterizing detonation waves. Traditional manual measurement of soot foils is time-consuming and subjective, while existing computer vision techniques often exhibit poor generalization on real experimental images with high noise, blurred boundaries, and severe overlapping. To address this, we propose a novel method for automated recognition and high-order feature extraction of detonation cells based on deep learning instance segmentation (Mask R-CNN). By constructing a custom heterogeneous dataset (numerical simulations and physical experiments) and integrating transfer learning, the model achieves accurate pixel-level mask prediction within highly noisy flow fields. Results indicate high pixel-level agreement in benchmark validations and strong robustness against noise in complex real-world soot foils. Predicted average cell sizes agree well with manual measurements, yielding relative errors under 2% and 3.5% for regular and irregular conditions, respectively. Sensitivity ablation experiments confirm the model's scale adaptability and guided the establishment of a standardized preprocessing paradigm for appropriate image patching. Overcoming the limitation of extracting only global average sizes, this model achieves automated tracking of the transient spatial evolution of cell sizes along the propagation direction. Furthermore, it quantitatively extracts high-order regularity features, such as the irregularity index (RI) and standard deviation of cell deflection angles, demonstrating consistency with theoretical expectations. The proposed method enhances the efficiency and objectivity of statistical analysis, providing a powerful data extraction tool for experimental and numerical soot foils.

eess.IV↗

arXiv2026

An Interpretable Operator-Learning Model for Electric Field Profile Reconstruction in Discharges Based on the EFISH Method

Machine learning (ML) models have recently been used to reconstruct electric field distributions from EFISH signal profiles-the 'inverse EFISH problem'. This addresses the line-of-sight EFISH inaccuracy caused by the Gouy phase shift in focused beams. A key benefit of this approach is that the accuracy of the reconstructed profile can be directly checked via a 'forward transform' of the EFISH equation. Motivated by this latest success, the present study introduces a novel ML model with markedly improved performance. Based on a more powerful operator-learning architecture, it goes beyond the ANNs and CNNs employed previously. Termed Decoder-DeepONet (DDON), its main strength is learning function-to-function mappings, essential for recovering electric field profiles of unknown shape. The superior performance of DDON is exemplified via a comparison with our published CNN model and the feasibility of a classical mathematical method, as well as its application to both discharge simulations and experimental EFISH data from a nanosecond pulsed discharge. In almost all cases, the DDON model exhibits better generalizability, higher prediction accuracy, and wider applicability. Furthermore, the intrinsic nature of this operator-learning architecture renders it less sensitive to the exact location(s) of the acquired data, enabling electric field reconstruction even with seemingly 'incomplete' input profiles--an issue often accompanying poor signal sensitivity. We also employ Integrated Gradients (IG) to identify the signal regions most critical to reconstruction accuracy, providing guidance on the optimal sampling window for EFISH acquisition. Overall, we believe that the DDON model is a robust and comprehensive model which can be readily applied to reconstruct 'bell-shaped' electric field profiles with an existing axis of symmetry, especially in non-equilibrium plasmas.

physics.plasm-ph↗

arXiv2026

Toward Quantitative Electric-Field Measurements of Inception Clouds in Nanosecond Discharges Using E-FISH Assisted by Machine Learning

This study investigates the spatio-temporal evolution of the electric field during the early stages of a nanosecond positive corona discharge in atmospheric-pressure air by combining time-resolved E-FISH measurements, machine-learning-assisted field inversion (based on a recently developed operator-learning model), and iCCD optical emission imaging. The objective is to quantitatively characterize the electric field in the vicinity of the high-voltage electrode during inception and the transition toward streamer formation. By averaging over a large number of discharge events and operating in a regime where the discharge remains statistically axisymmetric, the proposed approach enables reconstruction of the electric-field profiles with nanosecond resolution. The results show a rapid increase of the field during the first nanoseconds, followed by the formation of a shell-like structure exhibiting the highest reduced fields prior to destabilization. The reconstructed reduced electric-field magnitude reaches peak values in the range of approximately 230-270 Td, with an estimated uncertainty of about 20-30% associated with calibration and profile-shape effects. These values correspond to the regime where electron-impact excitation and photoionization processes become highly efficient, consistent with the observed transition from a stable inception cloud to streamer destabilization. After the onset of streamer branching, increasing asymmetry limits the applicability of the inversion, and the reconstructed fields represent averaged contributions rather than the local field at individual streamer heads. The methodology thus identifies the conditions under which quantitative E-field mapping is reliable and establishes a framework for extending electric-field diagnostics to the inception phase of nanosecond atmospheric discharges.

physics.plasm-ph↗