Evolutionary computing-based image segmentation method to detect defects and features in Additive Friction Stir Deposition Process

TL;DR

This paper introduces an evolutionary computing-based image segmentation method using Particle Swarm Optimization to detect defects and features in Additive Friction Stir Deposition processes, enhancing defect detection and interface analysis.

Contribution

It presents a novel integration of PSO with gradient and distance transform analysis for precise segmentation and visualization in AFSD defect detection.

Findings

PSO automatically finds optimal segmentation thresholds (156-173).

Multi-channel visualization highlights defect regions and material transitions.

Attention-based analysis identifies inhomogeneities and incomplete bonding.

Abstract

This work proposes an evolutionary computing-based image segmentation approach for analyzing soundness in Additive Friction Stir Deposition (AFSD) processes. Particle Swarm Optimization (PSO) was employed to determine optimal segmentation thresholds for detecting defects and features in multilayer AFSD builds. The methodology integrates gradient magnitude analysis with distance transforms to create novel attention-weighted visualizations that highlight critical interface regions. Five AFSD samples processed under different conditions were analyzed using multiple visualization techniques i.e. self-attention maps, and multi-channel visualization. These complementary approaches reveal subtle material transition zones and potential defect regions which were not readily observable through conventional imaging. The PSO algorithm automatically identified optimal threshold values (ranging from 156-173) for each sample, enabling precise segmentation of material interfaces. The multi-channel visualization technique effectively combines boundary information (red channel), spatial relationships (green channel), and material density data (blue channel) into cohesive representations that quantify interface quality. The results demonstrate that attention-based analysis successfully identifies regions of incomplete bonding and inhomogeneities in AFSD joints, providing quantitative metrics for process optimization and quality assessment of additively manufactured components.