计算机科学
基本事实
分割
可靠性(半导体)
聚类分析
数据挖掘
点云
可靠性工程
组分(热力学)
航程(航空)
点(几何)
精确性和召回率
人工智能
算法
云计算
图像分割
体积热力学
启发式
稳健性(进化)
机器学习
目标检测
作者
Miguel O. da Cruz,Daniel Gil Afonso,Miguel Armando Riem de Oliveira
标识
DOI:10.1016/j.optlastec.2025.113904
摘要
Damage detection in point clouds is a critical step for automating systems of metal component repair through additive manufacturing. However, current approaches face challenges due to the variability in part geometries and the diversity of damage types. This paper presents a novel damage detection algorithm that adapts to variations in damage location, geometry, and volume through a parameter-driven approach based on plane segmentation and clustering tasks. A synthesized dataset was generated for the validation, with ground truth established using efficient Boolean comparisons combining voxelization with spatial data structures. To optimize the performance of the algorithm, a Design of Experiments was conducted, analyzing parameter influences and guiding the development of optimal detection models. This approach demonstrated a remarkable performance across a wide range of complex damage scenarios, achieving higher precision, recall, and F1 scores than existing methods. The optimized version further enhances recall with minimal impact on precision, ensuring robust and balanced detection capabilities. The approach was also validated in a case study, demonstrating its operational reliability under realistic conditions. This work offers a generalizable solution for effective damage detection, setting a strong foundation for future advancements in automated repair systems. • Novel damage detection algorithm for random damages. • Proven synthesized dataset of 500 damaged models. • A ground truth determination method using a K-Dimensional (K-D) tree-based Spatial Data Structure (SDS). • Comprehensive performance evaluation of the proposed method against existing approaches using detection metrics, addressing the lack of comparative analyses in the field. • Effective detection algorithm for complex and small-scale damages across diverse damage scenarios. • Real-world case study validating robustness and versatility on damaged metallic components.
科研通智能强力驱动
Strongly Powered by AbleSci AI