Spatial randomness-based anomaly detection approach for monitoring local variations in multimode surface topography

Jaeseung Baek (), Myong K. Jeong () and Elsayed A. Elsayed ()
Additional contact information
Jaeseung Baek: Northern Michigan University
Myong K. Jeong: Rutgers University
Elsayed A. Elsayed: Rutgers University

Annals of Operations Research, 2024, vol. 341, issue 1, No 7, 173-195

Abstract: Abstract Anomaly detection of three-dimensional (3D) topographic data is a challenging problem in spatial data analysis. In this paper, we investigate spatial patterns of 3D surface data that exhibit multiple in-control modes. In complex manufacturing processes, surfaces of final products could contain different topographic features from one in-control surface to another, thus making it difficult to monitor the surface with existing approaches, which rely on the assumption of the presence of single mode surface topography. We propose a novel anomaly detection approach for monitoring local topographic variations in the presence of multimode surface topography. We present a binarization model to capture the generic behavior of the multimode surfaces and enhance the representation of the surface. To systematically monitor the surface, we introduce a new probabilistic distance measure (PDM) that quantifies the similarity of spatial patterns between two binarized surfaces. The proposed PDM takes advantage of identifying local variations by utilizing the order neighbor statistics, which captures the local property on the surface. Experimental results with numerical simulation data and real-life paper surface data are provided to demonstrate the effectiveness of the proposed approach.

Keywords: Anomaly detection; Kullback–Leibler divergence; Multimode surface; Spatial analysis; Spatial randomness; Surface monitoring (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10479-023-05468-2 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:annopr:v:341:y:2024:i:1:d:10.1007_s10479-023-05468-2

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10479

DOI: 10.1007/s10479-023-05468-2

Access Statistics for this article

Annals of Operations Research is currently edited by Endre Boros

More articles in Annals of Operations Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().