Analysis of oxide wear debris using ferrography image segmentation

Abstract

Purpose

It is a challenging task to analysis oxide wear particles when they are stuck together with other types of wear particles in complex ferrography images. Hence, this paper aims to propose a method of ferrography image segmentation to analysis oxide wear debris in complex ferrography images.

Design/methodology/approach

First, ferrography images are segmented with watershed transform. Then, two region merging rules are proposed to improve the initial segmentation results. Finally, the features of each particle are extracted to detect and assess the oxide wear particles.

Findings

The results show that the proposed method outperforms other methods of ferrography image segmentation, and the overlapping wear particles in complex ferrography images can be well separated. Moreover, the features of each separated wear particles can be easily extracted to analysis the oxide wear particles.

Practical implications

The proposed method provides a useful approach for the automatic detection and assessment of oxide wear particles in complex ferrography images.

Originality/value

The colours, edges and position information of wear debris are considered in the proposed method to improve the segmentation result. Moreover, the proposed method can not only detect oxide wear particles in ferrography images but also evaluate oxide wear severity in ferrography images.

Citation

Peng, P. and Wang, J. (2019), "Analysis of oxide wear debris using ferrography image segmentation", Industrial Lubrication and Tribology, Vol. 71 No. 7, pp. 901-906. https://doi.org/10.1108/ILT-09-2018-0355