An object detection network for wear debris recognition in ferrography images

被引：7

作者：

Jia, Fengguang ^{[1
,2
]}

Wei, Haijun ^{[1
]}

Sun, Hongyuan ^{[2
]}

Song, Lei ^{[2
]}

Yu, Fulin ^{[2
]}

机构：

[1] Shanghai Maritime Univ, Sch Merchant Marine, Shanghai 201306, Peoples R China

[2] Shandong Jiaotong Univ, Sch Naval Architecture & Port Engn, Weihai 264209, Peoples R China

来源：

JOURNAL OF THE BRAZILIAN SOCIETY OF MECHANICAL SCIENCES AND ENGINEERING | 2022年 / 44卷 / 02期

关键词：

Ferrography images; Object detection; Wear debris; Deep learning; Condition monitoring; PARTICLE CLASSIFICATION;

D O I：

10.1007/s40430-022-03375-4

中图分类号：

TH [机械、仪表工业];

学科分类号：

0802 ;

摘要：

The intelligent recognition of wear debris in ferrography images is a great challenge. Aiming at the detection characteristics of multi-scale objects, small objects and overlapping objects in ferrography images, a real-time on-line object detection model combining feature fusion, self-attention mechanism and improved NMS is proposed. Based on YOLOv3, a fully convolutional network based on feature fusion is constructed, and a residual unit with self-attention mechanism and an object selection mechanism based on improved non-maximum suppression are introduced. The performance of the model is compared with three advanced object detection algorithms on a great number of ferrography images. The experimental results show that the model has high detection accuracy, short detection time and strong adaptability. The proposed model can be further developed and applied to fault diagnosis and condition monitoring of machinery and equipment in future.

引用

页数：15