A New Target Detection Method of Ferrography Wear Particle Images Based on ECAM-YOLOv5-BiFPN Network
For mechanical equipment, the wear particle in the lubrication system during equipment operation can reflect the lubrication condition, wear mechanism, and severity of wear between equipment friction pairs. To solve the problems of false detection and missed detection of small, dense, and overlappin...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-07-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/14/6477 |
_version_ | 1797587522399764480 |
---|---|
author | Lei He Haijun Wei Qixuan Wang |
author_facet | Lei He Haijun Wei Qixuan Wang |
author_sort | Lei He |
collection | DOAJ |
description | For mechanical equipment, the wear particle in the lubrication system during equipment operation can reflect the lubrication condition, wear mechanism, and severity of wear between equipment friction pairs. To solve the problems of false detection and missed detection of small, dense, and overlapping wear particles in the current ferrography wear particle detection model in a complex oil background environment, a new ferrography wear particle detection network, EYBNet, is proposed. Firstly, the MSRCR algorithm is used to enhance the contrast of wear particle images and reduce the interference of complex lubricant backgrounds. Secondly, under the framework of YOLOv5s, the accuracy of network detection is improved by introducing DWConv and the accuracy of the entire network is improved by optimizing the loss function of the detection network. Then, by adding an ECAM to the backbone network of YOLOv5s, the saliency of wear particles in the images is enhanced, and the feature expression ability of wear particles in the detection network is enhanced. Finally, the path aggregation network structure in YOLOv5s is replaced with a weighted BiFPN structure to achieve efficient bidirectional cross-scale connections and weighted feature fusion. The experimental results show that the average accuracy is increased by 4.46%, up to 91.3%, compared with YOLOv5s, and the detection speed is 50.5FPS. |
first_indexed | 2024-03-11T00:40:07Z |
format | Article |
id | doaj.art-767ec6b8eb864dfaa40d2ead3753b714 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-11T00:40:07Z |
publishDate | 2023-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-767ec6b8eb864dfaa40d2ead3753b7142023-11-18T21:18:17ZengMDPI AGSensors1424-82202023-07-012314647710.3390/s23146477A New Target Detection Method of Ferrography Wear Particle Images Based on ECAM-YOLOv5-BiFPN NetworkLei He0Haijun Wei1Qixuan Wang2Merchant Marine College, Shanghai Maritime University, Shanghai 201306, ChinaMerchant Marine College, Shanghai Maritime University, Shanghai 201306, ChinaMerchant Marine College, Shanghai Maritime University, Shanghai 201306, ChinaFor mechanical equipment, the wear particle in the lubrication system during equipment operation can reflect the lubrication condition, wear mechanism, and severity of wear between equipment friction pairs. To solve the problems of false detection and missed detection of small, dense, and overlapping wear particles in the current ferrography wear particle detection model in a complex oil background environment, a new ferrography wear particle detection network, EYBNet, is proposed. Firstly, the MSRCR algorithm is used to enhance the contrast of wear particle images and reduce the interference of complex lubricant backgrounds. Secondly, under the framework of YOLOv5s, the accuracy of network detection is improved by introducing DWConv and the accuracy of the entire network is improved by optimizing the loss function of the detection network. Then, by adding an ECAM to the backbone network of YOLOv5s, the saliency of wear particles in the images is enhanced, and the feature expression ability of wear particles in the detection network is enhanced. Finally, the path aggregation network structure in YOLOv5s is replaced with a weighted BiFPN structure to achieve efficient bidirectional cross-scale connections and weighted feature fusion. The experimental results show that the average accuracy is increased by 4.46%, up to 91.3%, compared with YOLOv5s, and the detection speed is 50.5FPS.https://www.mdpi.com/1424-8220/23/14/6477wear particleimage recognitionYOLOV5sECAMweighted BiFPN |
spellingShingle | Lei He Haijun Wei Qixuan Wang A New Target Detection Method of Ferrography Wear Particle Images Based on ECAM-YOLOv5-BiFPN Network Sensors wear particle image recognition YOLOV5s ECAM weighted BiFPN |
title | A New Target Detection Method of Ferrography Wear Particle Images Based on ECAM-YOLOv5-BiFPN Network |
title_full | A New Target Detection Method of Ferrography Wear Particle Images Based on ECAM-YOLOv5-BiFPN Network |
title_fullStr | A New Target Detection Method of Ferrography Wear Particle Images Based on ECAM-YOLOv5-BiFPN Network |
title_full_unstemmed | A New Target Detection Method of Ferrography Wear Particle Images Based on ECAM-YOLOv5-BiFPN Network |
title_short | A New Target Detection Method of Ferrography Wear Particle Images Based on ECAM-YOLOv5-BiFPN Network |
title_sort | new target detection method of ferrography wear particle images based on ecam yolov5 bifpn network |
topic | wear particle image recognition YOLOV5s ECAM weighted BiFPN |
url | https://www.mdpi.com/1424-8220/23/14/6477 |
work_keys_str_mv | AT leihe anewtargetdetectionmethodofferrographywearparticleimagesbasedonecamyolov5bifpnnetwork AT haijunwei anewtargetdetectionmethodofferrographywearparticleimagesbasedonecamyolov5bifpnnetwork AT qixuanwang anewtargetdetectionmethodofferrographywearparticleimagesbasedonecamyolov5bifpnnetwork AT leihe newtargetdetectionmethodofferrographywearparticleimagesbasedonecamyolov5bifpnnetwork AT haijunwei newtargetdetectionmethodofferrographywearparticleimagesbasedonecamyolov5bifpnnetwork AT qixuanwang newtargetdetectionmethodofferrographywearparticleimagesbasedonecamyolov5bifpnnetwork |