Back to Search
Start Over
FFWR-Net: A feature fusion wear particle recognition network for wear particle classification
- Source :
- Journal of Mechanical Science and Technology. 35:1699-1710
- Publication Year :
- 2021
- Publisher :
- Springer Science and Business Media LLC, 2021.
-
Abstract
- Wear particles produced by machines in the process of wear carry valuable information including wear mechanism and wear severity. Wear particle classification based on wear particle images provides predictive analysis for wear condition of machines. A novel wear particle recognition network based on feature fusion, FFWR-Net, is proposed in this research paper for wear particle images classification. In FFWR-Net, traditional feature extraction method by image processing technique (i.e. manually feature extracting) and deep learning convolutional neural network method (i.e. automatically feature extracting) is paralleled to extract the features of wear particle image. Then the features obtained by two different methods are fused together for building a wear particle classifier. In order to verify the effectiveness of the proposed classifier, it is compared with the previous convolutional neural network models on the same wear particle dataset. The comparison results show the accuracy and effectiveness of the proposed FFWR-Net classifier is better than the previous models.
- Subjects :
- 0209 industrial biotechnology
Hardware_MEMORYSTRUCTURES
Computer science
business.industry
Mechanical Engineering
Deep learning
Feature extraction
Process (computing)
Image processing
Pattern recognition
02 engineering and technology
Convolutional neural network
Image (mathematics)
020303 mechanical engineering & transports
020901 industrial engineering & automation
0203 mechanical engineering
Mechanics of Materials
Feature (computer vision)
Classifier (linguistics)
Artificial intelligence
business
Subjects
Details
- ISSN :
- 19763824 and 1738494X
- Volume :
- 35
- Database :
- OpenAIRE
- Journal :
- Journal of Mechanical Science and Technology
- Accession number :
- edsair.doi...........9097be23c78d5e1a109366aea481a45d