Recognition and
classification for surface defects ofSi3N4ceramic bearing inner ring based on RetinaNet method and NAM attention
mechanism
LIAO Dahai1,2#, CUI Zhihui1,2#,
ZHANG Xin2, LI Wenjie2, ZHENG
Qi1, WU Nanxing1,2*
(1.School
of Mechanical and Electronic Engineering, Jingdezhen Ceramic University,
Jingdezhen, People’s Republic of China)
(2. Laboratory of Ceramic Material Processing Technology Engineering,
Jiangxi 333403, PR China)
Abstract: Due to surface defects on inner ring of
Si3N4 ceramic bearing are tiny and
difficult to defect, the defects accelerate the wear of ceramic parts
and reduce the performance of ceramic parts. A surface defect detection
method based on RetinaNet method and NAM attention mechanism is
proposed. Besides, the performance of RetinaNet method and Faster RCNN
method is compared. The platform for surface defects of
Si3N4 ceramic bearing inner ring is
built independently to collect images. The dataset is made up of
collected images and expanded by online data augmentation. Resnet-50 is
used as the feature extraction network. The NAM attention mechanism is
added to the tail of Resnet-50 to form an attention module to improve
the model accuracy. As the bounding box regression loss function, loss
is used for learning bounding box regression and localization
uncertainty. A multi-scale feature pyramid is constructed by a feature
pyramid network to integrate multi-level feature information. And a
small full convolutional network is used as a classification sub-network
and a bounding box regression sub-network. The results show that the mAP
of the method reaches 91.84%, which is 13.45% and 2.1% higher
compared to Faster RCNN and RetinaNet, respectively. The method has good
detection effect on the identification and classification of surface
defect species.
Keywords:Si3N4ceramic bearing inner ring, RetinaNet, Online data augment, NAM
attention mechanism, Surface defects detection