Classification of Tool Wear State based on Dual Attention Mechanism Network

Zhou, Jiaqi; Yue, Caixu; Liu, Xianli; Xia, Wei; Wei, Xudong; Qu, Jiaxu; Liang, Steven Y.; Wang, Lihui

doi:10.1016/j.rcim.2023.102575

Cited by 14 publications

(2 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The field of tool wear state monitoring has seen extensive application of computer vision technology due to advancements in information technology. Zhou et al [8] successfully detected tool wear state on-site by applying computer vision technology based on deep learning, significantly enhancing detection efficiency.…”

Section: Introductionmentioning

confidence: 99%

Identification of Tool Wear Based on Infographics and a Double-Attention Network

Ni,

Liu,

Meng

et al. 2023

Machines

View full text Add to dashboard Cite

Tool wear is a crucial factor in machining as it directly impacts surface quality and indirectly decreases machining efficiency, which leads to significant economic losses. Hence, monitoring tool wear state is of the utmost importance for achieving high performance and efficient machining. Although monitoring tool wear state using a single sensor has been validated in laboratory settings, it has certain drawbacks such as limited feature information acquisition and inability to learn important features adaptively. These limitations pose challenges to quickly extending the monitoring function of tool wear state of the machine tools. To solve these problems, this paper proposes a double-attention deep learning network based on vibroacoustic signal fusion feature infographics. The first solution is the construction of novel infographics using tool-intrinsic characteristics and multi-domain fusion features of multi-sensor inputs, which includes correlation analysis, principal component analysis, and feature fusion. The second solution is to build a novel deep network with a double-attention module and a spatial pyramid pooling module which can accurately and quickly identify tool wear state by successfully extracting critical spatial data from the infographics at various scales. The validity of the network is examined through an interpretability analysis based on the class activation graph. In terms of the tool wear status recognition task, the F1 score of the double-attention model based on an information graph is 11.61% higher than Resnet18, and peak recognition accuracy reaches 97.98%.

show abstract

Section: Introductionmentioning

confidence: 99%

Identification of Tool Wear Based on Infographics and a Double-Attention Network

Ni,

Liu,

Meng

et al. 2023

Machines

View full text Add to dashboard Cite

show abstract

“…Hou et al [20] combined channel attention with multiscale convolution to extract multiscale spatial-temporal features in cutting signals for tool wear monitoring. Zhou et al [21] proposed Dual Attention Mechanism Network to learn pixel feature dependency and inter-channel correlation respectively. He et al [22] proposed a cross-domain adaptation network based on attention mechanism to realize the tool wear state recognition and prediction.…”

Section: Introductionmentioning

confidence: 99%

Tool Wear State Recognition Based on One-Dimensional Convolutional Channel Attention

Xue,

Li,

Chen

et al. 2023

Micromachines

View full text Add to dashboard Cite

Tool wear state recognition is an important part of tool condition monitoring (TCM). Online tool wear monitoring can avoid wasteful early tool changes and degraded workpiece quality due to later tool changes. This study incorporated an attention mechanism implemented by one-dimensional convolution in a convolutional neural network for improving the performance of the tool wear recognition model (1DCCA-CNN). The raw multichannel cutting signals were first preprocessed and three time-domain features were extracted to form a new time-domain sequence. CNN was used for deep feature extraction of temporal sequences. A novel 1DCNN-based channel attention mechanism was proposed to weigh the channel dimensions of deep features to enhance important feature channels and capture key features. Compared with the traditional squeeze excitation attention mechanism, 1DCNN can enhance the information interaction between channels. The performance of the model was validated on the PHM2010 public cutting dataset. The excellent performance of the proposed 1DCCA-CNN was verified by the improvement of 4% and 5% compared to the highest level of existing research results on T1 and T3 datasets, respectively.

show abstract