Tool Wear Prediction Based on a Multi-Scale Convolutional Neural Network with Attention Fusion
Compared with traditional machine learning algorithms, the convolutional neural network (CNN) has an excellent automatic feature learning ability and can complete the nonlinear representation from original data input to output by itself. However, the CNN does not sufficiently mine the tool wear info...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/13/10/504 |
| _version_ | 1797472611031056384 |
|---|---|
| author | Qingqing Huang Di Wu Hao Huang Yan Zhang Yan Han |
| author_facet | Qingqing Huang Di Wu Hao Huang Yan Zhang Yan Han |
| author_sort | Qingqing Huang |
| collection | DOAJ |
| description | Compared with traditional machine learning algorithms, the convolutional neural network (CNN) has an excellent automatic feature learning ability and can complete the nonlinear representation from original data input to output by itself. However, the CNN does not sufficiently mine the tool wear information contained in the multi-sensor data due to disregard of the differences in the contribution of different features when extracting features. In this paper, a tool wear prediction method based on a multi-scale convolutional neural network with attention fusion is proposed, which fuses the tool wear degradation information collected by different types of sensors. In the multi-scale convolution module, convolution kernels with different sizes are used to extract the degradation information of different scales in the wear information, and then the attention fusion module is constructed to fuse the multi-scale feature information. Finally, the mapping between tool wear and multi-sensor data is realized through the feature information obtained by residual connection and full connection layer. By comparing the multi-scale convolutional neural network with different attention mechanisms, the experiments demonstrated the effectiveness and superiority of the proposed method. |
| first_indexed | 2024-03-09T20:03:50Z |
| format | Article |
| id | doaj.art-67da0f70522b4c0ea01d1f3b552bf08e |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-09T20:03:50Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-67da0f70522b4c0ea01d1f3b552bf08e2023-11-24T00:36:22ZengMDPI AGInformation2078-24892022-10-01131050410.3390/info13100504Tool Wear Prediction Based on a Multi-Scale Convolutional Neural Network with Attention FusionQingqing Huang0Di Wu1Hao Huang2Yan Zhang3Yan Han4Key Laboratory of Industrial Internet of Things and Networked Control, Ministry of Education, Chongqing University of Posts and Telecommunications, Chongqing 40065, ChinaKey Laboratory of Industrial Internet of Things and Networked Control, Ministry of Education, Chongqing University of Posts and Telecommunications, Chongqing 40065, ChinaKey Laboratory of Industrial Internet of Things and Networked Control, Ministry of Education, Chongqing University of Posts and Telecommunications, Chongqing 40065, ChinaKey Laboratory of Industrial Internet of Things and Networked Control, Ministry of Education, Chongqing University of Posts and Telecommunications, Chongqing 40065, ChinaKey Laboratory of Industrial Internet of Things and Networked Control, Ministry of Education, Chongqing University of Posts and Telecommunications, Chongqing 40065, ChinaCompared with traditional machine learning algorithms, the convolutional neural network (CNN) has an excellent automatic feature learning ability and can complete the nonlinear representation from original data input to output by itself. However, the CNN does not sufficiently mine the tool wear information contained in the multi-sensor data due to disregard of the differences in the contribution of different features when extracting features. In this paper, a tool wear prediction method based on a multi-scale convolutional neural network with attention fusion is proposed, which fuses the tool wear degradation information collected by different types of sensors. In the multi-scale convolution module, convolution kernels with different sizes are used to extract the degradation information of different scales in the wear information, and then the attention fusion module is constructed to fuse the multi-scale feature information. Finally, the mapping between tool wear and multi-sensor data is realized through the feature information obtained by residual connection and full connection layer. By comparing the multi-scale convolutional neural network with different attention mechanisms, the experiments demonstrated the effectiveness and superiority of the proposed method.https://www.mdpi.com/2078-2489/13/10/504tool wear predictionmulti-scale convolutionattention fusion |
| spellingShingle | Qingqing Huang Di Wu Hao Huang Yan Zhang Yan Han Tool Wear Prediction Based on a Multi-Scale Convolutional Neural Network with Attention Fusion Information tool wear prediction multi-scale convolution attention fusion |
| title | Tool Wear Prediction Based on a Multi-Scale Convolutional Neural Network with Attention Fusion |
| title_full | Tool Wear Prediction Based on a Multi-Scale Convolutional Neural Network with Attention Fusion |
| title_fullStr | Tool Wear Prediction Based on a Multi-Scale Convolutional Neural Network with Attention Fusion |
| title_full_unstemmed | Tool Wear Prediction Based on a Multi-Scale Convolutional Neural Network with Attention Fusion |
| title_short | Tool Wear Prediction Based on a Multi-Scale Convolutional Neural Network with Attention Fusion |
| title_sort | tool wear prediction based on a multi scale convolutional neural network with attention fusion |
| topic | tool wear prediction multi-scale convolution attention fusion |
| url | https://www.mdpi.com/2078-2489/13/10/504 |
| work_keys_str_mv | AT qingqinghuang toolwearpredictionbasedonamultiscaleconvolutionalneuralnetworkwithattentionfusion AT diwu toolwearpredictionbasedonamultiscaleconvolutionalneuralnetworkwithattentionfusion AT haohuang toolwearpredictionbasedonamultiscaleconvolutionalneuralnetworkwithattentionfusion AT yanzhang toolwearpredictionbasedonamultiscaleconvolutionalneuralnetworkwithattentionfusion AT yanhan toolwearpredictionbasedonamultiscaleconvolutionalneuralnetworkwithattentionfusion |