Intelligent Tool Wear Monitoring Method Using a Convolutional Neural Network and an Informer
Tool wear (TW) is the gradual deterioration and loss of cutting edges due to continuous cutting operations in real production scenarios. This wear can affect the quality of the cut, increase production costs, reduce workpiece accuracy, and lead to sudden tool breakage, affecting productivity and saf...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Lubricants |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4442/11/9/389 |
| _version_ | 1827725538556379136 |
|---|---|
| author | Xingang Xie Min Huang Weiwei Sun Yiming Li Yue Liu |
| author_facet | Xingang Xie Min Huang Weiwei Sun Yiming Li Yue Liu |
| author_sort | Xingang Xie |
| collection | DOAJ |
| description | Tool wear (TW) is the gradual deterioration and loss of cutting edges due to continuous cutting operations in real production scenarios. This wear can affect the quality of the cut, increase production costs, reduce workpiece accuracy, and lead to sudden tool breakage, affecting productivity and safety. Nevertheless, since conventional tool wear monitoring (TWM) approaches often employ complex physical models and empirical rules, their application to complex and non-linear manufacturing processes is challenging. As a result, this study presents a TWM model using a convolutional neural network (CNN), an Informer encoder, and bidirectional long short-term memory (BiLSTM). First, local feature extraction is performed on the input multi-sensor signals using CNN. Then, the Informer encoder deals with long-term time dependencies and captures global time features. Finally, BiLSTM captures the time dependency in the data and outputs the predicted tool wear state through the fully connected layer. The experimental results show that the proposed TWM model achieves a prediction accuracy of 99%. It is able to meet the TWM accuracy requirements of real production needs. Moreover, this method also has good interpretability, which can help to understand the critical tool wear factors. |
| first_indexed | 2024-03-10T22:31:45Z |
| format | Article |
| id | doaj.art-1e2d19ea103d4c2a878193a6cad0c158 |
| institution | Directory Open Access Journal |
| issn | 2075-4442 |
| language | English |
| last_indexed | 2024-03-10T22:31:45Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Lubricants |
| spelling | doaj.art-1e2d19ea103d4c2a878193a6cad0c1582023-11-19T11:39:49ZengMDPI AGLubricants2075-44422023-09-0111938910.3390/lubricants11090389Intelligent Tool Wear Monitoring Method Using a Convolutional Neural Network and an InformerXingang Xie0Min Huang1Weiwei Sun2Yiming Li3Yue Liu4School of Mechanical Electronic and Information Engineering, China University of Mining and Technology-BEIJING, Beijing 100083, ChinaSchool of Mechanical Electronic and Information Engineering, China University of Mining and Technology-BEIJING, Beijing 100083, ChinaMechanical Electrical Engineering School, Beijing Information Science and Technology University, Beijing 100192, ChinaMechanical Electrical Engineering School, Beijing Information Science and Technology University, Beijing 100192, ChinaMechanical Electrical Engineering School, Beijing Information Science and Technology University, Beijing 100192, ChinaTool wear (TW) is the gradual deterioration and loss of cutting edges due to continuous cutting operations in real production scenarios. This wear can affect the quality of the cut, increase production costs, reduce workpiece accuracy, and lead to sudden tool breakage, affecting productivity and safety. Nevertheless, since conventional tool wear monitoring (TWM) approaches often employ complex physical models and empirical rules, their application to complex and non-linear manufacturing processes is challenging. As a result, this study presents a TWM model using a convolutional neural network (CNN), an Informer encoder, and bidirectional long short-term memory (BiLSTM). First, local feature extraction is performed on the input multi-sensor signals using CNN. Then, the Informer encoder deals with long-term time dependencies and captures global time features. Finally, BiLSTM captures the time dependency in the data and outputs the predicted tool wear state through the fully connected layer. The experimental results show that the proposed TWM model achieves a prediction accuracy of 99%. It is able to meet the TWM accuracy requirements of real production needs. Moreover, this method also has good interpretability, which can help to understand the critical tool wear factors.https://www.mdpi.com/2075-4442/11/9/389tool wearconvolutional neural network (CNN)global time featureinformerBiLSTM |
| spellingShingle | Xingang Xie Min Huang Weiwei Sun Yiming Li Yue Liu Intelligent Tool Wear Monitoring Method Using a Convolutional Neural Network and an Informer Lubricants tool wear convolutional neural network (CNN) global time feature informer BiLSTM |
| title | Intelligent Tool Wear Monitoring Method Using a Convolutional Neural Network and an Informer |
| title_full | Intelligent Tool Wear Monitoring Method Using a Convolutional Neural Network and an Informer |
| title_fullStr | Intelligent Tool Wear Monitoring Method Using a Convolutional Neural Network and an Informer |
| title_full_unstemmed | Intelligent Tool Wear Monitoring Method Using a Convolutional Neural Network and an Informer |
| title_short | Intelligent Tool Wear Monitoring Method Using a Convolutional Neural Network and an Informer |
| title_sort | intelligent tool wear monitoring method using a convolutional neural network and an informer |
| topic | tool wear convolutional neural network (CNN) global time feature informer BiLSTM |
| url | https://www.mdpi.com/2075-4442/11/9/389 |
| work_keys_str_mv | AT xingangxie intelligenttoolwearmonitoringmethodusingaconvolutionalneuralnetworkandaninformer AT minhuang intelligenttoolwearmonitoringmethodusingaconvolutionalneuralnetworkandaninformer AT weiweisun intelligenttoolwearmonitoringmethodusingaconvolutionalneuralnetworkandaninformer AT yimingli intelligenttoolwearmonitoringmethodusingaconvolutionalneuralnetworkandaninformer AT yueliu intelligenttoolwearmonitoringmethodusingaconvolutionalneuralnetworkandaninformer |