Tool Condition Monitoring with Convolutional Neural Network for Milling Tools and Turning Inserts
Tool wear is one of the cost drivers in the manufacturing industry because it directly affects the quality of the manufactured workpiece and production efficiency. Identifying the right time to replace the cutting tool is a challenge. If the tool is replaced too soon, the production time can be dis...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Petra Christian University
2023-04-01
|
| Series: | Jurnal Teknik Industri |
| Subjects: | |
| Online Access: | https://jurnalindustri.petra.ac.id/index.php/ind/article/view/25743 |
| _version_ | 1797794098022711296 |
|---|---|
| author | Achmad Pratama Rifai Silvyaniza Briliananda Hideki Aoyama |
| author_facet | Achmad Pratama Rifai Silvyaniza Briliananda Hideki Aoyama |
| author_sort | Achmad Pratama Rifai |
| collection | DOAJ |
| description |
Tool wear is one of the cost drivers in the manufacturing industry because it directly affects the quality of the manufactured workpiece and production efficiency. Identifying the right time to replace the cutting tool is a challenge. If the tool is replaced too soon, the production time can be disrupted, causing unscheduled downtime. Conversely, if it is replaced too late, there will be an additional cost to replace raw materials damaged by broken tools. Therefore, researchers continue to develop tool condition monitoring (TCM) methods to analyze tool wear. A recent popular method is machine vision with convolutional neural networks (CNN). The present research aims to develop classification models that can categorize the image data of milling and turning inserts into GO (suitable for use) and NO GO (not suitable for use). Two approaches are selected for the modeling process, custom learning and transfer learning, with image data input from smartphones and microscope cameras. The experimental results show that the best model is the transfer learning approach using Inception-V3 architecture with a smartphone image. The model reaches 92.2% accuracy, hence demonstrating a relatively good performance in determining whether the tool is suitable for use or not.
|
| first_indexed | 2024-03-13T02:57:51Z |
| format | Article |
| id | doaj.art-b1c7c71f2bd841489e58e5e9281b4a8f |
| institution | Directory Open Access Journal |
| issn | 1411-2485 2087-7439 |
| language | English |
| last_indexed | 2024-03-13T02:57:51Z |
| publishDate | 2023-04-01 |
| publisher | Petra Christian University |
| record_format | Article |
| series | Jurnal Teknik Industri |
| spelling | doaj.art-b1c7c71f2bd841489e58e5e9281b4a8f2023-06-28T01:47:04ZengPetra Christian UniversityJurnal Teknik Industri1411-24852087-74392023-04-0125110.9744/jti.25.1.1-16Tool Condition Monitoring with Convolutional Neural Network for Milling Tools and Turning InsertsAchmad Pratama Rifai0Silvyaniza Briliananda1Hideki Aoyama2Universitas Gadjah Mada, JogjakartaUniversitas Gadjah Mada, JogjakartaKeio University, Yokohama Tool wear is one of the cost drivers in the manufacturing industry because it directly affects the quality of the manufactured workpiece and production efficiency. Identifying the right time to replace the cutting tool is a challenge. If the tool is replaced too soon, the production time can be disrupted, causing unscheduled downtime. Conversely, if it is replaced too late, there will be an additional cost to replace raw materials damaged by broken tools. Therefore, researchers continue to develop tool condition monitoring (TCM) methods to analyze tool wear. A recent popular method is machine vision with convolutional neural networks (CNN). The present research aims to develop classification models that can categorize the image data of milling and turning inserts into GO (suitable for use) and NO GO (not suitable for use). Two approaches are selected for the modeling process, custom learning and transfer learning, with image data input from smartphones and microscope cameras. The experimental results show that the best model is the transfer learning approach using Inception-V3 architecture with a smartphone image. The model reaches 92.2% accuracy, hence demonstrating a relatively good performance in determining whether the tool is suitable for use or not. https://jurnalindustri.petra.ac.id/index.php/ind/article/view/25743Tool condition monitoring Convolutional neural networkBinary ClassificationMilling and turning tools |
| spellingShingle | Achmad Pratama Rifai Silvyaniza Briliananda Hideki Aoyama Tool Condition Monitoring with Convolutional Neural Network for Milling Tools and Turning Inserts Jurnal Teknik Industri Tool condition monitoring Convolutional neural network Binary Classification Milling and turning tools |
| title | Tool Condition Monitoring with Convolutional Neural Network for Milling Tools and Turning Inserts |
| title_full | Tool Condition Monitoring with Convolutional Neural Network for Milling Tools and Turning Inserts |
| title_fullStr | Tool Condition Monitoring with Convolutional Neural Network for Milling Tools and Turning Inserts |
| title_full_unstemmed | Tool Condition Monitoring with Convolutional Neural Network for Milling Tools and Turning Inserts |
| title_short | Tool Condition Monitoring with Convolutional Neural Network for Milling Tools and Turning Inserts |
| title_sort | tool condition monitoring with convolutional neural network for milling tools and turning inserts |
| topic | Tool condition monitoring Convolutional neural network Binary Classification Milling and turning tools |
| url | https://jurnalindustri.petra.ac.id/index.php/ind/article/view/25743 |
| work_keys_str_mv | AT achmadpratamarifai toolconditionmonitoringwithconvolutionalneuralnetworkformillingtoolsandturninginserts AT silvyanizabriliananda toolconditionmonitoringwithconvolutionalneuralnetworkformillingtoolsandturninginserts AT hidekiaoyama toolconditionmonitoringwithconvolutionalneuralnetworkformillingtoolsandturninginserts |