Convolution neural network model with improved pooling strategy and feature selection for weld defect recognition
Abstract Weld defect recognition plays an important role in the manufacturing process of large-scale equipment. Traditional methods generally include several serial steps, such as image preprocessing, region segmentation, feature extraction, and type recognition. The results of each s...
| Main Authors: | , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Springer Berlin Heidelberg
2021
|
| Online Access: | https://hdl.handle.net/1721.1/136821 |
| _version_ | 1826214024065318912 |
|---|---|
| author | Jiang, Hongquan Hu, Qihang Zhi, Zelin Gao, Jianmin Gao, Zhiyong Wang, Rongxi He, Shuai Li, Hua |
| author2 | Massachusetts Institute of Technology. Laboratory for Manufacturing and Productivity |
| author_facet | Massachusetts Institute of Technology. Laboratory for Manufacturing and Productivity Jiang, Hongquan Hu, Qihang Zhi, Zelin Gao, Jianmin Gao, Zhiyong Wang, Rongxi He, Shuai Li, Hua |
| author_sort | Jiang, Hongquan |
| collection | MIT |
| description | Abstract
Weld defect recognition plays an important role in the manufacturing process of large-scale equipment. Traditional methods generally include several serial steps, such as image preprocessing, region segmentation, feature extraction, and type recognition. The results of each step have significant impact on the accuracy of the final defect identification. The convolutional neural network (CNN) has strong pattern recognition ability, which can overcome the above problem. However, there are two problems: one is that the pooling strategy has poor dynamic adaptability and the other is the insufficient feature selection ability. To overcome these problems, we propose a CNN-based weld defect recognition method, which includes an improved pooling strategy and an enhanced feature selection method. According to the characteristics of the weld defect image, an improved pooling strategy that considers the distribution of the pooling region and feature map is introduced. Additionally, in order to enhance the feature selection ability of the CNN, an enhanced feature selection method integrating the ReliefF algorithm with the CNN is proposed. A case study is presented for demonstrating the proposed techniques. The results show that the proposed method has higher accuracy than the traditional CNN method, and establish that the proposed CNN-based method is successfully applied for weld defect recognition. |
| first_indexed | 2024-09-23T15:58:35Z |
| format | Article |
| id | mit-1721.1/136821 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T15:58:35Z |
| publishDate | 2021 |
| publisher | Springer Berlin Heidelberg |
| record_format | dspace |
| spelling | mit-1721.1/1368212023-12-06T17:27:14Z Convolution neural network model with improved pooling strategy and feature selection for weld defect recognition Jiang, Hongquan Hu, Qihang Zhi, Zelin Gao, Jianmin Gao, Zhiyong Wang, Rongxi He, Shuai Li, Hua Massachusetts Institute of Technology. Laboratory for Manufacturing and Productivity Abstract Weld defect recognition plays an important role in the manufacturing process of large-scale equipment. Traditional methods generally include several serial steps, such as image preprocessing, region segmentation, feature extraction, and type recognition. The results of each step have significant impact on the accuracy of the final defect identification. The convolutional neural network (CNN) has strong pattern recognition ability, which can overcome the above problem. However, there are two problems: one is that the pooling strategy has poor dynamic adaptability and the other is the insufficient feature selection ability. To overcome these problems, we propose a CNN-based weld defect recognition method, which includes an improved pooling strategy and an enhanced feature selection method. According to the characteristics of the weld defect image, an improved pooling strategy that considers the distribution of the pooling region and feature map is introduced. Additionally, in order to enhance the feature selection ability of the CNN, an enhanced feature selection method integrating the ReliefF algorithm with the CNN is proposed. A case study is presented for demonstrating the proposed techniques. The results show that the proposed method has higher accuracy than the traditional CNN method, and establish that the proposed CNN-based method is successfully applied for weld defect recognition. 2021-11-01T14:33:36Z 2021-11-01T14:33:36Z 2020-11-16 2021-04-15T03:15:52Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/136821 en https://doi.org/10.1007/s40194-020-01027-6 Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. International Institute of Welding application/pdf Springer Berlin Heidelberg Springer Berlin Heidelberg |
| spellingShingle | Jiang, Hongquan Hu, Qihang Zhi, Zelin Gao, Jianmin Gao, Zhiyong Wang, Rongxi He, Shuai Li, Hua Convolution neural network model with improved pooling strategy and feature selection for weld defect recognition |
| title | Convolution neural network model with improved pooling strategy and feature selection for weld defect recognition |
| title_full | Convolution neural network model with improved pooling strategy and feature selection for weld defect recognition |
| title_fullStr | Convolution neural network model with improved pooling strategy and feature selection for weld defect recognition |
| title_full_unstemmed | Convolution neural network model with improved pooling strategy and feature selection for weld defect recognition |
| title_short | Convolution neural network model with improved pooling strategy and feature selection for weld defect recognition |
| title_sort | convolution neural network model with improved pooling strategy and feature selection for weld defect recognition |
| url | https://hdl.handle.net/1721.1/136821 |
| work_keys_str_mv | AT jianghongquan convolutionneuralnetworkmodelwithimprovedpoolingstrategyandfeatureselectionforwelddefectrecognition AT huqihang convolutionneuralnetworkmodelwithimprovedpoolingstrategyandfeatureselectionforwelddefectrecognition AT zhizelin convolutionneuralnetworkmodelwithimprovedpoolingstrategyandfeatureselectionforwelddefectrecognition AT gaojianmin convolutionneuralnetworkmodelwithimprovedpoolingstrategyandfeatureselectionforwelddefectrecognition AT gaozhiyong convolutionneuralnetworkmodelwithimprovedpoolingstrategyandfeatureselectionforwelddefectrecognition AT wangrongxi convolutionneuralnetworkmodelwithimprovedpoolingstrategyandfeatureselectionforwelddefectrecognition AT heshuai convolutionneuralnetworkmodelwithimprovedpoolingstrategyandfeatureselectionforwelddefectrecognition AT lihua convolutionneuralnetworkmodelwithimprovedpoolingstrategyandfeatureselectionforwelddefectrecognition |