A defect detection method for topological phononic materials based on few-shot learning
Topological phononic materials have been widely used in many fields, such as topological antennas, asymmetric waveguides, and noise insulation. However, due to the limitations of the manufacturing process, topological protection is vulnerable to some severe defects that may affect the application ef...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2022-01-01
|
| Series: | New Journal of Physics |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/1367-2630/ac8307 |
| _version_ | 1797748435271548928 |
|---|---|
| author | Beini Zhang Xiao Luo Yetao Lyu Xiaoxiao Wu Weijia Wen |
| author_facet | Beini Zhang Xiao Luo Yetao Lyu Xiaoxiao Wu Weijia Wen |
| author_sort | Beini Zhang |
| collection | DOAJ |
| description | Topological phononic materials have been widely used in many fields, such as topological antennas, asymmetric waveguides, and noise insulation. However, due to the limitations of the manufacturing process, topological protection is vulnerable to some severe defects that may affect the application effect. Therefore, the quality inspection of topological materials is essential to ensure reliable results. Due to the low contrast and irregularity of defects and the similarity of topological phononics, they are difficult to recognize by traditional image processing algorithms, so manual detection is still mainstream at present. But manual detection requires experienced inspectors, which is expensive and time-consuming. In addition, topological materials are expensive to produce, and there is no large publicly available dataset, but deep learning usually relies on large datasets for training. To solve the above problems, we propose an automatic deep learning topology structure defect detection method (ADLTSDM) in this work, which could classify not only the structure of topological materials but also detect the defects of topological phononics based on a small dataset. ADLTSDM exploits the prior knowledge of the topological material structure and achieves an augmentation factor of more than 100 times through the random and fixed interval screenshot algorithm, thus enabling the training of deep neural networks with only two raw data. For defect detection, ADLTSDM has an accuracy of more than 97% and improves detection speed by more than 38% compared with manual detection. For structure classification, ADLTSDM can achieve an accuracy of over 99% and seven times faster speed compared with manual classification. Besides, the detection standard of ADLTSDM is unified, so the accuracy will not be affected by the experience of the inspectors, which has more potential in high-throughput industrial applications. |
| first_indexed | 2024-03-12T16:04:43Z |
| format | Article |
| id | doaj.art-89c32d6c807e4a80b11d8ab2ab9db5ee |
| institution | Directory Open Access Journal |
| issn | 1367-2630 |
| language | English |
| last_indexed | 2024-03-12T16:04:43Z |
| publishDate | 2022-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | New Journal of Physics |
| spelling | doaj.art-89c32d6c807e4a80b11d8ab2ab9db5ee2023-08-09T14:24:47ZengIOP PublishingNew Journal of Physics1367-26302022-01-0124808301210.1088/1367-2630/ac8307A defect detection method for topological phononic materials based on few-shot learningBeini Zhang0Xiao Luo1https://orcid.org/0000-0002-0431-7924Yetao Lyu2Xiaoxiao Wu3Weijia Wen4https://orcid.org/0000-0003-3784-7494Advanced Materials Thrust, The Hongkong University of Science and Technology , Guangzhou, 511458, People’s Republic of China; HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute , Futian, Shenzhen, 518000, People’s Republic of ChinaDepartment of Physics, The Hong Kong University of Science and Technology , Hong Kong, 999077, People’s Republic of ChinaRobotics and Artificial Intelligence Division, Hong Kong Productivity Council (HKPC) , Hong Kong, 999077, People’s Republic of ChinaDepartment of Physics, The Hong Kong University of Science and Technology , Hong Kong, 999077, People’s Republic of ChinaAdvanced Materials Thrust, The Hongkong University of Science and Technology , Guangzhou, 511458, People’s Republic of China; HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute , Futian, Shenzhen, 518000, People’s Republic of China; Department of Physics, The Hong Kong University of Science and Technology , Hong Kong, 999077, People’s Republic of ChinaTopological phononic materials have been widely used in many fields, such as topological antennas, asymmetric waveguides, and noise insulation. However, due to the limitations of the manufacturing process, topological protection is vulnerable to some severe defects that may affect the application effect. Therefore, the quality inspection of topological materials is essential to ensure reliable results. Due to the low contrast and irregularity of defects and the similarity of topological phononics, they are difficult to recognize by traditional image processing algorithms, so manual detection is still mainstream at present. But manual detection requires experienced inspectors, which is expensive and time-consuming. In addition, topological materials are expensive to produce, and there is no large publicly available dataset, but deep learning usually relies on large datasets for training. To solve the above problems, we propose an automatic deep learning topology structure defect detection method (ADLTSDM) in this work, which could classify not only the structure of topological materials but also detect the defects of topological phononics based on a small dataset. ADLTSDM exploits the prior knowledge of the topological material structure and achieves an augmentation factor of more than 100 times through the random and fixed interval screenshot algorithm, thus enabling the training of deep neural networks with only two raw data. For defect detection, ADLTSDM has an accuracy of more than 97% and improves detection speed by more than 38% compared with manual detection. For structure classification, ADLTSDM can achieve an accuracy of over 99% and seven times faster speed compared with manual classification. Besides, the detection standard of ADLTSDM is unified, so the accuracy will not be affected by the experience of the inspectors, which has more potential in high-throughput industrial applications.https://doi.org/10.1088/1367-2630/ac8307topological materialsfew-shot learningdeep learningdefect detectionstructure classification |
| spellingShingle | Beini Zhang Xiao Luo Yetao Lyu Xiaoxiao Wu Weijia Wen A defect detection method for topological phononic materials based on few-shot learning New Journal of Physics topological materials few-shot learning deep learning defect detection structure classification |
| title | A defect detection method for topological phononic materials based on few-shot learning |
| title_full | A defect detection method for topological phononic materials based on few-shot learning |
| title_fullStr | A defect detection method for topological phononic materials based on few-shot learning |
| title_full_unstemmed | A defect detection method for topological phononic materials based on few-shot learning |
| title_short | A defect detection method for topological phononic materials based on few-shot learning |
| title_sort | defect detection method for topological phononic materials based on few shot learning |
| topic | topological materials few-shot learning deep learning defect detection structure classification |
| url | https://doi.org/10.1088/1367-2630/ac8307 |
| work_keys_str_mv | AT beinizhang adefectdetectionmethodfortopologicalphononicmaterialsbasedonfewshotlearning AT xiaoluo adefectdetectionmethodfortopologicalphononicmaterialsbasedonfewshotlearning AT yetaolyu adefectdetectionmethodfortopologicalphononicmaterialsbasedonfewshotlearning AT xiaoxiaowu adefectdetectionmethodfortopologicalphononicmaterialsbasedonfewshotlearning AT weijiawen adefectdetectionmethodfortopologicalphononicmaterialsbasedonfewshotlearning AT beinizhang defectdetectionmethodfortopologicalphononicmaterialsbasedonfewshotlearning AT xiaoluo defectdetectionmethodfortopologicalphononicmaterialsbasedonfewshotlearning AT yetaolyu defectdetectionmethodfortopologicalphononicmaterialsbasedonfewshotlearning AT xiaoxiaowu defectdetectionmethodfortopologicalphononicmaterialsbasedonfewshotlearning AT weijiawen defectdetectionmethodfortopologicalphononicmaterialsbasedonfewshotlearning |