Automated Classification of Ultrasonic Signal via a Convolutional Neural Network
Ultrasonic signal classification in nondestructive testing is of great significance for the detection of defects. The current methods have mainly utilized low-level handcrafted features based on traditional signal processing approaches, such as the Fourier transform, wavelet transform and the like,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/9/4179 |
| _version_ | 1797505783878909952 |
|---|---|
| author | Yakun Shi Wanli Xu Jun Zhang Xiaohong Li |
| author_facet | Yakun Shi Wanli Xu Jun Zhang Xiaohong Li |
| author_sort | Yakun Shi |
| collection | DOAJ |
| description | Ultrasonic signal classification in nondestructive testing is of great significance for the detection of defects. The current methods have mainly utilized low-level handcrafted features based on traditional signal processing approaches, such as the Fourier transform, wavelet transform and the like, to interpret the information carried by signals for classification. This paper proposes an automatic classification method via a convolutional neural network (CNN) which can automatically extract features from raw data to classify ultrasonic signals collected of a circumferential weld composed of austenitic and martensitic stainless steel with internal slots. Experiments demonstrate that our method outperforms the traditional classifier with manually extracted features, achieving an accuracy rate of classification up to 0.982. Furthermore, we visualize the shape, location and orientation of defects with a C-scan imaging process based on classification results, validating the effectiveness of the results. |
| first_indexed | 2024-03-10T04:23:15Z |
| format | Article |
| id | doaj.art-d5499a4e8e8842518b7d2326b01764b0 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T04:23:15Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-d5499a4e8e8842518b7d2326b01764b02023-11-23T07:45:23ZengMDPI AGApplied Sciences2076-34172022-04-01129417910.3390/app12094179Automated Classification of Ultrasonic Signal via a Convolutional Neural NetworkYakun Shi0Wanli Xu1Jun Zhang2Xiaohong Li3School of Power and Mechanical Engineering, Wuhan University, Wuhan 430072, ChinaSchool of Power and Mechanical Engineering, Wuhan University, Wuhan 430072, ChinaSchool of Power and Mechanical Engineering, Wuhan University, Wuhan 430072, ChinaSchool of Materials and Engineering, Southeast University, Nanjing 211189, ChinaUltrasonic signal classification in nondestructive testing is of great significance for the detection of defects. The current methods have mainly utilized low-level handcrafted features based on traditional signal processing approaches, such as the Fourier transform, wavelet transform and the like, to interpret the information carried by signals for classification. This paper proposes an automatic classification method via a convolutional neural network (CNN) which can automatically extract features from raw data to classify ultrasonic signals collected of a circumferential weld composed of austenitic and martensitic stainless steel with internal slots. Experiments demonstrate that our method outperforms the traditional classifier with manually extracted features, achieving an accuracy rate of classification up to 0.982. Furthermore, we visualize the shape, location and orientation of defects with a C-scan imaging process based on classification results, validating the effectiveness of the results.https://www.mdpi.com/2076-3417/12/9/4179ultrasonic signalautomated classificationfeaturessignal processingconvolutional neural network |
| spellingShingle | Yakun Shi Wanli Xu Jun Zhang Xiaohong Li Automated Classification of Ultrasonic Signal via a Convolutional Neural Network Applied Sciences ultrasonic signal automated classification features signal processing convolutional neural network |
| title | Automated Classification of Ultrasonic Signal via a Convolutional Neural Network |
| title_full | Automated Classification of Ultrasonic Signal via a Convolutional Neural Network |
| title_fullStr | Automated Classification of Ultrasonic Signal via a Convolutional Neural Network |
| title_full_unstemmed | Automated Classification of Ultrasonic Signal via a Convolutional Neural Network |
| title_short | Automated Classification of Ultrasonic Signal via a Convolutional Neural Network |
| title_sort | automated classification of ultrasonic signal via a convolutional neural network |
| topic | ultrasonic signal automated classification features signal processing convolutional neural network |
| url | https://www.mdpi.com/2076-3417/12/9/4179 |
| work_keys_str_mv | AT yakunshi automatedclassificationofultrasonicsignalviaaconvolutionalneuralnetwork AT wanlixu automatedclassificationofultrasonicsignalviaaconvolutionalneuralnetwork AT junzhang automatedclassificationofultrasonicsignalviaaconvolutionalneuralnetwork AT xiaohongli automatedclassificationofultrasonicsignalviaaconvolutionalneuralnetwork |