Song Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Song Yang has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Faye Zhang
Shandong University
1 shared publication - Feiyu Teng
School of Control Science and Engineering, Shandong University, Jinan, China
1 shared publication - Hong Zhang
School of Control Science and Engineering, Shandong University, Jinan, China
1 shared publication - Hongmei Shi
School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing 100044, China
1 shared publication - Jianbo Yin
School of Intelligence Science and Technology, University of Science and Technology Beijing, Beijing, China
1 shared publication - Jiayi Yao
School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, China
1 shared publication
Latest Publications
- 30 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 1-20
Segformer: A Transformer-Based Deep Learning Framework for Defect Recognition of Spiral Welded Pipeline Based on Ultrasonic Guided Waves
Ultrasonic guided wave pipeline inspection plays a crucial role in structural integrity assessment. In spiral-welded pipelines, ultrasonic guided-wave defect signals are typically weak, multimodal, dispersive, and globally distributed, requiring models that preserve local physical semantics while directly and flexibly capturing long-range dependencies for defect recognition and localization—an objective that remains challenging for existing approaches. To address these challenges, this paper proposes Segformer, an innovative Transformer-based model enhanced by a segmentation mechanism. Recognizing the influence of spiral welds and the critical importance of local features in guided wave signals, our approach incorporates a time-segmentation strategy to effectively capture both global and local signal characteristics. We first constructed artificial defects and validated their equivalence to real-world defects. Using the resulting dataset, our model achieved 100% defect identification accuracy and a localization error of just 0.080 meters. We also performed validation experiments on impulse noise samples, real defects, and real-world water-filled pipeline system and achieved satisfactory results. Furthermore, uncertainty evaluation and interpretability analysis were conducted to verify the reliability of the model. The results demonstrate that Segformer can autonomously extract statistically significant features from guided wave echo signals, enabling accurate defect detection. This advancement positions the model as a robust solution for time-series signal analysis in guided wave-based Non-Destructive Testing (NDT) and Structural Health Monitoring (SHM) applications.
- 30 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 1-20
Segformer: A Transformer-Based Deep Learning Framework for Defect Recognition of Spiral Welded Pipeline Based on Ultrasonic Guided Waves
Ultrasonic guided wave pipeline inspection plays a crucial role in structural integrity assessment. In spiral-welded pipelines, ultrasonic guided-wave defect signals are typically weak, multimodal, dispersive, and globally distributed, requiring models that preserve local physical semantics while directly and flexibly capturing long-range dependencies for defect recognition and localization—an objective that remains challenging for existing approaches. To address these challenges, this paper proposes Segformer, an innovative Transformer-based model enhanced by a segmentation mechanism. Recognizing the influence of spiral welds and the critical importance of local features in guided wave signals, our approach incorporates a time-segmentation strategy to effectively capture both global and local signal characteristics. We first constructed artificial defects and validated their equivalence to real-world defects. Using the resulting dataset, our model achieved 100% defect identification accuracy and a localization error of just 0.080 meters. We also performed validation experiments on impulse noise samples, real defects, and real-world water-filled pipeline system and achieved satisfactory results. Furthermore, uncertainty evaluation and interpretability analysis were conducted to verify the reliability of the model. The results demonstrate that Segformer can autonomously extract statistically significant features from guided wave echo signals, enabling accurate defect detection. This advancement positions the model as a robust solution for time-series signal analysis in guided wave-based Non-Destructive Testing (NDT) and Structural Health Monitoring (SHM) applications.
- 1 April 2025
- Published by IOP Publishing in Smart Materials and Structures
- Vol. 34 (4) , 045002
Dual-signal reconstruction algorithm under empirical mode decomposition in ultrasonic guided waves for temperature compensation
Pipeline structures are widely used in industry, but the increase in service life may lead to damage to the pipeline structure, bringing economic losses. Ultrasonic guided wave has been widely used for accurate damage detection of pipeline structures. However, temperature variations can also lead to changes in guided wave signals. In order to reduce the influence brought by the external environment, this paper proposes a dual-signal reconstruction method based on empirical mode decomposition. By simultaneously performing empirical mode decomposition on the baseline signal and the test signal and quantifying the correlation between their intrinsic mode functions, the similarity between the two signals can be effectively enhanced, thereby mitigating the impact of signal fluctuations caused by environmental variations. The experiments were conducted with 28.25 ∘C as the baseline, and 100 % accuracy of condition monitoring was achieved under a temperature fluctuation of 9.5 ∘C.
- 1 April 2025
- Published by IOP Publishing in Smart Materials and Structures
- Vol. 34 (4) , 045002
Dual-signal reconstruction algorithm under empirical mode decomposition in ultrasonic guided waves for temperature compensation
Pipeline structures are widely used in industry, but the increase in service life may lead to damage to the pipeline structure, bringing economic losses. Ultrasonic guided wave has been widely used for accurate damage detection of pipeline structures. However, temperature variations can also lead to changes in guided wave signals. In order to reduce the influence brought by the external environment, this paper proposes a dual-signal reconstruction method based on empirical mode decomposition. By simultaneously performing empirical mode decomposition on the baseline signal and the test signal and quantifying the correlation between their intrinsic mode functions, the similarity between the two signals can be effectively enhanced, thereby mitigating the impact of signal fluctuations caused by environmental variations. The experiments were conducted with 28.25 ∘C as the baseline, and 100 % accuracy of condition monitoring was achieved under a temperature fluctuation of 9.5 ∘C.