Jianbo Yin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jianbo Yin has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Hongmei Shi
School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing 100044, China
2 shared publications - Jiayi Yao
School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, China
2 shared publications - Shi Liu
School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, China
2 shared publications - Xining Xu
State Key Laboratory of Advanced Rail Autonomous Operation, Beijing Jiaotong University, Beijing, 100044, China; School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, 100044, China
2 shared publications Song Yang
School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, China
1 shared publication- Song Yang
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 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (19) , 35916-35929
PLI and CNN-BiLSTM: An Enhanced Data Augmentation and Deep Learning Approach for Defect Recognition in Spiral Welded Pipe Based on Ultrasonic Guided Waves
Defect detection in urban heat pipes is critical for ensuring system safety and reliability, where Ultrasonic Guided Wave (UGW) technology plays a pivotal role. However, the complex guided wave propagation caused by spiral welds (resulting in low SNR) and the scarcity of valid defect samples (due to high acquisition costs) significantly reduce the performance of conventional deep learning algorithms. To address these challenges, we proposed a Proportional Linear Integration (PLI) model for data augmentation that preserves label invariance through linear transformations, accounting for the inherent linearity of UGW defect echo signals—a property often overlooked. PLI integrates four single-sample and two multi-sample linear transformation methods in equal proportions. Furthermore, we propose a hybrid CNN-BiLSTM architecture integrating Convolutional Neural Networks (CNNs) for local feature extraction with Bi-directional Long Short-Term Memory (BiLSTM) networks for long-range dependency capture, followed by LSTM to preserve the physical temporal sequence of UGWs. Using a small dataset of artificial defects (validated as equivalent to real defects), we applied original and PLI-augmented data to train our CNN-BiLSTM model, achieving defect localization error of only 0.2384 meters—outperforming other data augmentation methods and deep learning models. Our results highlight the method’s ability to significantly enhance defect localization precision in spiral-welded pipes, even with scarce samples. This study underscores the potential of tailored data augmentation and hybrid deep learning models for Non-Destructive Testing (NDT) and Structural Health Monitoring (SHM) of UGW time-series signals.
- 1 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (19) , 35916-35929
PLI and CNN-BiLSTM: An Enhanced Data Augmentation and Deep Learning Approach for Defect Recognition in Spiral Welded Pipe Based on Ultrasonic Guided Waves
Defect detection in urban heat pipes is critical for ensuring system safety and reliability, where Ultrasonic Guided Wave (UGW) technology plays a pivotal role. However, the complex guided wave propagation caused by spiral welds (resulting in low SNR) and the scarcity of valid defect samples (due to high acquisition costs) significantly reduce the performance of conventional deep learning algorithms. To address these challenges, we proposed a Proportional Linear Integration (PLI) model for data augmentation that preserves label invariance through linear transformations, accounting for the inherent linearity of UGW defect echo signals—a property often overlooked. PLI integrates four single-sample and two multi-sample linear transformation methods in equal proportions. Furthermore, we propose a hybrid CNN-BiLSTM architecture integrating Convolutional Neural Networks (CNNs) for local feature extraction with Bi-directional Long Short-Term Memory (BiLSTM) networks for long-range dependency capture, followed by LSTM to preserve the physical temporal sequence of UGWs. Using a small dataset of artificial defects (validated as equivalent to real defects), we applied original and PLI-augmented data to train our CNN-BiLSTM model, achieving defect localization error of only 0.2384 meters—outperforming other data augmentation methods and deep learning models. Our results highlight the method’s ability to significantly enhance defect localization precision in spiral-welded pipes, even with scarce samples. This study underscores the potential of tailored data augmentation and hybrid deep learning models for Non-Destructive Testing (NDT) and Structural Health Monitoring (SHM) of UGW time-series signals.