journal article·2026-06

A Pipeline Defect Size Prediction Method Integrating Simulation-Driven, Data Augmentation, and Physics-Guided Approaches

Xulai Zhu, Yuxiang Zhang, Qiansheng Fang, Jin Jiang, Gongquan Zhang

Publisher page

Abstract

No abstract is available for this record. The assistant can identify its topic from the title, but cannot infer the study’s results.

Source: Not provided · Quality: missing

Research context

OpenAlex topics: Non-Destructive Testing Techniques · Structural Integrity and Reliability Analysis · Water Systems and Optimization

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (26)

Show source-provided references
1. Long, Y., Huang, S., Peng, L., et al.: A characteristic approximation approach to defect opening profile recognition in magnetic flux leakage detection [J]. IEEE Trans. Instrum. Meas. 70, 1–12 (2021). https://doi.org/10.1109/TIM.2021.305018510.1109/TIM.2021.3050185 ↗
2. Dai, L., Feng, Q., Sutherland, J., et al.: Application of MFL on girth-weld defect detection of oil and gas pipelines [J]. J. Pipeline Syst. Eng. Pract. 11(4), 04020047 (2020). https://doi.org/10.1061/(ASCE)PS.1949-1204.000049710.1061/(ASCE)PS.1949-1204.0000497 ↗
3. Feng, J., Li, F., Lu, S., et al.: Injurious or noninjurious defect identification from MFL images in pipeline inspection using convolutional neural network [J]. IEEE Trans. Instrum. Meas. 66(7), 1883–1892 (2017). https://doi.org/10.1109/TIM.2017.267302410.1109/TIM.2017.2673024 ↗
4. Bo, F., Jianbo, W., Hongming, T., et al.: A review of magnetic flux leakage nondestructive testing [J]. Materials 15(20), 7362 (2022). https://doi.org/10.3390/MA1520736210.3390/MA15207362 ↗
5. Feng, J., Yao, Y., Lu, S., et al.: Domain knowledge-based deep-broad learning framework for fault diagnosis [J]. IEEE Trans. Ind. Electron. 68(4), 3454–3464 (2021). https://doi.org/10.1109/TIE.2020.298208510.1109/TIE.2020.2982085 ↗
6. Priewald, R.H., Magele, C., Ledger, P.D., et al.: Fast magnetic flux leakage signal inversion for the reconstruction of arbitrary defect profiles in steel using finite elements [J]. IEEE Trans. Magn. 49(1), 506–516 (2013). https://doi.org/10.1109/TMAG.2012.220811910.1109/TMAG.2012.2208119 ↗
7. Feng, J., Lu, S., Liu, J., et al.: A sensor liftoff modification method of magnetic flux leakage signal for defect profile estimation. IEEE Transactions on Magnetics, 6201813 (2017). https://doi.org/10.1109/TMAG.2017.269062810.1109/TMAG.2017.2690628 ↗
8. Liu J, Ren Y.: A general transfer framework based on industrial process fault diagnosis under small samples [J]. IEEE Transactions on Industrial Informatics, pp. 99. (2020). https://doi.org/10.1109/TII.2020.303615910.1109/TII.2020.3036159 ↗
9. Li Y, Sun C.: Research on magnetic flux leakage testing of pipelines by finite element simulation combined with artificial neural network [J]. Int. J. Pres. Ves. Pip. 212(PartA) (2024). https://doi.org/10.1016/j.ijpvp.2024.10533810.1016/j.ijpvp.2024.105338 ↗
10. Xu, L., Wang, Y., Mo, L., et al.: The research progress and prospect of data mining methods on corrosion prediction of oil and gas pipelines [J]. Eng. Fail. Anal. (2023). https://doi.org/10.1016/j.engfailanal.2022.10695110.1016/j.engfailanal.2022.106951 ↗
11. Wu, L., Liang, W., Sha, D.: Cross-domain feature selection and diagnosis of oil and gas pipeline defects based on transfer learning [J]. Eng. Fail. Anal. (2023). https://doi.org/10.1016/j.engfailanal.2022.10687610.1016/j.engfailanal.2022.106876 ↗
12. Wang, L., Zhang, H., Liu, J., et al.: Defect size quantification for pipeline magnetic flux leakage detection system via multilevel knowledge-guided neural network [J]. IEEE Trans. Industr. Electron. 70(9), 9550–9560 (2022). https://doi.org/10.1109/TIE.2022.321055710.1109/TIE.2022.3210557 ↗
13. Xie J, Yang J, Fu K, et al.: Quantitative assessment of pipeline defects utilizing a dual-stage deep learning framework: integration of pretrained YOLO network and multi-input parallel convolution architectures on magnetic flux leakage data [J]. J. Pipeline Sci. Eng. 100282 (2025). https://doi.org/10.1016/j.jpse.2025.100282.10.1016/j.jpse.2025.100282 ↗
14. Gao, B., Zhao, H., Miao, X.: Multi-modal cascade detection of pipeline defects based on deep transfer metric learning. Eng. Fail. Anal. (2024). https://doi.org/10.1016/j.engfailanal.2024.10821610.1016/j.engfailanal.2024.108216 ↗
15. Li S, Bai L, Ren C, et al.: A multidirectional magnetic flux leakage detection based crack 3-D profile reconstruction method [J]. Mech. Syst. Signal Process. 228(000) (2025). https://doi.org/10.1016/j.ymssp.2025.11240810.1016/j.ymssp.2025.112408 ↗
16. Yang J, Xie J, Gao X, et al.: Synthetic magnetic flux leakage signal generation using diffusion models: a novel approach to improve pipeline defect detection accuracy [J]. J. Pipeline Sci. Eng. 100363 (2025). https://doi.org/10.1016/j.jpse.2025.10036310.1016/j.jpse.2025.100363 ↗
17. Liu, C., Antypenko, R., Sushko, I., et al.: Intrusion detection system after data augmentation schemes based on the VAE and CVAE. IEEE Transactions on Reliability 71(2), 1000–1010 (2022). https://doi.org/10.1109/TR.2022.316487710.1109/TR.2022.3164877 ↗
18. Liu, Y., Fu, S., Lin, L., et al.: DECVAE: data augmentation via conditional variational auto-encoder with distribution enhancement for few-shot fault diagnosis of mechanical system. Meas. Sci. Technol. 35(4), 046104 (2024). https://doi.org/10.1088/1361-6501/ad197c10.1088/1361-6501/ad197c ↗
19. Peres, R.S., Azevedo, M., Araújo, S.O., et al.: Generative adversarial networks for data augmentation in structural adhesive inspection. Applied Sciences 11(7), 3086 (2021). https://doi.org/10.3390/app1107308610.3390/app11073086 ↗
20. Qiu, Z., Huang, P., Zheng, F., et al.: The synergistic evolution of pipeline MFL inspection: A review on the fusion of physical models, AI, and multi-modal sensing [J]. Sens. Actuators A: Phys. 398(c), 117367 (2026). https://doi.org/10.1016/j.sna.2025.11736710.1016/j.sna.2025.117367 ↗
21. Jiang X, Hu Y, Cao S, et al.: Physical-guided graph deep learning for composite pipelines structural health monitoring [J]. Structural Health Monitor. 14759217251368998 (2025). https://doi.org/10.1177/1475921725136899810.1177/14759217251368998 ↗
22. Wu, C., Lu, H., Liu, D., et al.: Research on gas pipeline leakage prediction model based on physics-aware GL-TransLSTM [J]. Biomimetics 10(11), 743 (2025). https://doi.org/10.3390/biomimetics1011074310.3390/biomimetics10110743 ↗
23. Xiong, Y., Liu, S., Hou, L., et al.: Magnetic flux leakage defect size estimation method based on physics-informed neural network. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences (2024). https://doi.org/10.1098/rsta.2022.038710.1098/rsta.2022.0387 ↗
24. Sohn K, Lee H, Yan X.: Learning structured output representation using deep conditional generative models [J]. Adv. Neural Inform. Process. Syst. 28 (2015)
25. Garcia-Perez, A., Gomez-Silva, M.J., de la Escalera-Hueso, A.: A generative AI approach to improve in-situ vision tool wear monitoring with scarce data [J]. J. Intell. Manuf. 36(5), 3165–3183 (2025). https://doi.org/10.1007/s10845-024-02379-210.1007/s10845-024-02379-2 ↗
26. Zhang, J., Sun, M., Qin, L., et al.: In-line inspection methods and tools for oil and gas pipeline: a review. International Journal of Pressure Vessels and Piping 214, 105409 (2025). https://doi.org/10.1016/j.ijpvp.2024.10540910.1016/j.ijpvp.2024.105409 ↗