EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Quantitative Fault Diagnosis of Railway Wheel Polygonization Based on Fractional-Order-Enhanced Transform-Domain Multi-Instance Learning and FiLM Modulation

Tao Li, Xuyuan Gao, Zhoncheng Jiang, Wei Liu, Dengke Li, Xuancheng Yuan, Bowen Yao

Fractal and Fractional · 05.11.2026 · 10 (11) · 774

DOI: 10.3390/fractalfract10110774 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Fractal and Fractional, online erschienen am 05.11.2026. Verfasst von Tao Li und 6 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Hunan Province, and the State Key Laboratory of Heavy-duty and Express High-power Electric Locomotive.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wheel polygonization is a typical out-of-roundness fault in high-speed trains, and multi-order roughness spectra can quantitatively describe its fault condition. Variations in operating speed, wheel diameter, and reprofiling state cause differences in axle-box vibration responses, making the diagnosis of multi-order roughness amplitudes difficult. A fractional-order-enhanced transform-domain multi-instance learning method with FiLM modulation is proposed for quantitative fault diagnosis of wheel polygonization. First, axle-box vibration acceleration, operating speed, and measured roughness data are jointly processed to construct multi-instance samples containing angular-domain time series, order-domain spectra, vibration statistics, and operating-condition information. Second, a model integrating transform-domain multi-instance learning and FiLM modulation is constructed, combining a state-adaptive multi-regression mechanism with order-aware correlation mapping to achieve quantitative diagnosis of roughness amplitudes across orders 1–32. Finally, the Grünwald–Letnikov fractional-order difference is introduced into the loss function to enhance the model’s ability to learn inter-order correlations and overall spectral-shape features, thereby reducing diagnostic errors in multi-order roughness amplitudes. Experimental results show that the proposed method achieves an RMSE of 1.157 dB, 60.5% lower than that of CNN-LSTM, the best-performing comparison method, providing a quantitative diagnostic method for high-speed train wheel condition assessment and reprofiling evaluation.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Hunan Province
  • and the State Key Laboratory of Heavy-duty and Express High-power Electric Locomotive

Zitieren

APA

Li, T., Gao, X., Jiang, Z., Liu, W., Li, D., Yuan, X., & Yao, B. (2026). Quantitative Fault Diagnosis of Railway Wheel Polygonization Based on Fractional-Order-Enhanced Transform-Domain Multi-Instance Learning and FiLM Modulation. Fractal and Fractional, 10(11), 774. https://doi.org/10.3390/fractalfract10110774

Vancouver

Li T, Gao X, Jiang Z, Liu W, Li D, Yuan X, et al. Quantitative Fault Diagnosis of Railway Wheel Polygonization Based on Fractional-Order-Enhanced Transform-Domain Multi-Instance Learning and FiLM Modulation. Fractal and Fractional. 2026;10(11):774. doi:10.3390/fractalfract10110774

BibTeX
@article{Li2026,
  author = {Li, Tao and Gao, Xuyuan and Jiang, Zhoncheng and Liu, Wei and Li, Dengke and Yuan, Xuancheng and Yao, Bowen},
  title = {Quantitative Fault Diagnosis of Railway Wheel Polygonization Based on Fractional-Order-Enhanced Transform-Domain Multi-Instance Learning and FiLM Modulation},
  journal = {Fractal and Fractional},
  year = {2026},
  volume = {10},
  number = {11},
  pages = {774},
  doi = {10.3390/fractalfract10110774}
}
Kostenlos starten →