Varying Speed Diagnosis of High Speed Train Bogie Rolling Bearing: Real Train Experiment, Comparison and Prediction of Transfer Learning Performance

Bo Yang, Tengfei Wang, Jingsong XieCivil-comp 2024 · DOI

Abstract

Intelligent fault diagnosis of high-speed train bogies faces significant challenges as speeds increase: diagnostic models trained on lower-speed data often fail at high velocities, and labeled fault data at high speeds is difficult to obtain. This paper presents a framework for reliably diagnosing unlabeled signals at varying speeds using limited labeled samples through deep transfer learning. The study involves a real-train experiment on a rolling test bed to obtain fault data across a range of speeds (50–350 km/h). By analyzing distributional differences and cross-speed transfer performance, the proposed model predicts the optimal source domain for high-speed monitoring. The feasibility and stability of the method are verified across various signal processing techniques and network architectures.

Introduction

As high-speed trains (HSTs) push the limits of velocity, the mechanical signatures of their components change. A diagnostic model trained to recognize a failing bearing at 100 km/h often fails at 300 km/h because the vibration patterns—the "features" the AI looks for—shift significantly. The core problem is a lack of labeled data; while it is relatively easy to collect and label fault data at lower speeds in controlled environments, doing so at 350 km/h is expensive and rare. This creates a "label-less" problem for high-speed operations. Engineers need a way to take the knowledge gained at lower speeds (the source domain) and apply it to higher speeds (the target domain) without needing a new set of labels for every incremental speed increase.

Proposed Methodology

The authors propose an adaptive transfer learning strategy composed of three main stages:

  1. Feature Distribution Difference Calculation: A 1D Convolutional Neural Network (CNN) extracts features from vibration signals. The "distance" between these features across different speeds is measured using metrics like Maximum Mean Discrepancy (MMD), Wasserstein Distance (WD), and Cosine Similarity.
  2. Cross-Transfer Learning: The performance of models trained at one speed is tested at another across various transfer learning (TL) algorithms, including Deep Adaptation Network (DAN), Domain-Adversarial Neural Network (DANN), and Batch Nuclear-norm Maximization (BNM).
  3. Ensemble Learning Mapping: Gradient Boosting Regression fits the relationship between distribution differences and actual diagnostic accuracy, allowing the system to predict transfer performance before deployment.
Workflow of the proposed adaptive transfer learning strategy, including discrepancy computation and performance prediction.

Experimental Setup

The study is grounded in high-fidelity experimental data rather than simulations. The platform utilizes a real high-speed train car on a full-scale rolling test bed, employing NTN CRI-2692 double-row tapered roller bearings. Simulated "real-world" damages, including outer ring indentation, peeling, and corrosion, were introduced. Vibration data was sampled at 25.6 kHz across seven distinct speed conditions ranging from 50 km/h to 350 km/h.

Experimental setup showing (a) the real high-speed train on the test bed and (b) a schematic of the rolling test bed.

Results and Discussion

Transferability and Speed Discrepancy

The research reveals that "transferability" between speeds is non-intuitive. One might assume that a 250 km/h model is naturally the best fit for 300 km/h data, but complex mechanical resonances can mean a much lower speed provides a better feature set for a high-speed target.

Performance Analysis

The BNM (Batch Nuclear-norm Maximization) method emerged as the most robust, often achieving near 100% accuracy when transferring between various speed domains using envelope spectrum data. The proposed framework successfully predicted the "optimal source domain." For example, when diagnosing a 350 km/h target, the model correctly identified that transferring from the 200 km/h or 300 km/h source would yield the highest accuracy. The framework also proved stable across different bogie structures.

Key Insights

  • Envelope Spectrum: Using envelope spectral data consistently outperformed raw time-domain data in transfer tasks.
  • Negative Transfer: Some popular methods, like "DeepCoral," suffered from "negative transfer," where the transfer process actually degraded the model's performance compared to simpler approaches.

Conclusion and Future Work

This study demonstrates that deep transfer learning can effectively bridge the gap between low-speed labeled data and high-speed unlabeled operating conditions in rail maintenance. While successful, future work will address the computational costs of finding optimal source-target matches and the real-time constraints for on-board deployment. Further theoretical investigation into the uncertainty of transfer between highly disparate conditions is also required.

Summary updated

Abstract

Due to the increasing speed of high-speed trains, intelligent fault diagnosis of train bogies is facing new problems: the diagnostic model for lower speeds is no longer applicable, and the lack of fault labels for high speed data makes the training of deep learning diagnostic models even more difficult.In order to be able to reliably diagnose unlabeled signals of different speeds using a limited number of labeled fault samples, this paper conducts an experiment and comparison of the effects of transfer learning on bearing faults of a real train.experiments and migration learning effects are compared.The axle bearing failure simulation experiment was conducted on a real high-speed train car using a rolling test bed, and the monitoring data with fault labels at different speeds were obtained; then the cross-migration was conducted using multiple speed monitoring data and multiple migration learning methods to obtain the cross-speed migration learning fault diagnosis effect; finally, the comparison of the distributional differences and the migration learning effect dataset was used to ensure the migration learning model could accomplish the monitoring at higher speeds.model can accomplish higher speed monitoring data migration diagnosis.At the same time, this paper uses a variety of signal pre-processing methods, network models and migration learning methods in the proposed framework for comparison, further verifying the feasibility and stability of the prediction method, and gives the optimal application of reference suggestions.
BibTeX
@inproceedings{yang2024varying,
  author = {Bo Yang and Tengfei Wang and Jingsong Xie},
  title = {{Varying Speed Diagnosis of High Speed Train Bogie Rolling Bearing: Real Train Experiment, Comparison and Prediction of Transfer Learning Performance}},
  booktitle = {Civil-comp},
  year = {2024},
  doi = {10.4203/ccc.7.28.1},
}
Figure