Interference from high-speed trains meeting operating conditions frequently results in poor assessments when track operational status is monitored based on onboard signals. In extreme situations, this can lead to safety problems and financial losses. High-speed train meeting must be removed to assess track service conditions more precisely. In light of this, this paper proposes an intelligent identification technique based on onboard vibration characteristics for high-speed trains meeting operating conditions. Firstly, a simulation model of high-speed trains meeting situations is built using finite element, dynamic, and aerodynamic models. Secondly, based on statistical analysis of large amounts of on-site measured data, this model reveals distinctive waveforms during train encounters by analyzing the lateral vibration characteristics of high-speed trains during meeting operating conditions. Lastly, a technique based on these distinctive vibration waveforms is suggested for identifying meeting conditions. Validation using operational onboard measurement data confirms that the proposed meeting operating condition recognition method achieves an accuracy rate of 94.7%. This paper holds significant implications for track condition assessment and meeting operating condition identification.
Yin et al. (2026) studied this question.