【摘要】 转向架是高铁的重要动力传输单元，转向架轴承作为转向架中的承力元件，长期承受交变载荷，是极易发生故障的部位。现有用于滚动轴承故障诊断的频域分析方法对适用条件有严格的要求，如快速谱峭度方法在分析具有较大干扰信息或是背景噪声的信号时，极易导致方法的失效，大大限制了相关方法在实际工程中的广泛应用。针对上述问题，提出多频谱融合评价的故障诊断与决策方法。构建一种频域分析方法的加权评价准则，从诊断效果、稳定性以及计算时间等三个方面进行构建，实现算法工程适配性的量化。提出一种频谱评价准则，实现对频域分析方法诊断效果的评价。针对高铁运营中的数据积累与完备的两个阶段，分别通过频谱特征降维融合以及最优化Fisher判别比进行频谱评价赋权，以获得具有最好诊断效果的融合频谱。通过数据采集试验对方法进行了有效性验证，表明该方法具有较好的工程适用性及鲁棒性。更多还原

【Abstract】 The rail bogie is recognized as an important power transmission unit in high-speed trains, and the bogie bearing, serving as a load-bearing element within it, is subjected to prolonged alternating loads and is highly prone to failure. Existing frequency domain analysis methods for rolling bearing fault diagnosis are limited by strict applicability conditions. For example, the fast kurtogram method often fails when analyzing signals contaminated by interference or excessive background noise, significantly limiting the widespread practical application of those methods. To address these limitations, a fault diagnosis and decision-making method based on multi-spectrum fusion evaluation is developed. A weighted evaluation criterion is constructed for frequency domain analysis methods, considering three aspects-diagnostic effect, stability, and calculation time-to quantify their engineering suitability. Furthermore, a spectrum evaluation criterion is established to assess the diagnostic effectiveness of frequency domain analysis methods. To accommodate the distinct requirements of data accumulation and completion phases in high-speed rail operation, the proposed spectrum evaluation criterion incorporates downscaled spectral feature fusion and an optimized Fisher’s discriminant ratio, respectively. This facilitates the selection of the fusion spectrum yielding optimal diagnostic performance. The validity of the method is confirmed through data collection experiments. The results demonstrate its good engineering applicability and robustness.更多还原