基于深度学习和经验模态分解的双列圆锥滚动轴承故障诊断

双列圆锥滚动轴承在列车走行部应用广泛,由于该类轴承结构比较复杂,传统的故障诊断方法难以识别该类轴承的早期微弱故障.为此,提出基于深度学习的双列圆锥滚动轴承早期微弱故障诊断方法.首先,对轴承的振动信号进行经验模态分解,提取信号的瞬时能量构造特征向量;最后,利用深度学习方法对特征向量进行无监督学习,生成故障诊断分类器,完成故障的分类识别.实验中对某型号双列圆锥滚动轴承的正常状态、内圈故障和外圈故障进行信号分析与故障识别.结果表明,所提方法能有效识别双列圆锥滚动轴承的早期微弱故障,分类准确率达到98%.

全地形车的轴承寿命优化

全地形车因不受地形限制且极具玩乐的属性,在国内外高速发展。作为支撑运转的轮毂轴承,其失效是直接影响全地形车寿命和安全性的重要因素之一。本文针对全地形车恶劣工况下双列圆锥滚动轴承的失效情况,首先对内外圈和密封结构进行模型建立,针对预紧力对工作游隙的影响分析和计算,其次通过软件Romax得出云图对轴承寿命进行预测,然后用台架试验机进行试验,分析试验结果,选取出最优的工作游隙和密封结构。最后,在全地形标准测试场地进行6000km相应测试,应用Trail1000,希望通过以上努力将轴承失效率降为零。

Time-varying stiffness analysis of double-row tapered roller bearing based on the mapping structure of bearing stiffness matrix

Time-varying stiffness is one of the most important dynamic characteristics of rolling element bearings.The method of analyzing the elements in the bearing stiffness matrix is usually adopted to investigate the characteristics of bearing stiffness.Linear mapping structure of the bearing stiffness matrix is helpful to understand the varying compliance excitation and its influence on vibration transmission.In this study,a method to analyze the mapping structure of bearing stiffness matrix is proposed based on the singular value decomposition of block matrices in the stiffness matrix.Not only does this method have the advantages of coordinate transformation independence and unit independence,but also the analysis procedure involved is geometrically intuitive.The time-varying stiffness matrix of double-row tapered bearing is calculated and analyzed using the proposed method under two representative load cases.The principal stiffnesses and principal axes defined in the method together indicate the dominant and insignificant stiffness properties with the corresponding directions,and the vibration transmission properties are also revealed.Besides,the coupling behaviors between different shaft motions are found during the analysis of mapping structure.The mechanism of the generation of varying compliance excitation is also revealed.