基于Kriging模型的高速列车齿轮箱箱体裂纹识别

Crack Identification of High-speed Train Gear Box Based on Kriging Model

齿轮箱作为高速列车走行部的关键部件,其箱体结构的性能时刻关乎着列车运行安全性。裂纹作为一种重要且常见的结构损伤形式,其存在与否以及损伤情况对结构的性能有着极其重要的影响。基于此,提出了一种基于Kriging代理模型的非运行条件下高速列车齿轮箱箱体裂纹识别方法。利用拉丁超立方取样抽取裂纹参数样本,通过有限元分析计算得到相应的结构响应,从而构建Kriging代理模型,模拟四种工况进行模型精度验证。结果表明,与基于信号处理和基于数值分析的裂纹识别相比,该方法在保证识别精度的情况下,极大地提高了识别效率,同时还可实现裂纹定位识别。

As a key component of the train running part,the performance of the gearbox structure is always related to the safety of train operation.As an common and important form of structural damage,cracks have an extremely important impact on the performance of the structure whether it exists or not and the damage.Based on this,a crack identification method for high-speed train gear box under non-operating conditions based on Kriging agent model is proposed.The Latin hypercube sampling is used to extract the crack parameter samples,and the corresponding structural response is obtained through finite element analysis and calculation,so as to construct the Kriging proxy model and simulate the four working conditions to verify the model accuracy.The results show that,compared with the crack recognition based on signal processing and numerical analysis,this method greatly improves the recognition efficiency while ensuring the recognition accuracy,and can also achieve crack location recognition.