基于盲反卷积去噪的机车走行部齿轮箱故障诊断

Running Gear Gearbox Fault Diagnosis Based on BlindDeconvolution Denoising Locomotive

摘要:

为了有效地识别机车走行部的早期故障,提高我国重载机车的运输能力,以机车走行部齿轮箱为例,在分析总结大量实际振动信号的基础上,探讨了运用盲反卷积去噪的方法来提取机车齿轮的故障特征信息,即采用傅里叶变换在送入滤波器中使振动信号变换为时域信号；再对所有的盲信号进行盲源分离,与TSA(时间同步平均)方法相比,考虑了外界因素的影响,尽量避免了预测和诊断误差；通过对实际机车走行部齿轮振动信号的分析,成功提取到故障特征信号,阐述了该方法在机车走行部在线故障诊断系统中的应用,不仅能满足在线监测和故障的实时性和可靠性的要求,使机车在正常运行的时候,同时显示出其可靠性、耐用性和高置信度性。

Abstract:

In order to effectively identify early failures locomotive running gear to improve transport capacity of heavy-duty locomotives, locomotive running gear gearbox for example, summed up the basis of the analysis of a large number of actual vibration signals, discusses the use of blind deconvolution de-noising method for extracting characteristic information motorcycle gear, which uses Fourier transform filter manipulation in the vibration signal into time domain signal, and then all of the blind signal source separation, and TSA (time Synchronization average ) compared to consider the impact of external factors, try to avoid the prediction and diagnosis errors. Through the analysis of the actual locomotive running gear vibration signals to extract the fault characteristic signal successfully, the method described in the locomotive running gear line fault diagnosis system application, not only meet the requirements of real-time and reliability of online monitoring and fault diagnosis so that the normal operation of the locomotive at the time, while showing its reliability, durability, and high degree of confidence.