齿轮箱在线监测诊断方法研究与系统设计

Research on Gearbox On-line Monitoring and Fault Diagnosis System

研究了齿轮箱齿面缺损和齿轮偏心等典型故障的时域、频域和时频域特征,以此为依据提取了故障特征向量,应用RBF神经网络进行了齿轮箱故障识别,识别试验表明文中所研究的方法能准确识别齿轮箱故障状态。以前面研究的故障诊断方法为基础设计了基于LabVIEW的齿轮箱在线监测诊断系统,系统具有齿轮箱振动信号采集,齿轮箱振动信号时域、频域分析和时频分析,以及齿轮箱故障模式识别功能,系统已经应用于交通部救助局海洋救助船船舶动力装置监测诊断系统,作为齿轮箱监测诊断模块。

The vibration signal of typical failures of gearbox like gear wear and eccentric has been analyzed,using the method like time-domain analysis,frequency-domain analysis,and time-frequency analysis.On the basis of the research,different key characteristics of time-domain and frequency-domain have been chosen as RBF neural network inputs,the pattern recognition of different failures in gearbox have been carried precisely.The on-line monitoring and fault diagnosis system for gearbox has been designed.The main function of the system is time-domain analysis,frequency-domain analysis,time-frequency analysis,and pattern recognition of gearbox running state.As one part of main power plant on-line monitoring and fault diagnosing system,it has been used in ocean salvage vessel of The Ministry of Transport.