Gear Monitoring System Based On Vibration Signal

Gear transmission is the main way of mechanical transmission, the gear failure in gear transmission is the inevitable phenomenon and the final home to return to, and is one of the important reasons induced malfunction.On-line monitoring and fault diagnosis of gear running state, to reduce equipment maintenance costs, is of great significance to prevent sudden accident, and received wide attention and research.The gear vibration signal analysis and processing, in order to judge the operation condition of the gear, the main method is currently running gear fault diagnosis. In this paper, LabVIEW programming language, designed and developed off-line analysis of online monitoring system based on gear and fault vibration signal system, the main research work in the following areas:1.The significance of off-line analysis of online monitoring system on the present research and the gearbox fault diagnosis technology were analyzed, the vibration from the gear meshing gear mechanism analysis of the common engagement fault mode causes as well as the failure modes of vibration signal characteristics.Statistical analysis of the time domain parameters, the amplitude spectrum and power spectrum, refinement spectrum, envelope spectrum, cepstrum, wavelet packet decomposition and reliability assessment principles,providing a theoretical for the off-line analysis of online monitoring system.2. Based on virtual instrument technology is developed gear vibration signal collection and analysis system.The hardware part for the sensor, the constant current source Conditioning, data acquisition card and optical encoder selected, the software part developed a parameter setting module, signal analysis module, data management module and help module implements gear meshing vibration data acquisition, monitoring, and fault analysis, fault diagnosis to build gear test rig, comparative analysis of gear normal and fault conditions vibration signal is verified in practice gear and off-line monitoring system fault analysis system accuracy and reliability.3. Aiming at feature extraction of gear fault pattern recognition, a method based on the Optimum Wavelet Packet Decomposition(OWPD) and Hidden Markov Model(HMM) is proposed in this paper. Processing of the vibration signals in the time domain is considered, using the wavelet packet. The characteristic energy automatically selected by OWPD is then employed as the input of HMM model for training and test. Finally the effect and accurate of the new method is validated by experiments.