| As one of the most important mechanical equipments in industrial production,the status of gearbox needs to be monitored at all times.With the gradual expansion of the production scale of enterprises,the traditional monitoring methods of gearbox can no longer meet the needs of enterprises.The information mined from the gearbox vibration signal can efficiently and accurately diagnose the current status of the gearbox.Therefore,fault diagnosis based on gearbox vibration signal is the main research direction of gearbox status monitoring.Based on the actual needs of enterprises,this paper designs and develops a gearbox gear vibration online monitoring and diagnosis system.(1)Analyze the impact of application scenarios of gearbox on system data acquisition methods,and design a data acquisition scheme based on Wi-Fi transmission for gearbox vibration online monitoring and diagnosis system.(2)Research on vibration fault characteristics of gearbox based on double-tree complex wavelet transform method of extraction.Aiming at the requirements of robustness and computational efficiency of gearbox vibration online monitoring and diagnosis system,the principle,structure and characteristics of dual-tree complex wavelet transform are studied.Combined with the feature extraction and information entropy theory of gearbox vibration signal in time domain and frequency domain,this paper finally realizes multi-dimensional feature vector extraction of gearbox vibration fault.(3)Deep belief network is an important model in deep learning.Study the principle,composition and training process of the deep belief network,and use the gearbox vibration experiment platform data to build and train the deep belief network model.Finally,compared with BP neural network and support vector machine,it proves that the system has good fault classification ability in gearbox vibration fault diagnosis.(4)Based on python,develop a gearbox vibration online monitoring and diagnosis system.The system can achieve 99.7% accuracy when troubleshooting the gearbox.The system can simultaneously a plurality of gearbox vibration fault monitoring device,and has a certain practicality. |