Vibration signal diagnostic analysis method based on EEMD and deep domain adversarial network

The invention provides a vibration signal diagnosis and analysis method based on EEMD and a depth domain adversarial network, and the method comprises the following steps: constructing an EEMD time-frequency graph group of time-frequency characteristics based on the vibration signals of rotating equipment under different working conditions; an EMBRNDNMD model is constructed; and based on the EEMD time-frequency graph group and the EMBRNDNMD model, a fault classification result is obtained, and vibration signal diagnosis is completed. According to the method, the adversarial network module and the MK-MMD distribution difference evaluation method are introduced to optimize the MBRN, so that the EMBRNDNMD model can achieve high target domain state diagnosis accuracy in various migration modes, and the method has high variable working condition scene adaptability. 本发明提供了基于EEMD和深度域对抗网络的振动信号诊断分析方法，包括以下步骤：基于不同工况下的旋转设备振动信号，构建时频特性的EEMD时频图组；构建EMBRNDNMD模型；基于所述EEMD时频图组与所述EMBRNDNMD模型，获得故障分类结果，完成振动信号诊断。本发明引入与对抗网络模块和MK-MMD分