Lubrication State Recognition Based on Energy Characteristics of Friction Vibration with EEMD and SVM

In order to identify different lubrication states, experiments were carried out on a Bruker UMT-3 tester. The experimental results show that the frequency band energy characteristics of friction vibration signals are under states. Based this, state recognition method with ensemble empirical mode decomposition (EEMD) and support vector machine (SVM) was proposed. decomposed into finite number stationary intrinsic functions (IMFs) EEMD method. first six IMF components containing main information retained calculate ratio construct feature vector. mixed can be identified by hundred percent, there is slight confusion between boundary dry friction. an effective proposed used