Fatigue life prediction method of complex mechanical structure based on EMD

In order to improve the accuracy of prediction results, a fatigue life prediction method of complex mechanical structures based on EMD is studied. Firstly, the complex mechanical structure signal is decomposed into several eigenmode functions by EMD decomposition method. Then, the orthogonal coefficient is introduced to improve the EMD decomposition method, and the decomposition results of vibration signals of complex mechanical structures are output. Finally, the results of vibration signal decomposition are used as the input of support vector regression machine, and the fatigue life prediction model of complex mechanical structure is constructed, and the fatigue life prediction results are output. The experimental results show that this method can effectively denoise the signal, and the accuracy of the prediction results is high, which shows that the prediction results are reliable.