Search

In this paper, a novel bearing intelligent fault diagnosis method based on a novel krill herd algorithm (NKH) and kernel extreme learning machine (KELM) is proposed. Firstly, multiscale dispersion entropy (MDE) is used to extract fault features of bearings to obtain a set of fault feature vectors composed of dispersion entropy. Then, it is imported into the kernel extreme learning machine for fault diagnosis. But considering the kernel function parameters σ and the error penalty factor C will affect the classification accuracy of the kernel extreme learning machine, this paper uses the novel krill herd algorithm (NKH) for their optimization. The opposite populations are added to the NKH in the initialization of population to improve its speed and prevent local optimum, and during the period of looking for the optimal solution, the impulse operator is introduced to ensure it has enough impulse to rush out of the local optimal once into the local optimum. Finally, in order to verify the effectiveness of the proposed method, it was applied to the bearing fault experiment of Case Western Reserve University and XJTU-SY bearing data set. The results show that the proposed method not only has good fault diagnosis performance and generalization but also has fast convergence speed and does not easily fall into the local optimum. Therefore, this paper provides a method for fault diagnosis under different loads. Meanwhile, the new method (NKH-KELM) is compared and analyzed with other mainstream intelligent bearing fault diagnosis methods to verify the effectiveness and accuracy of the proposed method. [ABSTRACT FROM AUTHOR]

Aiming at the problem that the composite fault signal of the gearbox is weak and the fault characteristics are difficult to extract under strong noise environment, an improved singular spectrum decomposition (ISSD) method is proposed to extract the composite fault characteristics of the gearbox. Singular spectrum decomposition (SSD) has been proved to have higher decomposition accuracy and can better suppress modal mixing and pseudo component. However, noise has a great influence on it, and it is difficult to extract weak impact components. In order to improve the limitations of SSD, we chose the minimum entropy deconvolution adjustment (MEDA) as the pre-filter of the SSD to preprocess the signal. The main function of the minimum entropy deconvolution adjustment is to reduce noise and enhance the impact component, which can make up for the limitations of SSD. However, the ability of MEDA to reduce noise and enhance the impact signal is greatly affected by its parameter, the filter length. Therefore, to improve the shortcomings of MEDA, a parameter adaptive method based on Cuckoo Search (CS) is proposed. First, construct the objective function as the adaptive function of CS to optimize the MEDA algorithm. Then, the pre-processed signal is decomposed into singular spectral components (SSC) by SSD, and the meaningful components are selected by Correlation coefficient. For the existing modal mixing phenomenon, the SSC component is reconstructed to eliminate the misjudgment of the result. Then, the frequency spectrum analysis is performed to obtain the frequency information for fault diagnosis. Finally, the effectiveness and superiority of ISSD are validated by simulation signals and applying to compound faults of a Gear box test rig. [ABSTRACT FROM AUTHOR]