Rolling Bearing Performance Degradation Assessment Based on Convolutional Sparse Combination Learning

A novel bearing performance degradation assessment method based on convolutional sparse coding and combination learning is proposed in this paper, which can avoid the impact of the traditional features on the assessment results under complex operation conditions. The vibration signal can be decomposed into the convolution of the kernel sets and their corresponding sparse solutions using convolutional sparse coding. The learned kernel sets based on the training signal samples are the comprehensive embodiment of the information related to the operational complexity and the bearing healthy state, and the corresponding sparse solutions indicate the energy of the kernel activation. Asimulation experiment of bearing signal proves that the activation energy of the kernels, which are more related to bearing healthy, will rise with the increase of the bearing degradation degree; meanwhile, the error of reconstructed signal based on the learned kernel sets and original signal will decrease since the description effect of convolutional sparse coding to the signal will be enhanced with the periodic strengthen of signal caused by the fault. Thus, an index based on the kernel sparse norms and the errors between the original and reconstructed signals has been proposed to evaluate the degradation degree of the bearing in this paper. On the other hand, combination learning will be fused into the convolutional sparse coding to improve the real-time performance of the index calculation and obtain the best assessment result in the testing part by dividing the kernel dictionary set into multiple sub-dictionaries. A bearing run-to-fail experiment is analyzed to verify the validity of the proposed method. The testing results show that the proposed assessment index can clearly detect the initial fault, serve fault and failure of the bearing in the whole life, and the proposed method is more self-adaptive and sensitive to the fault degree. In addition, it is verified that the time consumption of the combination dictionaries is less than that of a single dictionary set.