Intelligent Early Fault Diagnosis of Space Flywheel Rotor System.

Three frequently encountered problems-a variety of fault types, data with insufficient labels, and missing fault types-are the common challenges in the early fault diagnosis of space flywheel rotor systems. Focusing on the above issues, this paper proposes an intelligent early fault diagnosis method based on the multi-channel convolutional neural network with hierarchical branch and similarity clustering (HB-SC-MCCNN). First, a similarity clustering (SC) method is integrated into the parameter-shared dual MCCNN architecture to set up as the basic structural block. The hierarchical branch model and additional loss are then added to SC-MCCNN to form a hierarchical branch network, which simplifies the problem of fault multi-classification into binary classification with multi-steps. Based on the self-learning characteristics of the proposed model, the unlabeled data and the missing fault types in the training set are re-labeled to realize the re-training of the network. The results of the experiments for comparing the abilities between the proposed method and several advanced deep learning models confirm that on the established early fault dataset of the space flywheel rotor system, the proposed method successfully achieves the hierarchical diagnosis and presents stronger competitiveness in the case of insufficient labeled data and missing fault types at the same time.

Dynamic Evaluation of the Degradation Process of Vibration Performance for Machine Tool Spindle Bearings.

Real-time condition monitoring and fault diagnosis of spindle bearings are critical to the normal operation of the matching machine tool. In this work, considering the interference of random factors, the uncertainty of the vibration performance maintaining reliability (VPMR) is introduced for machine tool spindle bearings (MTSB). The maximum entropy method and Poisson counting principle are combined to solve the variation probability, so as to accurately characterize the degradation process of the optimal vibration performance state (OVPS) for MTSB. The dynamic mean uncertainty calculated using the least-squares method by polynomial fitting, fused into the grey bootstrap maximum entropy method, is utilized to evaluate the random fluctuation state of OVPS. Then, the VPMR is calculated, which is used to dynamically evaluate the failure degree of accuracy for MTSB. The results show that the maximum relative errors between the estimated true value and the actual value of the VPMR are 6.55% and 9.91%, and appropriate remedial measures should be taken before 6773 min and 5134 min for the MTSB in Case 1 and Case 2, respectively, so as to avoid serious safety accidents that are caused by the failure of OVPS.