Intelligent fault diagnosis for rotating machinery using L_1/2-SF under variable rotational speed

Abstract

Sparse filtering (SF), as an effective feature extraction technique, has attracted considerable attention in the field of mechanical fault diagnosis. But the generalization ability of SF to handle non-stationary signal under variable rotational speed is still poor. When the rotating parts of mechanical transmission work at a constant speed, the collected vibration signal is strongly correlated with the fault type. However, the mappings will no longer be so simple under the condition of variable rotational speed, which brings a rigorous challenge to intelligent fault diagnosis. To overcome the aforementioned deficiency, a novel L1/2 regularized SF method ( L1/2-SF) is studied in this paper. Specifically, L1/2 regularization strategy is added to the cost function of SF, then the L1/2-SF is directly employed to extract sparse features from the raw vibration data under variable rotational speed condition. In order to understand the sparse feature extraction ability of the L1/2 regularization, a physical explanation of the sparse solution generated by the L1/2 regularization strategy is explored. Next, softmax regression is employed for fault classification connected with the output layer of L1/2-SF. The effectiveness of L1/2-SF method is verified using a planetary gearbox dataset and a bearing dataset, respectively. Experiment results show that L1/2-SF can deal well with the variable rotational speed problem and is superior to other methods.

Attention mechanism guided sparse filtering for mechanical intelligent fault diagnosis under variable speed condition

“…The planetary gearbox test bench as shown in figure 5 was used to collect vibration signals under variable speed condition [23]. The test bench mainly includes: motor, coupling, planetary gearbox, and bearing seat, etc.…”

Improvement of VMD for anomalous collision disturbance based on nonlinear l 1/2 norm

“…The l 1/2 norm is commonly used in the fields of feature extraction and signal processing. It is expressed as follows [35]:…”

Research on fault diagnosis of rolling bearings in roller-to-roller printing units based on siamese network

“…17,18 Meanwhile, unsupervised methods play more important roles in the diagnosis of rotating machinery under strong noise and varying rotational speeds such as Parallel Sparse Filtering and Auto Encoder. [19][20][21] New types of networks are also generated for sparse fault samples, such as Caps Network and Prototypical Network. 22,23 As to printing units, there are some special problems such as small number of fault samples, weak fault signals, and strong environmental noise.…”