Selective laser sintering (SLS) is a desirable method for fabricating human motion detecting sensors as it can produce a complex shape with different materials that are machinable to specific applications.

Deep learning techniques have been widely used to achieve promising results for fault diagnosis. In many real-world fault diagnosis applications, labeled training data (source domain) and unlabeled test data (target domain) have different distributions due to the frequent changes of working conditions, leading to performance degradation. This study proposes an end-to-end unsupervised domain adaptation bearing fault diagnosis model that combines domain alignment and discriminative feature learning on the basis of a 1D convolutional neural network. Joint training with classification loss, center-based discriminative loss, and correlation alignment loss between the two domains can adapt learned representations in the source domain for application to the target domain. Such joint training can also guarantee domain-invariant features with good intraclass compactness and interclass separability. Meanwhile, the extracted features can efficiently improve the cross-domain testing performance. Experimental results on the Case Western Reserve University bearing datasets confirm the superiority of the proposed method over many existing methods.

No abstract

In many practical fault diagnosis applications, the acquisition of fault data labels requires substantial manpower and resources, which are sometimes impossible to achieve. To address this, an unsupervised bearing fault diagnosis method based on deep clustering is proposed. In this method, an autoencoder is initially applied to the signal spectrum to learn the initial representation. Then, its potential manifold is further searched, and a Gaussian mixture model is finally used for clustering. Experiments conducted on the Case Western Reserve University bearing datasets show that the proposed method can find the optimal clusterable manifold. Moreover, its clustering performance is better than those of the current advanced baseline methods, and it is only slightly complex. Thus, the effectiveness of the proposed method is verified.

No abstract

No abstract

No abstract

No abstract