Recently, cross-domain fault diagnosis based on transfer learning methods has been extensively explored and well-addressed when class-balance data with supervision information are available. However, data under machine faulty states are mostly difficult to collect; there is a huge divide between current transfer learning methods based on implicit class-balance data and real industrial applications. In this article, we propose a class-imbalance adversarial transfer learning (CIATL) network with input being imbalanced data to learn domain-invariant and knowledge. Within this framework, class-imbalance learning is embedded into the adversarial training process to learn class-separate diagnostic knowledge with imbalanced data, double-level adversarial transfer learning including marginal and conditional distribution adaptations is conducted to learn domain-invariant knowledge. Extensive experiments on a planetary gearbox rig with imbalanced data verify the effectiveness and generalization of the proposed method and show its superior performance over contrastive transfer learning methods. Moreover, the proposed method relaxes the underlying assumption that the success of current transfer learning regimes is rooted in class-balance data and extends the application of the transfer learning method for real-industrial cross-domain diagnosis tasks.

Most previous studies on nonlinear Lamb waves are conducted using mode pairs that satisfying strict phase velocity matching and non-zero power flux criteria. However, there are some limitations in existence. First, strict phase velocity matching is not existed in the whole frequency bandwidth; Second, excited center frequency is not always exactly equal to the true phase-velocity-matching frequency; Third, mode pairs are isolated and quite limited in number; Fourth, exciting a single desired primary mode is extremely difficult in practice and the received signal is quite difficult to process and interpret. And few attention has been paid to solving these shortcomings. In this paper, nonlinear S0 mode Lamb waves at low-frequency range satisfying approximate phase velocity matching is proposed for the purpose of overcoming these limitations. In analytical studies, the secondary amplitudes with the propagation distance considering the fundamental frequency, the maximum cumulative propagation distance (MCPD) with the fundamental frequency and the maximum linear cumulative propagation distance (MLCPD) using linear regression analysis are investigated. Based on analytical results, approximate phase velocity matching is quantitatively characterized as the relative phase velocity deviation less than a threshold value of 1%. Numerical studies are also conducted using tone burst as the excitation signal. The influences of center frequency and frequency bandwidth on the secondary amplitudes and MCPD are investigated. S1–S2 mode with the fundamental frequency at 1.8 MHz, the primary S0 mode at the center frequencies of 100 and 200 kHz are used respectively to calculate the ratios of nonlinear parameter of Al 6061-T6 to Al 7075-T651. The close agreement of the computed ratios to the actual value verifies the effectiveness of nonlinear S0 mode Lamb waves satisfying approximate phase velocity matching for characterizing the material nonlinearity. Moreover, the ratios derived from the primary and secondary horizontal displacements generated from nonlinear S0 mode Lamb waves are closest to the real value, which indicates that using horizontal displacements is more suitable for detecting evenly distributed microstructural changes in large thin plate-like structure. Successful application to evaluating material at different levels of evenly distributed fatigue damage is also numerically conducted.

The Deaf are a large social group in society. Their unique way of communicating through sign language is often confined within their community due to limited understanding by individuals outside of this demographic. This is where sign language recognition (SLR) comes in to help people without hearing impairments understand the meaning of sign language. In recent years, new methods of sign language recognition have been developed and achieved good results, so it is necessary to make a summary. This review mainly focuses on the introduction of sign language recognition techniques based on algorithms especially in recent years, including the recognition models based on traditional methods and deep learning approaches, sign language datasets, challenges and future directions in SLR. To make the method structure clearer, this article explains and compares the basic principles of different methods from the perspectives of feature extraction and temporal modelling. We hope that this review will provide some reference and help for future research in sign language recognition.

In recent years, unsupervised domain adaptation-based methods have been widely developed for intelligent bearing fault diagnosis across various working conditions. However, a considerably more challenging and practical fault diagnosis scenario in which the source and target domains are respectively collected from bearings across different positions and machines is urgent to be addressed. To solve this issue, an innovative end-to-end domain conditioned joint adaptation network (DCJAN), which is composed of a domain conditioned feature extractor, two classifiers, and a domain discriminator is presented. On the one hand, the domain conditioned feature extraction structure is designed to relax totally-shared network assumptions in feature extraction and learn more domain-specialized features for cross-domain fault diagnosis of bearings. On the other hand, a joint adaptation strategy is implemented for diagnostic knowledge transfer across domains, in which domain-level and class-level adaptations are respectively achieved by domain-adversarial training and bi-classifier adversarial training. Extensive experiments including cross-position fault diagnosis and cross-machine fault diagnosis of bearings indicate the validity and superiority of the proposed method.

Domain adaptation (DA)-based methods have been broadly developed for cross-domain fault diagnosis of machinery, in which the target and source label spaces are identical. However, a more challenging and practical diagnostic scenario in which the source label space subsumes target one is remaining to be solved. To address this issue, an innovative two-stage dual-weight consistency-induced partial DA (DCPDA) network, consisting of two feature extractors, a classifier, a domain discriminator, a dual-weight consistency-induced reweighting (DCR) module, and a Wasserstein distance-based-DA (WDA) module, is proposed. In the pretrained stage, a well-trained model on the source domain is acquired. In the fine-tuned stage, the DCR, which conducts a dual-weight consistency-induced weighting strategy, obtains a bi-level compound weight from both class- and sample-level weights. Embedded with the bi-level weight, the WDA is encouraged to transfer the source knowledge with mutual agreement from double-level weights across domains. Accordingly, the DCPDA is capable of alleviating negative transfer dramatically and mapping the source diagnostic knowledge into the target domain selectively. Extensive experiments indicate the validity and advantage of the proposed DCPDA.