Search

Despite the remarkable success of end-to-end intelligent diagnosis methods, the shortage of available training data remains one of the most challenging issues in real industrial scenarios. In light of this, a wide variety of deep generative models are developed for data volume expansion. Notably, the denoising diffusion probabilistic model (DDPM) has recently shown impressive sample quality and diversity in various tasks. However, DDPM typically operates in the original pixel space, resulting in an expensive computational cost and restricting its applicability in industrial applications. In tackling the above issues, we develop an interpretable vector quantization-guided latent denoising diffusion probability model (IVQ-LDM) in this work. In IVQ-LDM, the vector quantized-variational autoencoder is introduced to compress the data to a lower dimensional space, where the kernels with physical meaning are then designed in the first layer to enhance the density of latent information and improve model interpretability. After that, a conditional DDPM is built in this latent space to learn the low-dimensional representation for data augmentation. Compared with existing methods, the IVQ-LDM achieves enhancements in sample quality, computational efficiency, and interpretability. Extensive experiments on three mechanical systems corroborate the effectiveness and superiority of the proposed method.

To cater to fault diagnosis of rotating machinery under complex working conditions, unsupervised domain adaptation technology has been widely explored and applied. Existing methods mainly reduce domain bias in two ways, including metric learning and discriminator-based adversarial learning. Different from these technologies, in this work, we only resort to entropy optimization strategies and develop a novel entropy-oriented domain adaptation (EODA) model for intelligent diagnosis of rotating machinery. Specifically, a convolutional network with a cosine-distance classifier is introduced to construct the model framework, which can reduce intraclass variation and make the output more confident. In addition, negentropy-guided prediction diversity optimization and minimax entropy game-guided prototype-feature alignment are co-designed to realize domain adaptation. Extensive experiments based on two different mechanical systems are used to validate our method. Comprehensive results and discussions demonstrate that our EODA can achieve compelling performance.

To alleviate the predicament of data annotating and the need for collecting data from identical distribution, unsupervised domain adaptation technologies have been widely deployed in the field of machine fault diagnosis. Nevertheless, most of them focus only on domain alignment and fail to make full use of the unlabeled target data. Given this, a novel self-training reinforced adversarial adaptation (SRAA) diagnosis method is developed in this article. In SRAA, an adversarial adaptation mechanism based on a bi-classifier disparity measure is introduced to implicitly align two domains. Meanwhile, a bi-classifier-oriented self-training algorithm is further proposed to fully mine the connotation information of unlabeled target data and reinforce model performance, in which an adaptive sample selection strategy and soft cross-entropy loss are included to guide high-confidence self-training. Empirical evidence from extensive experiments demonstrates the efficacy of SRAA, and comprehensive comparisons against the existing approaches show the superiority of our method.

Domain adaptation technology has been intensively studied in machine fault diagnosis for more reliable diagnosis performance. Nonetheless, most approaches rely on the availability of source data, which is always unattainable in many practical industrial scenarios due to the costs of expensive data storage and transmission as well as privacy protection. As a consequence, there is an urgent need to design an adaptation method that is independent of source data. This technology is also more in line with the requirements for lightweight and timely diagnosis. Given this, in this article, we develop a novel source-free adaptation diagnosis (SFAD) method. In SFAD, a robust self-training mechanism and a target prediction matrix constraint are presented, achieving model adaption with only unlabeled target data. Extensive experiments on our own and public datasets demonstrate the effectiveness and superiority of the proposed method.