Search

The increasing complexity and varying operational conditions of today’s rotating machinery present significant challenges for automated fault diagnosis. While data-driven fault diagnosis methods have grown in popularity, they often rely heavily on full-cycle data, making them resource-intensive and less adaptive to diverse working conditions. Addressing this gap, our proposed system avoids the dependence on full-cycle data, employing an efficient two-stage methodology. In the initial stage, an isolation forest (iForest) module operates in an unsupervised mode, isolating operational anomalies indicative of potential faults. These identified anomalies are then channeled into the second stage, where a adversarial discriminant domain adaptation (ADDA) module performs an in-depth fault diagnosis. By streamlining the diagnostic process, our approach not only accelerates fault identification but also reduces the reliance on extensive datasets that are often a staple in conventional diagnostics. Performance evaluations with the XJTU-SY and CWRU bearing datasets show that our system reaches an accuracy of 95.67%, affirming its superiority as a cost-efficient, data-lean solution in machinery fault diagnostics.

Deep image hiding is a challenging image processing task that aims to hide a secret image into a cover image of equal size perfectly. How to improve the imperceptibility of deep image hiding while ensuring high computational efficiency is a primary challenge. Where imperceptibility means not being visually perceived while not being perceived by the steganalysis model. In this paper, we propose a novel deep image hiding framework called DIH-OAIN (Deep Image Hiding based on One-way Adversarial Invertible Networks) to address it. Firstly, an image cascade framework is introduced to extract image semantics and details with dual-resolution branches, and reduces computation complexity by balancing image resolution and model complexity. Secondly, a hidden probability guided module is designed to constrain the secret image to be hidden in the texture region, utilizing the image texture complexity as prior knowledge. The above two points can effectively improve visual imperceptibility. Finally, a one-way adversarial training strategy is proposed to enhance the model imperceptibility. A series of experimental results show that the proposed method is significantly improved in imperceptibility comparing to state-of-the-art deep image hiding algorithms, while maintaining a low computation complexity.