Difference mode decomposition for adaptive signal decomposition

TL;DR: This paper proposes a graph-guided collaborative convolutional neural network (GGCN) for fault diagnosis of electromechanical systems, leveraging graph reasoning fusion to explore correlations between multisource signals and outperforming seven state-of-the-art approaches under noisy conditions.

TL;DR: This paper proposes Dconformer, a novel CNN-Transformer network that extracts local and global features from noisy vibration signals for intelligent bearing fault diagnosis, outperforming five state-of-the-art approaches in strong noisy scenarios with a joint learning strategy.

TL;DR: This paper proposes VGNMD, a variational generalized nonlinear mode decomposition framework, to simultaneously separate chirp and dispersive components in noisy signals, improving noise robustness and resolution through adaptive time-frequency fusion and clustering.

TL;DR: A noise-robust adaptive feature mode decomposition method is proposed for accurate compound fault diagnosis in rotating machinery, addressing challenges in existing methods and effectively extracting individual fault components under strong periodic noise interference.

TL;DR: An introduction to a Transient World and an Approximation Tour of Wavelet Packet and Local Cosine Bases.

TL;DR: Chapter 11 includes more case studies in other areas, ranging from manufacturing to marketing research, and a detailed comparison with other diagnostic tools, such as logistic regression and tree-based methods.

TL;DR: The effect of the added white noise is to provide a uniform reference frame in the time–frequency space; therefore, the added noise collates the portion of the signal of comparable scale in one IMF.

TL;DR: This work proposes an entirely non-recursive variational mode decomposition model, where the modes are extracted concurrently and is a generalization of the classic Wiener filter into multiple, adaptive bands.