Aug 2026· Big Data and Cognitive Computing· 0 citations· 53 references
TL;DR
The TGME-GAN is a fault diagnosis approach that integrates a multi-expert gated conditional generative adversarial network with a clustering structure-aware feature enhancement, and substantially outperforms current mainstream models.
Abstract
In the domain of rotating machinery fault diagnosis, challenges such as multi-operating condition distribution heterogeneity and the difficulty of distinguishing fault features within multi-scale temporal signals persist. To address these issues, this paper introduces the Time-Gated Multi-Expert Generative Adversarial Network (TGME-GAN), a fault diagnosis approach that integrates a multi-expert gated conditional generative adversarial network with a clustering structure-aware feature enhancement. This method combines unsupervised K-means clustering with supervised discriminative learning. The optimal number of clusters is selected adaptively using the silhouette coefficient, and the distance vector from each sample to the cluster centers serves as a topological prior feature. A spatial–temporal joint representation matrix is then formed by concatenating PCA principal components, differential features, cumulative statistical features, and standardized change rates, which together capture both abrupt mutations and progressive degradation in fault signals. In the model, the discriminator incorporates a multi-expert gated network. Each expert learns a feature subspace corresponding to a distinct operating condition, and the gated network dynamically assigns fusion weights, allowing the discriminator to capture heterogeneous distributions across industrial conditions. The generator extracts multi-scale local patterns with a three-layer one-dimensional convolutional network and models sequential dependencies with a two-layer LSTM, producing high-quality fault samples that preserve intrinsic consistency. At the engineering level, TGME-GAN is deployed for gearbox fault diagnosis in uneven, small-sample industrial settings. In two gearbox fault experiments, this method substantially outperforms current mainstream models.
A dual-enhanced generative framework for zero-shot bearing compound fault diagnosis, which enhances the diagnosis from two aspects: semantic feature generation and global-local feature interaction.
Jie Liu, Kai Zhang, Ting Wang et al.· Proceedings of the Instituti...· 0 citations
Bearings are critical components in rotating machinery, and their condition recognition is essential to ensure operational safety and reliability. However, vibration signals collected under different operating scenarios often exhibit non-stationarity and distribution discrepancies, which limits the generalization abili...
Xiang-Xiang Chen, Yu-Bin Pan, Jie Chen et al.· Structural Health Monitoring· 0 citations
In complex industrial environments, single monitoring signals, limited labeled data, and varying operating conditions often lead to low accuracy and poor generalization in cross-domain fault diagnosis of rotating machinery. To address these issues, a multi-channel information fusion with adaptive weighting network (MIF...
Lu Qian, Jian-Xin Tang, Yi-Fan Li· Measurement science and tech...· 0 citations
Severe noise in industrial environments often leads to distribution shifts, posing a critical challenge for deep learning-based bearing fault diagnosis. Models trained on clean data typically degrade under such conditions due to their inability to effectively disentangle noise from fault-related features. To address th...
Jin-Ze Zhang, Lu Yang, Tian-Tian Xu et al.· IEEE Signal Processing Lette...· 0 citations
A fault diagnosis method based on a ConvNeXt-FECAM architecture, integrated within an enhanced conditional adversarial domain adaptation framework, which has potential for cross-condition fault diagnosis and condition monitoring of rotating machinery is proposed.
Shu-Hang Liu, Gui-Ji Tang, Long Zhang· Measurement science and tech...· 0 citations
An interpretable multi-sensor fault diagnosis framework, termed LCWC-DAMiT, is proposed that introduces a learnable continuous wavelet convolution (LCWC) module to incorporate time–frequency priors into patch embedding and focuses on physically meaningful fault characteristic frequencies and informative sensor location...