Fucan Huang

Dr. Fucan Huang

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 April 2025 in Measurement Science and Technology
Verified
Journal Article
Closed access
BHBaokun Han
Baokun Han
FHFucan Huang
Fucan Huang
MQMin Qin
Min Qin
HQHaiqin QIN
Haiqin QIN
JWJinrui Wang
Jinrui Wang
YYYanwu Yu
Yanwu Yu
Signal instability, noise interference and the inability of individual signals to accurately represent the operational state of the equipment present substantial challenges for traditional fault diagnosis methods under fluctuating conditions. Furthermore, the over-globalization of the self-attention mechanism in deep networks undermines feature diversity, while conventional inter-domain distance metrics lack the robustness required to address complex scenarios. To tackle these issues, we propose an innovative adversarial training network model based on a dual-domain fused vision transformer, which processes time-domain and frequency-domain signals in parallel. The model enhances feature diversity through a residual attention mechanism and dynamically fuses signals via self-attention. By co-optimizing a dual-domain distance metric that incorporates maximum mean discrepancy and Wasserstein distance to reduce domain distance, the ability of the model to transfer across domains is strengthened. Experimental results from three sets of tests demonstrate that the proposed model significantly improves fault diagnosis accuracy under fluctuating conditions, effectively mitigates instability and noise interference, and exhibits enhanced stability and generalization capabilities.

4 December 2025 in Measurement Science and Technology
Verified
Journal Article
Closed access
FHFucan Huang
Fucan Huang
QZQingyao Zhang
Qingyao Zhang
BHBaokun Han
Baokun Han
JWJinrui Wang
Jinrui Wang
ZZZongzhen Zhang
Zongzhen Zhang
HGHuan Gong
Huan Gong
The acquisition of fault samples is often constrained by factors such as the low occurrence probability of faults and the high costs associated with data collection, leading to an imbalanced distribution of fault types and impairing the ability of the model to accurately recognize minority fault classes. In response to this challenge, this paper proposes an adaptive attenuation self-attention adversarial network. In the feature extraction phase, the model incorporates an attention mechanism utilizing a spatial attenuation matrix and bidirectional decomposition, which effectively mitigates the interference of irrelevant distant information while enhancing the ability of the model to capture local feature representations and reducing computational overhead. In the classification phase, an adaptive loss-weighting strategy is introduced, which dynamically adjusts loss weights based on both sample distribution and variations in inter-class accuracy, thereby improving the recognition performance of minority fault classes. For domain adaptation, the model combines conditional domain adversarial network, guided by an entropy filtering mechanism, with supervised contrastive learning to align features across domains and mitigate the adverse effects of class imbalance. Experimental results on two bearing datasets demonstrate that the proposed model significantly outperforms comparison methods across multiple evaluation metrics, validating its effectiveness and potential for real-world deployment in complex operating conditions.

27 November 2025 in Machines
Verified
Journal Article
Open access
PDF file
YAYuxi An
Yuxi An
DZDongyue Zhang
Dongyue Zhang
MZMing Zhang
Ming Zhang
MXMingbo Xin
Mingbo Xin
ZWZhesheng Wang
Zhesheng Wang
JWJinrui Wang
Jinrui Wang
Traditional fault diagnosis methods, which rely on single-vibration signals, are insufficient for capturing the complexity of mechanical systems. As neural networks evolve, attention mechanisms often fail to preserve local features, which can reduce diagnostic accuracy. Additionally, transfer learning using single-domain metrics struggles under fluctuating conditions. To address these challenges, this paper proposes an innovative adversarial training approach based on the Time–Frequency Fused Vision Transformer Network (TFFViTN). This method processes signals in both the time and frequency domains and incorporates a robust attention mechanism, along with a novel metric that combines Wasserstein distance and maximum mean discrepancy (MMD) to precisely align feature distributions. Adversarial training further strengthens domain-invariant feature extraction. Experiments on bearing and gear datasets demonstrate that our model significantly improves diagnostic performance, stability, and generalization.

14 November 2025 in Measurement Science and Technology
Verified
Journal Article
Closed access
PDF file
RGRongkang Ge
Rongkang Ge
ZZZongzhen Zhang
Zongzhen Zhang
JWJinrui Wang
Jinrui Wang
WWWenqi Wang
Wenqi Wang
ZFZhikang Fan
Zhikang Fan
FHFucan Huang
Fucan Huang
Multi-source domain transfer learning enhances the adaptability of the target domain by integrating multi-source knowledge. However, sample imbalance hinders the learning of minority-class features. Meanwhile, disparities in source-domain feature quality and the multi-classifier averaging method limit diagnostic performance. To address these issues, a multi-source domain bearing fault collaborative diagnosis method for unbalanced samples guided by multi-attention mechanism is proposed. Firstly, features are extracted by using multi-layer convolution, and the multi-source domain features are optimized through localized maximum mean difference (LMMD) to enhance consistency. A multi-head attention mechanism among samples enriches the representation of scarce classes. Further combine LMMD with the domain adversarial mechanism to enhance the migration capability. In the classification stage, a dynamic weighted loss function embedded with Sigmoid was designed to balance the learning weights of each category. Finally, based on indicators such as information entropy and adversarial loss, the outputs of multiple classifiers are fused to further reduce the risk of misclassification. Multiple sets of experiments conducted on the bearing dataset show that this method performs well in both diagnostic accuracy and generalization ability.