| 引用本文: | 商柔,董宏丽,王闯,周国强,管闯,闫天红.基于多模态时序对比生成网络的数据增强算法[J].控制理论与应用,2025,42(4):805~815.[点击复制] |
| SHANG Rou,DONG Hong-li,WANG Chuang,ZHOU Guo-qiang,GUAN Chuang,YAN Tian-hong.Multimodal time-series contrastive generative network-based data augmentation algorithm[J].Control Theory & Applications,2025,42(4):805~815.[点击复制] |
|
| 基于多模态时序对比生成网络的数据增强算法 |
| Multimodal time-series contrastive generative network-based data augmentation algorithm |
| 摘要点击 0 全文点击 0 投稿时间：2023-02-15 修订日期：2025-03-05 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 10.7641/CTA.2023.30066 |
| 2025,42(4):805-815 |
| 中文关键词 管道故障诊断 类别不平衡 时间序列 数据增强 马尔可夫链 多任务学习 |
| 英文关键词 pipeline fault diagnosis class imbalance time series data augmentation Markov chain multi-task learning |
| 基金项目 国家自然科学基金项目(U21A2019,61873058,61933007), 海南省科技专项项目(ZDYF2022SHFZ105)资助. |
|
| 中文摘要 |
| 针对工业故障诊断中的小样本和类不平衡问题,本文提出一种基于马尔可夫链的多模态时序对比生成模
型(TCGN). 首先,为了提升合成数据时间结构的真实性,设计了一种时序趋势一致化损失(TTC),以提升真实数据与
合成数据之间时间演化规律的相似度.随后,为了在增强数据集中形成有效且正确的决策边界,提出了一种类意识
对比损失(CAC),以对齐真实数据与合成数据的类条件分布.此外,为了更好地维持不同学习任务之间的动态平衡,
引入了一种基于马尔可夫链的多模态切换策略,以实现TCGN算法在生成、刻画、探索、收敛4个模态之间的自适应
切换优化.最后,将所提出的TCGN算法应用于管道故障诊断.实验结果表明TCGN算法在视觉评估和量化指标方
面均优于一些先进的生成算法,显著提高了故障诊断准确率. |
| 英文摘要 |
| In this paper, a Markov chain-based multimodal time-series contrastive generative network (TCGN) is pro
posed to tackle the issues of small sample and class imbalance for industrial fault diagnosis. Firstly, a time-series trend
consistency loss (TTC) is designed to enhance the similarity of the time-evolving properties between the real and synthetic
data, which helps to improve the reality of the synthetic temporal structure. Subsequently, a class-aware contrastive loss
(CAC) is proposed to align the class-conditional distributions between the real and synthetic datasets, which facilitates the
formation of effective and proper decision boundaries. Furthermore, a Markov chain-based multimodal switching strategy
is introduced in this paper, which enables the TCGN algorithm to perform adaptive switching optimization between the
four modes of generation, depiction, exploration, and convergence, thus better maintaining the dynamic balance of differ
ent tasks. Finally, the proposed TCGN algorithm is applied to pipeline fault diagnosis. Experimental results show that
the TCGNalgorithm outperforms some state-of-the-art generation algorithms in terms of visual evaluation and quantitative
metrics, and significantly improves fault diagnosis accuracy. |
|
|
|
|
|