|
- Fault Diagnosis of Irregular Sequences by Adjoint Learning in . . .
Fault Diagnosis (FD) on sequential data suffers from irregular sampling (with missing values), limited training data, and varying underlying environments In response, this paper proposes FD by adjoint learning in continuous-time model space
- Fault Diagnosis of Irregular Sequences by Adjoint Learning in . . .
This study proposes FD of irregular sequences by learning in the continuous-time model space, introducing CT-Res for irregular-sequence fitting, along with an adjoint optimiza-tion strategy
- Huanhuan Chen - Publications by Year - 中国科学技术大学
"Efficient Anomaly Detection of Irregular Sequences in Ct-Echo Model Space" In Proceedings of the 39th AAAI Conference on Artificial Intelligence (AAAI'25), vol 39, no 15, pp
- Efficient anomaly detection of irregular sequences in Ct-Echo model space
Efficient anomaly detection of irregular sequences, especially those characterized by non-uniform sampling from discontinuous operations or unreliable sensors, presents challenges across various fields In response, this paper introduces irregular-sequence classification in "Ct-Echo Model Space"
- Continual learning fault diagnosis: A dual-branch adaptive aggregation . . .
A new Continual Learning Fault Diagnosis method (CLFD) is proposed in this paper to solve a series of fault diagnosis tasks with machine increments The stability–plasticity dilemma is an intrinsic issue in continual learning
- Intelligent fault diagnosis | 智能故障诊断 最新方向及成果追踪
亮点：提出了反向PINN，实现了 滚动轴承故障的 数字孪生，可解决不平衡故障诊断难题。 摘要：在现代工业系统中，组件之间有着复杂的相互作用，这使得识别工业系统的运行状况成为一项具有挑战性的任务。 考虑到一个工业系统，嵌入式组件和它们的相互作用可以分别表示为图中的节点和边。 因此，图表示算法是工业系统故障诊断的有力工具。 作为最常用的图表示算法之一， 图神经网络 （GNN）主要遵循 "学习参加 "的规律。 图神经网络提取训练数据的特征，学习特征和标签之间的统计相关性，从而使出席图偏向于访问非因果特征，作为预测的捷径。 这种捷径特征是不稳定的，取决于训练数据集中的数据分布特征，这降低了分类器的泛化能力。
- api. crossref. org
In response, this paper proposes FD by adjoint learning in continuous-time model space Model-Space Learning employs well-fitted models that capture data's dynamics (i e , changing information) as more stable and concise representations of the original data
- dblp: Ao Chen 0002
[i1] Ao Chen, Xiren Zhou, Yizhan Fan, Huanhuan Chen: Underground Diagnosis Based on GPR and Learning in the Model Space CoRR abs 2211 15480 (2022)
|
|
|