DSTN: Dynamic Spatio-Temporal Network for Early Fault Warning in Chemical Processes
文献类型：期刊论文
| 作者 | Duan, Chenming1; Wu, Zhichao1; Zhu, Li2,3; Xu, Xirong1; Zhu, Jianmin4; Wei, Ziqi5; Yang, Xin1
|
| 刊名 | KNOWLEDGE-BASED SYSTEMS
 |
| 出版日期 | 2024-07-19 |
| 卷号 | 296页码:13 |
| 关键词 | Adaptive feature fusion Spatio-temporal network Early fault warning Dynamic graph K-order relations |
| ISSN号 | 0950-7051 |
| DOI | 10.1016/j.knosys.2024.111892 |
| 通讯作者 | Zhu, Li() ; Wei, Ziqi() ; Yang, Xin(xinyang@dlut.edu.cn) |
| 英文摘要 | Multivariate time series prediction, especially in early fault warning for chemical processes, poses significant challenges. The advent of graph neural network (GNN) method has made breakthroughs in this domain by enabling the processing of topological data. However, the traditional methods suffer from the issue of oversmoothing and inability to capture intricate multi-scale spatio-temporal dependencies. Additionally, the existing graph structures fall short in describing the complex spatial relationships among multi -stage sensors, impeding their adaptability to dynamically evolving chain reaction scenarios. To alleviate these limitations, a novel Dynamic spatio-Temporal Network for early fault warning in chemical processes, named DSTN for short, is proposed in this paper. We extract the spatial and temporal features of the time series by the designed dynamic GNN and the improved Transformer network. Then, we integrate the spatio-temporal features through the residual network. DSTN has the following advantages: (1) A one-dimensional convolutional neural network is seamlessly incorporated into the Transformer architecture for bolstering its capacity to discern both global and local features within time series. (2) The continuous sliding window and mutual information methods are employed to construct a dynamic topology graph, and a K -order adjacency matrix is designed to rectify the inefficiencies in learning weights associated with convolution kernel parameters. (3) Multiple spatio-temporal modules interconnected via residual connection to adaptively fuse multi-scale features. Experimental results demonstrate that our proposed DSTN method outperforms existing methods in terms of both performance and interpretability in early fault warning of chemical processes. |
| WOS关键词 | GRAPH NEURAL-NETWORKS ; PREDICTION ; DIAGNOSIS |
| 资助项目 | Natural Science Founda-tion of China[U21A20491] ; Liaoning Provincial Natural Science Foundation of China[2023-MSBA-001] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001240991900001 |
| 出版者 | ELSEVIER |
| 资助机构 | Natural Science Founda-tion of China ; Liaoning Provincial Natural Science Foundation of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/59115]  |
| 专题 | 自动化研究所_中国科学院分子影像重点实验室 |
| 通讯作者 | Zhu, Li; Wei, Ziqi; Yang, Xin |
| 作者单位 | 1.Dalian Univ Technol, Sch Comp Sci & Technol, Key Lab Social Comp & Cognit Intelligence, Minist Educ, Dalian 116024, Peoples R China 2.Dalian Univ Technol, Sch Control Sci & Engn, Dalian 116024, Peoples R China 3.Dalian Univ Technol, Key Lab Intelligent Control & Optimizat Ind Equipm, Minist Educ, Dalian 116024, Peoples R China 4.Liao Ning Oxiranchem Inc, Liaoyang 111003, Peoples R China 5.Chinese Acad Sci, Inst Automat, CAS Key Lab Mol Imaging, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Duan, Chenming,Wu, Zhichao,Zhu, Li,et al. DSTN: Dynamic Spatio-Temporal Network for Early Fault Warning in Chemical Processes[J]. KNOWLEDGE-BASED SYSTEMS,2024,296:13. |
| APA | Duan, Chenming.,Wu, Zhichao.,Zhu, Li.,Xu, Xirong.,Zhu, Jianmin.,...&Yang, Xin.(2024).DSTN: Dynamic Spatio-Temporal Network for Early Fault Warning in Chemical Processes.KNOWLEDGE-BASED SYSTEMS,296,13. |
| MLA | Duan, Chenming,et al."DSTN: Dynamic Spatio-Temporal Network for Early Fault Warning in Chemical Processes".KNOWLEDGE-BASED SYSTEMS 296(2024):13. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。