Fault Diagnosis Methods Based on Spatio-Temporal Feature Fusion

Yongxin Zhou; Yuan Xu; Yi Luo; Wei Ke; Qun Xiong Zhu; Yang Zhang; Ming Qing Zhang

doi:10.1007/978-981-95-6733-1_4

Fault Diagnosis Methods Based on Spatio-Temporal Feature Fusion

Yongxin Zhou
, Yuan Xu
, Yi Luo
, Wei Ke
, Qun Xiong Zhu
, Yang Zhang
, Ming Qing Zhang

Faculty of Applied Sciences

Beijing University of Chemical Technology
Ministry of Education of China
Chinese Institute of Coal Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Accurate fault diagnosis in industrial processes depends on the ability to model and integrate spatial dependencies among process variables and temporal dynamics of operational data. To address this challenge, this paper proposes a novel spatio-temporal fusion fault diagnosis method, SDGCN-LSTM, integrating Graph Convolutional Networks (GCN) and Long Short-Term Memory (LSTM) networks. The GCN module captures spatial relationships among process variables based on their structural connections, while the LSTM network learns temporal patterns from sequential data. After separately extracting spatial and temporal features, a two-dimensional attention mechanism is applied to adaptively enhance the most informative features. Finally, the ADaboost algorithm is employed as a classifier to perform final fault identification. Experimental results demonstrate that the proposed SDGCN-LSTM method achieves superior fault diagnosis accuracy across Three-Phase Flow Facility (TFF) and Tennessee Eastman (TE) datasets compared to baseline methods.

Original language	English
Title of host publication	Advanced Computational Intelligence and Intelligent Informatics - 9th International Workshop, IWACIII 2025, Proceedings
Editors	Hongbin Ma, Bin Xin, Qing Wang, Jinhua She
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	39-49
Number of pages	11
ISBN (Print)	9789819567324
DOIs	https://doi.org/10.1007/978-981-95-6733-1_4
Publication status	Published - 2026
Event	9th International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2025 - Zhuhai, China Duration: 31 Oct 2025 → 4 Nov 2025

Publication series

Name	Communications in Computer and Information Science
Volume	2781 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	9th International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2025
Country/Territory	China
City	Zhuhai
Period	31/10/25 → 4/11/25

Keywords

Fault diagnosis
Feature extraction
Feature fusion
Spatio-Temporal
Tennessee Eastman
Three-phase Flow Facility

Access to Document

10.1007/978-981-95-6733-1_4

Cite this

Zhou, Y., Xu, Y., Luo, Y., Ke, W., Zhu, Q. X., Zhang, Y., & Zhang, M. Q. (2026). Fault Diagnosis Methods Based on Spatio-Temporal Feature Fusion. In H. Ma, B. Xin, Q. Wang, & J. She (Eds.), Advanced Computational Intelligence and Intelligent Informatics - 9th International Workshop, IWACIII 2025, Proceedings (pp. 39-49). (Communications in Computer and Information Science; Vol. 2781 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-95-6733-1_4

Zhou, Yongxin ; Xu, Yuan ; Luo, Yi et al. / Fault Diagnosis Methods Based on Spatio-Temporal Feature Fusion. Advanced Computational Intelligence and Intelligent Informatics - 9th International Workshop, IWACIII 2025, Proceedings. editor / Hongbin Ma ; Bin Xin ; Qing Wang ; Jinhua She. Springer Science and Business Media Deutschland GmbH, 2026. pp. 39-49 (Communications in Computer and Information Science).

@inproceedings{7c9011312e9344c2991a887a510d5883,

title = "Fault Diagnosis Methods Based on Spatio-Temporal Feature Fusion",

abstract = "Accurate fault diagnosis in industrial processes depends on the ability to model and integrate spatial dependencies among process variables and temporal dynamics of operational data. To address this challenge, this paper proposes a novel spatio-temporal fusion fault diagnosis method, SDGCN-LSTM, integrating Graph Convolutional Networks (GCN) and Long Short-Term Memory (LSTM) networks. The GCN module captures spatial relationships among process variables based on their structural connections, while the LSTM network learns temporal patterns from sequential data. After separately extracting spatial and temporal features, a two-dimensional attention mechanism is applied to adaptively enhance the most informative features. Finally, the ADaboost algorithm is employed as a classifier to perform final fault identification. Experimental results demonstrate that the proposed SDGCN-LSTM method achieves superior fault diagnosis accuracy across Three-Phase Flow Facility (TFF) and Tennessee Eastman (TE) datasets compared to baseline methods.",

keywords = "Fault diagnosis, Feature extraction, Feature fusion, Spatio-Temporal, Tennessee Eastman, Three-phase Flow Facility",

author = "Yongxin Zhou and Yuan Xu and Yi Luo and Wei Ke and Zhu, \{Qun Xiong\} and Yang Zhang and Zhang, \{Ming Qing\}",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.; 9th International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2025 ; Conference date: 31-10-2025 Through 04-11-2025",

year = "2026",

doi = "10.1007/978-981-95-6733-1\_4",

language = "English",

isbn = "9789819567324",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "39--49",

editor = "Hongbin Ma and Bin Xin and Qing Wang and Jinhua She",

booktitle = "Advanced Computational Intelligence and Intelligent Informatics - 9th International Workshop, IWACIII 2025, Proceedings",

address = "Germany",

}

Zhou, Y, Xu, Y, Luo, Y, Ke, W, Zhu, QX, Zhang, Y & Zhang, MQ 2026, Fault Diagnosis Methods Based on Spatio-Temporal Feature Fusion. in H Ma, B Xin, Q Wang & J She (eds), Advanced Computational Intelligence and Intelligent Informatics - 9th International Workshop, IWACIII 2025, Proceedings. Communications in Computer and Information Science, vol. 2781 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 39-49, 9th International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2025, Zhuhai, China, 31/10/25. https://doi.org/10.1007/978-981-95-6733-1_4

Fault Diagnosis Methods Based on Spatio-Temporal Feature Fusion. / Zhou, Yongxin; Xu, Yuan; Luo, Yi et al.
Advanced Computational Intelligence and Intelligent Informatics - 9th International Workshop, IWACIII 2025, Proceedings. ed. / Hongbin Ma; Bin Xin; Qing Wang; Jinhua She. Springer Science and Business Media Deutschland GmbH, 2026. p. 39-49 (Communications in Computer and Information Science; Vol. 2781 CCIS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Fault Diagnosis Methods Based on Spatio-Temporal Feature Fusion

AU - Zhou, Yongxin

AU - Xu, Yuan

AU - Luo, Yi

AU - Ke, Wei

AU - Zhu, Qun Xiong

AU - Zhang, Yang

AU - Zhang, Ming Qing

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.

PY - 2026

Y1 - 2026

N2 - Accurate fault diagnosis in industrial processes depends on the ability to model and integrate spatial dependencies among process variables and temporal dynamics of operational data. To address this challenge, this paper proposes a novel spatio-temporal fusion fault diagnosis method, SDGCN-LSTM, integrating Graph Convolutional Networks (GCN) and Long Short-Term Memory (LSTM) networks. The GCN module captures spatial relationships among process variables based on their structural connections, while the LSTM network learns temporal patterns from sequential data. After separately extracting spatial and temporal features, a two-dimensional attention mechanism is applied to adaptively enhance the most informative features. Finally, the ADaboost algorithm is employed as a classifier to perform final fault identification. Experimental results demonstrate that the proposed SDGCN-LSTM method achieves superior fault diagnosis accuracy across Three-Phase Flow Facility (TFF) and Tennessee Eastman (TE) datasets compared to baseline methods.

AB - Accurate fault diagnosis in industrial processes depends on the ability to model and integrate spatial dependencies among process variables and temporal dynamics of operational data. To address this challenge, this paper proposes a novel spatio-temporal fusion fault diagnosis method, SDGCN-LSTM, integrating Graph Convolutional Networks (GCN) and Long Short-Term Memory (LSTM) networks. The GCN module captures spatial relationships among process variables based on their structural connections, while the LSTM network learns temporal patterns from sequential data. After separately extracting spatial and temporal features, a two-dimensional attention mechanism is applied to adaptively enhance the most informative features. Finally, the ADaboost algorithm is employed as a classifier to perform final fault identification. Experimental results demonstrate that the proposed SDGCN-LSTM method achieves superior fault diagnosis accuracy across Three-Phase Flow Facility (TFF) and Tennessee Eastman (TE) datasets compared to baseline methods.

KW - Fault diagnosis

KW - Feature extraction

KW - Feature fusion

KW - Spatio-Temporal

KW - Tennessee Eastman

KW - Three-phase Flow Facility

UR - https://www.scopus.com/pages/publications/105038475191

U2 - 10.1007/978-981-95-6733-1_4

DO - 10.1007/978-981-95-6733-1_4

M3 - Conference contribution

AN - SCOPUS:105038475191

SN - 9789819567324

T3 - Communications in Computer and Information Science

SP - 39

EP - 49

BT - Advanced Computational Intelligence and Intelligent Informatics - 9th International Workshop, IWACIII 2025, Proceedings

A2 - Ma, Hongbin

A2 - Xin, Bin

A2 - Wang, Qing

A2 - She, Jinhua

PB - Springer Science and Business Media Deutschland GmbH

T2 - 9th International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2025

Y2 - 31 October 2025 through 4 November 2025

ER -

Zhou Y, Xu Y, Luo Y, Ke W, Zhu QX, Zhang Y et al. Fault Diagnosis Methods Based on Spatio-Temporal Feature Fusion. In Ma H, Xin B, Wang Q, She J, editors, Advanced Computational Intelligence and Intelligent Informatics - 9th International Workshop, IWACIII 2025, Proceedings. Springer Science and Business Media Deutschland GmbH. 2026. p. 39-49. (Communications in Computer and Information Science). doi: 10.1007/978-981-95-6733-1_4

Fault Diagnosis Methods Based on Spatio-Temporal Feature Fusion

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this