RESEARCH PAPER
Real-Time Industrial Sensor Fault Diagnosis via Global Correlation Modeling and Feature Attention-Optimized Network
1
Shanghai Institute of Technology, China
Submission date: 2025-10-09
Final revision date: 2025-12-13
Acceptance date: 2026-02-19
Online publication date: 2026-02-23
KEYWORDS
Fault diagnosisAttention mechanismCorrelation compensationMaximal information coefficientReliability detection
TOPICS
ABSTRACT
To address diagnostic delays and high false-alarm rates in multi-sensor systems, this paper proposes MIC‑GAEAN, a lightweight network for anomaly detection. The framework constructs a global sensor correlation network using the Maximal Information Coefficient (MIC) to capture complex dependencies, which is dynamically refined via a lightweight attention mechanism. Notably, training excludes the target sensor’s own historical data to prevent information leakage and enhance generalization. An adaptive MLP then performs point‑level anomaly detection through single‑step prediction. A novel Correlation Compensation Mechanism further uses healthy sensor data to set theoretical norms, distinguishing faults from normal variations and reducing false alarms. Validated on industrial data, MIC‑GAEAN demonstrates high real‑time accuracy, efficiency, and suitability for data‑scarce, long‑interval monitoring, offering a reliable solution for industrial system reliability.
REFERENCES (30)
1.
Zhao Q, Liu X, Li H, Han Y. Multi-Connected Temporal Encoding Graph Neural Network for Complex Industrial Fault Diagnosis. Eksploatacja i Niezawodność – Maintenance and Reliability 2026; 28(1). https://doi.org/10.17531/ein/2....
2.
Chauhan S, Vashishtha G, Zimroz R. Analysing recent breakthroughs in fault diagnosis through sensor: A comprehensive overview. CMES-Computer Modeling in Engineering & Sciences 2024; 141(3). https://doi.org/10.32604/cmes.....
3.
Sharma AB, Golubchik L and Govindan R. Sensor faults: Detection methods and prevalence in real-world datasets. ACM Transactions on Sensor Networks (TOSN) 2010; 6(3): 1–39. https://doi.org/10.1145/175441....
4.
Xie X, Wang J, Han Y, Li W, Knowledge graph-based in-context learning for advanced fault diagnosis in sensor networks. Sensors 2024; 24(24): 8086. https://doi.org/10.3390/s24248....
5.
Verhelst J, Van Ham G, Saelens D, Helsen L, Economic impact of persistent sensor and actuator faults in concrete core activated office buildings. Energy and Buildings 2017; 142: 111–127, https://doi.org/10.1016/j.enbu....
6.
Mahapatro A, Khilar P M. Fault diagnosis in wireless sensor networks: A survey. IEEE Communications Surveys & Tutorials 2013; 15(4): 2000–2026. https://doi.org/10.1109/ICCS.2....
7.
Ni K, Ramanathan N, Chehade M N H, Balzano L, Nair S, Zahedi S, Kohler E, Pottie G, Hansen M, Srivastava M. Sensor network data fault types. ACM Transactions on Sensor Networks (TOSN) 2009; 5(3): 1–29. https://doi.org/10.1145/152585....
8.
Jombo G, Zhang E and Lu N. Sensor fault detection and diagnosis: Methods and challenges. In 12th IFAC Symposium on Fault Detection, Supervision and Safety for Technical Processes. IFAC Proceedings 2024.
9.
Lei X, Lu N, Jiang B, Wang C, Chen C. A Multi-scale Attention Mechanism Diagnosis Method with Adaptive Online Updating Based on Deep Learning under Variable Working Conditions. Maintenance Reliability-Eksploatacja i Niezawodność 2025; 27(1). https://doi.org/10.17531/ein/1....
10.
Greff K, Srivastava RK, Koutnuık J, Steunebrink B R, Schmidthuber J. Lstm: A search space odyssey. IEEE transactions on neural networks and learning systems 2016; 28(10): 2222–2232. https://doi.org/10.1109/TNNLS.....
11.
Ji Z, Ye S, Ma X. Sparse coding inspired lstm and self-attention integration for medical image segmentation. IEEE Transactions on Image Processing 2024; 33: 6098–6113. https://doi.org/10.1109/TIP.20....
12.
Fei H, Xiao F, Li G H, Sun L J, Wang R C. An anomaly detection method of wireless sensor network based on multi-modals data stream. Chinese Journal of Computers 2017; 40(8): 1829–1842. https://doi.org/10.11897/SP.J.....
13.
Zhang J, Luo W, Dai Y. Integrated diagnostic framework for process and sensor faults in chemical industry. Sensors 2021; 21(3): 822. https://doi.org/10.3390/s21030....
14.
He S, He W, Du M, Jiang X, Dong Y. GDCMAD: Graph-based dual-contrastive representation learning for multivariate time series anomaly detection. Information Sciences 2025; 122790. https://doi.org/10.1016/j.ins.....
15.
Huang Y, Jin Y, Tao K, Xia K, Gu J, Yu L, Li H, Du L, Chen C. MTS-Net: dual- enhanced positional multi-head self-attention for 3D CT diagnosis of May-Thurner syndrome. Biomedical Signal Processing and Control 2026; 112: 108618. https://doi.org/10.1016/j.bspc....
16.
Lai Q, Chen P. Unveiling node relationships for traffic forecasting: A self-supervised approach with MixGT. Information Fusion 2025; 120: 103070. https://doi.org/10.1016/j.inff....
17.
Xu W, Wang H, Xie Z. Explainable multivariate time series anomaly detection by feature graph structure learning. Information Sciences 2025; 122789. https://doi.org/10.1016/j.ins.....
18.
Francis D, Sun F. A comparative analysis of mutual information methods for pairwise relationship detection in metagenomic data. BMC bioinformatics 2024; 25(1): 266. https://doi.org/10.1186/s12859....
19.
Prosvirin A E, Piltan F, Kim J M. Blade rub-impact fault identification using autoencoder- based nonlinear function approximation and a deep neural network. Sensors 2020; 20(21): 6265. https://doi.org/10.3390/s20216....
20.
Kinney J B, Atwal G S. Equitability, mutual information, and the maximal information coefficient. Proceedings of the National Academy of Sciences 2014; 111(9): 3354–3359. https://doi.org/10.1073/pnas.1....
21.
Reshef D N, Reshef Y A, Finucane H K, Grossman S R, Mcvean G, Turnbaugh P J, Lander E S, Mitzenmacher M, Sabeti P C. Detecting novel associations in large data sets. Science 2011; 334(6062): 1518–1524. https://doi.org/10.1126/scienc....
22.
De Winter J C, Gosling S D, Potter J. Comparing the pearson and spearman correlation coefficients across distributions and sample sizes: A tutorial using simulations and empirical data. Psychological methods 2016; 21(3): 273. https://doi.org/10.48550/arXiv....
23.
Duncan T E. On the calculation of mutual information. SIAM Journal on Applied Mathematics 1970; 19(1): 215–220. https://doi.org/10.1137/011902....
24.
Nagel D, Diez G, Stock G. Accurate estimation of the normalized mutual information of multidimensional data. The Journal of Chemical Physics 2024; 161(5). https://doi.org/10.1063/5.0217....
25.
Donders A R T, Van Der Heijden G J, Stijnen T, Moons K G M. A gentle introduction to imputation of missing values. Journal of clinical epidemiology 2006; 59(10): 1087–1091. https://doi.org/10.1016/j.jcli....
26.
Hyndman R J. Moving averages. In International encyclopedia of statistical science. Springer, 2011. pp. 866–869. https://doi.org/10.1007/978-3-....
27.
Cai T T, Hall P. Prediction in functional linear regression. The Annals of Statistics 2006; 34(287): 2159–2179. https://doi.org/10.1214/009053....
28.
Huang J, Yan X. Related and independent variable fault detection based on kpca and svdd. Journal of Process Control 2016; 39: 88–99. https://doi.org/10.1016/j.jpro....
29.
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez A N, Kaiser L, Polosukhin I. Attention is all you need. Advances in neural information processing systems 2017; 30. https://doi.org/10.48550/arXiv....
30.
Qin X, Wang Z, Bai Y, Xie X, Jia H. FFA-Net: Feature fusion attention network for single image dehazing. In Proceedings of the AAAI Conference on Artificial Intelligence 2020; 34(7): 11908–11915. https://doi.org/10.48550/arXiv....
Share
RELATED ARTICLE
| eISSN: | 2956-3860 |
| ISSN: | 1507-2711 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
