Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Mar 27;25(7):2098.
doi: 10.3390/s25072098.

Unsupervised Process Anomaly Detection and Identification Using the Leave-One-Variable-Out Approach

Jacob A Farber  1 , Ahmad Y Al Rashdan  1
Affiliations

Unsupervised Process Anomaly Detection and Identification Using the Leave-One-Variable-Out Approach

Jacob A Farber et al. Sensors (Basel). .

Abstract

Automated anomaly detection and identification can signal equipment issues and pinpoint causes in large-scale industrial systems. For systems with limited failure history, unsupervised machine learning methods can be utilized as they do not require past failures. This study introduces the leave-one-variable-out (LOVO) model, which masks one variable at a time to predict the others, learning underlying process correlations. Detection performance was assessed with synthetic and experimental data, while identification performance used only synthetic data due to its ability to generate labeled anomaly types. For detection using synthetic data, the LOVO model generally outperformed comparative models; while using experimental data, the comparative methods outperformed the LOVO model. However, the comparative methods required selecting a latent size, and these conclusions pertain to using the optimal size. In practice, it would not be feasible to always select the optimal value, and incorrect selections impacted performance. In contrast, the LOVO model does not require a latent space. For identification using synthetic data, the LOVO model was slightly outperformed in interpretability and repeatability but still demonstrated impressive results. These outcomes suggest that the LOVO model is an effective model and may be more easily implemented without the challenging tuning process of selecting a latent size.

Keywords: anomaly detection; anomaly identification; leave-one-variable-out model; online monitoring; root cause analysis.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest. The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript; or in the decision to publish the results.

Figures

Figure 1
Figure 1
Schematic of reconstruction-based contribution methods.
Figure 2
Figure 2
A sketch of the SMD system, with anomaly types highlighted in red.
Figure 3
Figure 3
Time-series data for the SMD position sensors and actuators.
Figure 4
Figure 4
Anomaly detection results for the SMD dataset showing the PR-AUC for the (a) PCA, (b) AE, and (c) iForest models, parameterized by both latent size and the level of data contamination.
Figure 5
Figure 5
Anomaly detection results for the SKAB dataset showing the PR-AUC for the (a) PCA, (b) AE, and (c) iForest models, parameterized by both latent size and the level of data contamination.
Figure 6
Figure 6
Anomaly identification results showing the average directions, parameterized by method and anomaly type.
See this image and copyright information in PMC

References

    1. Farber J.A., Al Rashdan A.Y., Reese R. Anomaly Detection and Identification Using a Leave-One-Variable-Out Method; Proceedings of the 13th Nuclear Plant Instrumentation, Control & Human-Machine Interface Technologies (NPIC&HMIT 2023), American Nuclear Society; Knoxville, TN, USA. 15–20 July 2023; pp. 441–446.
    1. Alcala C.F., Qin S.J. Reconstruction-based contribution for process monitoring. Automatica. 2009;45:1593–1600. doi: 10.1016/j.automatica.2009.02.027. - DOI
    1. Dunia R., Joe Qin S. Subspace approach to multidimensional fault identification and reconstruction. AIChE J. 1998;44:1813–1831. doi: 10.1002/aic.690440812. - DOI
    1. Yue H.H., Qin S.J. Reconstruction-Based Fault Identification Using a Combined Index. Ind. Eng. Chem. Res. 2001;40:4403–4414. doi: 10.1021/ie000141+. - DOI
    1. Li G., Qin S.J., Chai T. Multi-directional reconstruction based contributions for root-cause diagnosis of dynamic processes; Proceedings of the 2014 American Control Conference; Portland, OR, USA. 4–6 June 2014; pp. 3500–3505. - DOI

LinkOut - more resources