×
Home Current Archive Editorial board
Instructions for papers
For Authors Aim & Scope Contact
Original scientific article

INTERPRETABLE TRANSFORMER-BASED VIBRATION ANALYSIS FOR ANOMALY DETECTION IN INDUSTRIAL SYSTEMS

By
M. Mohamed Musthafa Orcid logo ,
M. Mohamed Musthafa

Al-Ameen Engineering College (Autonomous) , Erode , India

A. Aafiya Thahaseen Orcid logo ,
A. Aafiya Thahaseen

Al-Ameen Engineering College (Autonomous) , Erode , India

R. Arulmozhi Orcid logo ,
R. Arulmozhi

Al-Ameen Engineering College (Autonomous) , Erode , India

S. Mohammed Ibrahim Orcid logo ,
S. Mohammed Ibrahim

Al-Ameen Engineering College (Autonomous) , Erode , India

S. Sangeetha Orcid logo ,
S. Sangeetha

Al-Ameen Engineering College (Autonomous) , Erode , India

M. Rabiyathul Fathima Orcid logo ,
M. Rabiyathul Fathima

Al-Ameen Engineering College (Autonomous) , Erode , India

M. Gowthami Orcid logo ,
M. Gowthami

Al-Ameen Engineering College (Autonomous) , Erode , India

P. Esaiyazhini Orcid logo
P. Esaiyazhini

Al-Ameen Engineering College (Autonomous) , Erode , India

Abstract

The concept of monitoring conditions with the help of AI has become a significant aspect of Industry 4.0 that enhances machine reliability and provides predictive maintenance. However, the models of anomaly detection based on deep learning are not readily implemented because of their lack of interpretability. The article introduces a novel anomaly detection model of vibration signals using a Transformer and augmented with Shapley Additive exPlanations (SHAP) to provide the accountability of the model. To improve the power of the model in diverse circumstances, the hybrid approach of Wavelet Transform and Variational Mode Decomposition (WT-VMD) preprocessing technique is used to get meaningful time-frequency features. The proposed model was tested on an industrial vibration dataset, and the accuracy of anomaly detection is 99.2%, and the fidelity of SHAP elucidation is 88%. An experiment that used 50 industrial maintenance experts as the subjects showed that the level of trust grew by 45 % and the decision-making process became 30 times faster using explainable exploratory models than using non-explainable models. The results illustrate that the Transformer-based method is more effective in increasing the detection performance and interpretability, which is required in industrial predictive maintenance. This model allows implementing AI in industrial systems by defining fault detection in a clear way that facilitates the realization of the maintenance plans and makes it more reliable. The paper has demonstrated the potential of the application of deep learning, along with an interpretable model, in solving the issue of fault diagnosis and condition monitoring in the complicated industrial environment.

References

1.
Saeed A, Usman Akram M, Khattak M, Belal Khan M. An interpretable hybrid framework combining convolution latent vectors with transformer based attention mechanism for rolling element fault detection and classification. Heliyon. 2024;10(21):e38993.
2.
Wang X, Pi D, Zhang X, Liu H, Guo C. Variational transformer-based anomaly detection approach for multivariate time series. Measurement. 2022;191:110791.
3.
Kuculo T, Abdollahi S, Gottschalk S. Transformer-Based Architectures Versus Large Language Models in Semantic Event Extraction: Evaluating Strengths and Limitations. Semantic Web: – Interoperability, Usability, Applicability. 2025;16(5).
4.
Keshun Y, Zengwei L, Ronghua C, Yingkui G. A novel rolling bearing fault diagnosis method based on time-series fusion transformer with interpretability analysis. Nondestructive Testing and Evaluation. 2024;1–27.
5.
Liu J, Wang G, Zong X, Ning B, He K. EfficientTransformer: A Dynamic Anomaly Detection Model for Industrial Control Networks. IEEE Access. 2025;13:37931–45.
6.
Shi B, Jiang Y, Xiao W, Shang J, Li M, Li Z, et al. Power Transformer Vibration Analysis Model Based on Ensemble Learning Algorithm. IEEE Access. 2025;13:37812–27.
7.
Wang R, Dong E, Cheng Z, Liu Z, Jia X. Transformer-based intelligent fault diagnosis methods of mechanical equipment: A survey. Open Physics. 2024;22(1).
8.
Wang H, Yuan Y, Yang J, Peng Z, Huang K, Wang S, et al. Transformer vibration state anomaly detection based on Jensen-Shannon divergence and ensemble learning. IET Conference Proceedings. 2025;2024(6):260–6.
9.
Song Y, Li D. Application of a Novel Data-Driven Framework in Anomaly Detection of Industrial Data. IEEE Access. 2024;12:102798–812.
10.
Lee S, Jeong H, Kwon J. Transformer-Based GAN with Multi-STFT for Rotating Machinery Vibration Data Analysis. Electronics. 2024;13(21):4253.
11.
Muralidharan J. Machine learning techniques for anomaly detection in smart IoT sensor networks. Journal of Wireless Sensor Networks and IoT. 2024;(1):10–4.
12.
Sun S, Peng T, Huang H. Machinery Prognostics and High-Dimensional Data Feature Extraction Based on a Transformer Self-Attention Transfer Network. Sensors. 2023;23(22):9190.
13.
Borhan M. Exploring smart technologies towards applications across industries. Innovative Reviews in Engineering and Science. 2025;(2):9–16.
14.
Chen G, Yuan J, Zhang Y, Zhu H, Huang R, Wang F, et al. Enhancing Reliability Through Interpretability: A Comprehensive Survey of Interpretable Intelligent Fault Diagnosis in Rotating Machinery. IEEE Access. 2024;12:103348–79.
15.
Feng J, Shang R, Zhang M, Jiang G, Wang Q, Zhang G, et al. Transformer Abnormal State Identification Based on TCN-Transformer Model in Multiphysics. IEEE Access. 2025;13:44775–88.
16.
Sadulla S. Techniques and applications for adaptive resource management in reconfigurable computing. SCCTS Transactions on Reconfigurable Computing. 2024;(1):6–10.
17.
Dintén R, Zorrilla M. Design, Building and Deployment of Smart Applications for Anomaly Detection and Failure Prediction in Industrial Use Cases. Information. 2024;15(9):557.
18.
Liu R, Zhang Q, Han T, Yang B, Zhang W, Yin S, et al. Survey on Foundation Models for Prognostics and Health Management in Industrial Cyber-Physical Systems. IEEE Transactions on Industrial Cyber-Physical Systems. 2024;2:264–80.
19.
Antony ASM, Sundaram KM, Raman CJ, Murthy GR. Intelligent fault detection in battery systems: a machine learning approach with transformer-enhanced multi-modal Sensing. Electric Power Systems Research. 2026;251:112279.
20.
Chen F, Zhu Z, Qu F, Ni L, Jiang J, Chen Z. A Transformer-based fault detection method built on real-time data from microreactors. Chemical Engineering Science. 2025;312:121712.

Citation

This is an open access article distributed under the  Creative Commons Attribution Non-Commercial License (CC BY-NC) License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. 

Article metrics

Google scholar: See link

The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.