RESEARCH PAPER
An Explainable Adaptive Anomaly Detection Method for Multi-Condition Intelligent Equipment Monitoring
1
China University of Petroleum (Beijing), China
Submission date: 2025-07-25
Final revision date: 2025-09-25
Acceptance date: 2026-02-13
Online publication date: 2026-03-01
KEYWORDS
explainable adaptive anomaly detectionsensitivity and correlation analysesspatial memory matrixmultivariate state estimation techniquesequential probability ratio test
TOPICS
ABSTRACT
This paper addresses the challenges of weak parameter correlation, low detection accuracy, and poor interpretability in anomaly detection for rotating machinery under multi-condition operating scenarios. An explainable adaptive anomaly detection method is proposed. First, sensitivity and correlation analyses are employed to optimize the input parameters, and a spatial memory matrix is constructed by integrating an improved K-Nearest Neighbors algorithm with K-means clustering. Second, a multi-parameter anomaly detection model based on multivariate state estimation technique and sequential probability ratio test is developed to enable adaptive diagnosis of equipment operating conditions. Finally, error statistics are used to model the contribution trajectories of anomalous parameters, combined with a cumulative anomaly contribution rate metric to enhance the interpretability of anomaly localization. Experimental results show that the proposed method attains an average accuracy of 97.47% on multi-condition datasets, underscoring its wide applicability in industrial equipment monitoring
REFERENCES (31)
1.
An J, Liu J, Zhen H, Lu M. Camera-based PHM method in rotating machinery equipment micro-action scenarios. Eksploatacja i Niezawodność – Maintenance and Reliability 2023; 25(1): 10. https://doi.org/10.17531/ein.2....
2.
Zhang J, Kong X, Cheng L, Qi H, Yu M. Intelligent fault diagnosis of rolling bearings based on continuous wavelet transform-multiscale feature fusion and improved channel attention mechanism. Eksploatacja i Niezawodność – Maintenance and Reliability 2023; 25(1): 16. https://doi.org/10.17531/ein.2....
3.
Wei L, Peng X, Cao Y. Multi-scale graph transformer for rolling bearing fault diagnosis. Eksploatacja i Niezawodność – Maintenance and Reliability 2025; 27(2): 194779. https://doi.org/10.17531/ein/1....
4.
Lei C, Miao C, Yu Y, Wang L, Wang B. Rolling bearing fault diagnosis method based on multi-scale pooling residual convolutional neural network under noisy environment. Eksploatacja i Niezawodność – Maintenance and Reliability 2024; 27(1): 192167. https://doi.org/10.17531/ein/1....
5.
Wang J, Abdullah S, Arifin A, Karam Singh S S, Gao C. A semi-supervised fault diagnosis method for rolling bearing using time-frequency transform enhanced contrastive learning. Eksploatacja i Niezawodność – Maintenance and Reliability 2026; 28(1): 207015. https://doi.org/10.17531/ein/2....
6.
Bai R, Wang H, Sun W, Shi Y. Fault diagnosis method for rotating machinery based on SEDenseNet and gramian angular field. Eksploatacja i Niezawodność – Maintenance and Reliability 2024; 26(4): 1–17. https://doi.org/10.17531/ein/1....
7.
Wang X, Yao Y, Gao C. Wasserstein distance- EEMD enhanced multi-head graph attention network for rolling bearing fault diagnosis under different working conditions. Eksploatacja i Niezawodność – Maintenance and Reliability 2024; 26(2): 184037. https://doi.org/10.17531/ein/1....
8.
Zhang K, Yang G, Yang M, Ma C, Xu Y. LSESgram: a novel approach for optimal demodulation band selection in rolling bearing fault diagnosis. Eksploatacja i Niezawodność – Maintenance and Reliability 2026; 28(1): 208154. https://doi.org/10.17531/ein/2....
9.
Oshida T, Murakoshi T, Zhou L, Ojima H, Kaneko K, Onuki T, Shimizu J. Development and implementation of real-time anomaly detection on tool wear based on stacked LSTM encoder-decoder model. The International Journal of Advanced Manufacturing Technology 2023; 127(1-2): 263–278. https://doi.org/10.1007/s00170....
10.
Wang Y, Peng Y, Zi Y, Jin X, Tsui K-L. A two-stage data-driven-based prognostic approach for bearing degradation problem. IEEE Transactions on Industrial Informatics 2016; 12(3): 924–932. https://doi.org/10.1109/TII.20....
11.
Hardin J, Rocke D M. Outlier detection in the multiple cluster setting using the minimum covariance determinant estimator. Computational Statistics & Data Analysis 2004; 44(4): 625–638. https://doi.org/10.1016/S0167-....
12.
Wang Z, Jin X, Xu Z. An adaptive condition monitoring method of wind turbines based on multivariate state estimation technique and continual learning. IEEE Transactions on Instrumentation and Measurement 2023; 72: 1–9. https://doi.org/10.1109/TIM.20....
13.
Guo R, Zhang G, Zhang Q, Zhou L, Yu H, Lei M, Lv Y. An adaptive early fault detection model of induced draft fans based on multivariate state estimation technique. Energies 2021; 14(16): 4787. https://doi.org/10.3390/en1416....
14.
Caesarendra W, Tjahjowidodo T, Kosasih B, Tieu A K. Integrated condition monitoring and prognosis method for incipient defect detection and remaining life prediction of low speed slew bearings. Machines 2017; 5(2): 11–30. https://doi.org/10.3390/machin....
15.
Shan L, Liu Y, Ai X, Gao J. Research on fault sensor detection and localization method based on autoencoder. Annals of Nuclear Energy 2025; 220: 111546. https://doi.org/10.1016/j.anuc....
16.
Yang K, Hu B, Malekian R, Li Z. An improved control-limit-based principal component analysis method for condition monitoring of marine turbine generators. Journal of Marine Engineering & Technology 2020; 19(4): 249–256. https://doi.org/10.1080/204641....
17.
Saari J, Strömbergsson D, Lundberg J, Thomson A. Detection and identification of windmill bearing faults using a one-class support vector machine (SVM). Measurement 2019; 137: 287–301. https://doi.org/10.1016/j.meas....
18.
Wang J, Kou M, Li R, Qian Y, Li Z. Ultra-short-term wind power forecasting jointly driven by anomaly detection, clustering and graph convolutional recurrent neural networks. Advanced Engineering Informatics 2025; 65: 103137. https://doi.org/10.1016/j.aei.....
19.
Cui L, Zhang Q, Shi Y, Yang L, Wang Y, Wang J, Bai C. A method for satellite time series anomaly detection based on fast-DTW and improved-KNN. Chinese Journal of Aeronautics 2023; 36(2): 149–159. https://doi.org/10.1016/j.cja.....
20.
Wang H, Yang S, Liu Y, Li Q. A novel abnormal data detection method based on dynamic adaptive local outlier factor for the vibration signals of rotating parts. Measurement Science and Technology 2023; 34(8): 085118. https://doi.org/10.1088/1361-6....
21.
Shu X, Zhang S, Li Y, Chen M. An anomaly detection method based on random convolutional kernel andisolation forest for equipment state monitoring. Eksploatacja i Niezawodność – Maintenance and Reliability 2022; 24(4): 758–770. https://doi.org/10.17531/ein.2....
22.
Özüpak Y, Mansurov S. Optimizing electricity demand forecasting with a novel RNN-LSTM hybrid model. Energy Sources, Part B: Economics, Planning, and Policy 2025; 20(1): 2531448. https://doi.org/10.1080/155672....
23.
Li E, Li Y, Bedi S, Melek W, Gray P. Incremental learning of LSTM-autoencoder anomaly detection in three-axis CNC machines. The International Journal of Advanced Manufacturing Technology 2024; 130(3-4): 1265–1277. https://doi.org/10.1007/s00170....
24.
Li X, Huang T, Cheng K, Qiu Z, Sichao T. Research on anomaly detection method of nuclear power plant operation state based on unsupervised deep generative model. Annals of Nuclear Energy 2022; 167: 108785. https://doi.org/10.1016/j.anuc....
25.
He S, Xu X, Xie J, Wang F, Liu Z, Zhao F. Fault detection and fault-tolerant control of autonomous steering system for intelligent vehicles combining Bi-LSTM and SPRT. Measurement 2023; 212: 112708. https://doi.org/10.1016/j.meas....
26.
Wang B, Lei Y, Li N, Li N. A hybrid prognostics approach for estimating remaining useful life of rolling element bearings. IEEE Transactions on Reliability 2020; 69(1): 401–412. https://doi.org/10.1109/TR.201....
27.
Aslan E, Özüpak Y, Alpsalaz F, Elbarbary Z M S. A hybrid machine learning approach for predicting power transformer failures using internet of things-based monitoring and explainable artificial intelligence. IEEE Access 2025; 13: 113618–113633. https://doi.org/10.1109/ACCESS....
28.
Samee N A, Alhussan A A, Ghoneim V F, Atteia G, Alkanhel R, Al-antari M A, Kadah Y M. A hybrid deep transfer learning of CNN-based LR-PCA for breast lesion diagnosis via medical breast mammograms. Sensors 2022; 22(13): 4938. https://doi.org/10.3390/s22134....
29.
Nectoux P, Gouriveau R, Medjaher K, Ramasso E, Chebel-Morello B, Zerhouni N, Varnier C. PRONOSTIA: an experimental platform for bearings accelerated degradation tests. Conference on Prognostics and Health Management., Denver, Colorado, United States, IEEE Catalog Number : CPF12PHM-CDR: 2012;sur CD ROM:1–8.
30.
Alpsalaz F. Fault detection in power transmission lines: comparison of chirp-Z algorithm and machine learning based prediction models. Eksploatacja i Niezawodność – Maintenance and Reliability 2025; 27(4): 14. https://doi.org/10.17531/ein/2....
31.
Aslan E. Temperature prediction and performance comparison of permanent magnet synchronous motors using different machine learning techniques for early failure detection. Eksploatacja i Niezawodność – Maintenance and Reliability 2025; 27(1): 192164. https://doi.org/10.17531/ein/1....
| 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.
