A Novel Online Machine Learning Approach for Real-Time Condition Monitoring of Rotating Machines
Abstract
Nowadays, manufacturing companies are faced with many issues due to the growing demand for high-quality and reasonable price products. As maintenance expenses of industrial machines are around 60% to 70% of the production costs [1], an efficient and real-time method of fault detection is essential for reducing the cost of machine maintenance and prolonging the equipment's life, thereby decreasing the production expenses. In this article, a novel high-performance and precise anomaly detection framework based on edge computing technology is developed to enable real-time health monitoring of industrial assets. As such, hardware and firmware design is pursued to enable execution of all critical tasks such as data acquisition and preprocessing, feature extraction, and training the algorithm on the edge node, i-e. the microcontroller. This is a big challenge given the processing power and memory limitation of the microcontroller. The sensor used here is a 3-axis accelerometer for acquiring vibration signals. After storing enough training data in Flash memory of the MCU, an autoencoder with three hidden layers is trained on the edge to model the machine's healthy state. Finally, the reconstruction error of unseen data is used to detect anomalies. As far as we know, this is the first article that trains an artificial neural network (ANN) on an MCU and does the whole process of condition monitoring on edge. The design is validated by testing the framework on a centrifugal pump. The test result shows that the system can detect various pump faults with over 99.9% precision, recall, accuracy, and F1 Score.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Data-driven approaches using ML algorithms and deep learning are becoming more popular as a way to identify abnormal situations [133].
“Data-driven approach using ML algorithms and deep learning are becoming more and more popular as a way to identify abnormal situations [133].”
From A Comprehensive Survey on TinyML (2023) · cites this paper as [133]
Cites
Edge computing: Vision and challenges
Shi, W., Cao, J., Zhang, Q., Li, Y., & Xu, L. (2016) · IEEE Internet of Things Journal · doi:10.1109/jiot.2016.2579198 · Cited by 8,733 · see citing works
Tandon, N., & Choudhury, A. (1999) · Tribology International · doi:10.1016/s0301-679x(99)00077-8 · Cited by 1,358 · see citing works
A review on the application of deep learning in system health management
Khan, S., & Yairi, T. (2018) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2017.11.024 · Cited by 1,133 · see citing works
Novelty detection: a review—part 2:
Markou, M., & Singh, S. (2003) · Signal Processing · doi:10.1016/j.sigpro.2003.07.019 · Cited by 813 · see citing works
Model-Based Fault Diagnosis Techniques
Ding, S. X. (2012) · Advances in industrial control · doi:10.1007/978-1-4471-4799-2 · Cited by 664 · see citing works
A fog computing-based framework for process monitoring and prognosis in cyber-manufacturing
Wu, D., Liu, S., Zhang, L., Terpenny, J. P., Gao, R. X., Kurfess, T. R., & Guzzo, J. A. (2017) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2017.02.011 · Cited by 289 · see citing works
ROLLING ELEMENT BEARING DIAGNOSTICS IN RUN-TO-FAILURE LIFETIME TESTING
Williams, T. D., RIBADENEIRA, X., Billington, S. A., & Kurfess, T. R. (2001) · Mechanical Systems and Signal Processing · doi:10.1006/mssp.2001.1418 · Cited by 244 · see citing works
TinyOL: TinyML with Online-Learning on Microcontrollers
Ren, H., Anicic, D., & Runkler, T. A. (2021) · 2021 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9533927 · Cited by 185 · see citing works
Digital Twin-driven Online Anomaly Detection for an Automation System Based on Edge Intelligence
Huang, H., Yang, L., Wang, Y., Xu, X., & Lu, Y. (2021) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2021.02.010 · Cited by 183 · see citing works
Park, D., Kim, S., An, Y., & Jung, J. (2018) · Sensors · doi:10.3390/s18072110 · Cited by 174 · see citing works
A Cloud-based Approach for Maintenance of Machine Tools and Equipment Based on Shop-floor Monitoring
Mourtzis, D., Vlachou, E., Milas, N. T., & Xanthopoulos, N. (2016) · Procedia CIRP · doi:10.1016/j.procir.2015.12.069 · Cited by 142 · see citing works
Autoencoder-based Condition Monitoring and Anomaly Detection Method for Rotating Machines
Ahmad, S., Styp-Rekowski, K., Nedelkoski, S., & Kao, O. (2020) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata50022.2020.9378015 · Cited by 122 · see citing works
Goumas, S. K., Zervakis, M. E., & Stavrakakis, G. S. (2002) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2002.1017721 · Cited by 112 · see citing works
Qian, G., Lu, S., Pan, D., Tang, H., Liu, Y., & Wang, Q. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2899396 · Cited by 93 · see citing works
Spectral Regression Based Fault Feature Extraction for Bearing Accelerometer Sensor Signals
Xia, Z., Xia, S., Wan, L., et al. (2012) · Sensors · doi:10.3390/s121013694 · Cited by 84 · see citing works
Towards Distributed IoT/Cloud based Fault Detection and Maintenance in Industrial Automation
Xenakis, A., Karageorgos, A., Lallas, E., Chis, A. E., & González-Vélez, H. (2019) · Procedia Computer Science · doi:10.1016/j.procs.2019.04.091 · Cited by 43 · see citing works
Intelligent diagnosis of rotating machinery faults - A review
Yang, H., Mathew, J., & Ma, L. (2002) · QUT ePrints (Queensland University of Technology) · Cited by 33 · see citing works
Maasoum, S. M. H., Mostafavi, A., & Sadighi, A. (2020) · Iranian Conference on Signal Processing and Intelligent Systems (ICSPIS) · doi:10.1109/icspis51611.2020.9349574 · Cited by 8 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
A Comprehensive Survey on TinyML
Abadade, Y., Temouden, A., Bamoumen, H., Benamar, N., Chtouki, Y., & Hafid, A. S. (2023) · IEEE Access · doi:10.1109/access.2023.3294111 · Cited by 366 · see citing works
- Authors
- Mostafavi, A., & Sadighi, A.
- Affiliations
- University of Tehran (IR)
- Venue
- 2021 9th RSI International Conference on Robotics and Mechatronics (ICRoM)
- Publisher
- IEEE
- Published
- 2021-11-17
- Pages
- 267-273
- OpenAlex
- W4206187458
- Cited by
- 20
- References
- 18
- Citations by year
- 2026: 4 · 2025: 2 · 2024: 8 · 2023: 3 · 2022: 3
- FWCI
- 5.22
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- RSI International Conference on Robotics and Mechatronics (ICRoM) (publishedVersion)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Machine Fault Diagnosis Techniques
- Physical Sciences › Engineering › Control and Systems Engineering › Fault Detection and Control Systems
- Physical Sciences › Engineering › Safety, Risk, Reliability and Quality › Reliability and Maintenance Optimization
- Keywords
- online machine learning, real-time condition monitoring, rotating machinery, fault detection, edge computing, microcontroller, autoencoder, anomaly detection, reconstruction error, vibration signals, accelerometer, centrifugal pump, predictive maintenance
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
