Evaluating Machine Learning Algorithms for Anomaly Detection in Industrial Engines on Edge Devices
Resumo
Industrial automation and the Internet of Things (IoT) are rapidly evolving, highlighting the need for efficient anomaly detection systems to prevent failures and reduce maintenance and operational costs. This study evaluates the feasibility of running machine learning-based anomaly detection models on edge devices like the Raspberry Pi. Using real sensor data from industrial engines with induced faults, we tested three unsupervised algorithms: LOF, OCSVM, and IF. Metrics such as sensitivity, specificity, inference time, and resource usage were analyzed under different loads. The results show that accurate and low-latency detection is possible on resource-constrained devices, supporting the development of cost-effective and autonomous monitoring systems for industrial environments.Referências
Araújo-Filho, J. G. (2018). Comparação de desempenho de algoritmos de detecção de anomalias na rede can. Revista Brasileira de Engenharia Elétrica, 36(1):1–10.
Breunig, M. M., Kriegel, H.-P., Ng, R. T., and Sander, J. (2000). Lof: identifying density-based local outliers. ACM sigmod record, 29(2):93–104.
Chevtchenko, S. F., Rocha, E. D. S., Dos Santos, M. C. M., Mota, R. L., Vieira, D. M., De Andrade, E. C., and De Araújo, D. R. B. (2023a). Anomaly detection in industrial machinery using iot devices and machine learning: A systematic mapping. IEEE Access, 11:128288–128305.
Chevtchenko, S. F., Santos, M., Vieira, D. M., Mota, R. L., Rocha, E., Cruz, B. V., Araújo, D., Andrade, E., et al. (2023b). Predictive maintenance model based on anomaly detection in induction motors: A machine learning approach using real-time iot data. arXiv preprint arXiv:2310.14949.
Doe, J. and Smith, J. (2023). Performance evaluation of raspberry pi for mqtt under different request loads. Journal of IoT Applications, 12(3):45–58.
Dutta, D. and Mukhopadhyay, D. (2020). Edge AI: Machine Learning on Edge Devices. O’Reilly Media, Sebastopol, CA, 1 edition.
Foundation, R. P. (2019). Raspberry Pi 4 Model B: Technical Specifications. [link].
Garg, A., Zhang, W., Samaran, J., Savitha, R., and Foo, C.-S. (2022). An evaluation of anomaly detection and diagnosis in multivariate time series. IEEE Transactions on Neural Networks and Learning Systems, 33(6):2508–2517.
Ghazal, M., Basmaji, T., Yaghi, M., Alkhedher, M., Mahmoud, M., and El-Baz, A. S. (2020). Cloud-based monitoring of thermal anomalies in industrial environments using ai and the internet of robotic things. Sensors, 20(21):6348.
Hunter, J. D. (2007). Matplotlib: A 2D Graphics Environment, volume 9. IEEE.
Liu, F. T., Ting, K. M., and Zhou, Z.-H. (2008). Isolation forest. In 2008 Eighth IEEE International Conference on Data Mining, pages 413–422. IEEE.
McKinney, W. (2010). Data structures for statistical computing in python. [link].
Mian, T., Choudhary, A., Fatima, S., and Panigrahi, B. (2023). Artificial intelligence of things based approach for anomaly detection in rotating machines. Computers and Electrical Engineering, 109:108760.
Molina, A. L. B. (2022). Weapon: Uma arquitetura de aprendizado não supervisionado para detecção de anomalias de comportamento de usuários. Master’s thesis, Universidade de Brasília.
Mudaliar, M. D. and Sivakumar, N. (2020). Iot based real time energy monitoring system using raspberry pi. Internet of Things, 12:100292.
Mukherjee, I., Sahu, N. K., and Sahana, S. K. (2023). Simulation and modeling for anomaly detection in iot network using machine learning. International Journal of Wireless Information Networks, 30(2):173–189.
Powers, D. M. (2011). Evaluation: From precision, recall and f-measure to roc, informedness, markedness and correlation. Journal of Machine Learning Technologies, 2(1):37–63.
Schmidl, S., Wenig, P., and Papenbrock, T. (2022). Anomaly detection in time series: a comprehensive evaluation. Proceedings of the VLDB Endowment, 15(9):1779–1797.
Schölkopf, B., Platt, J. C., Shawe-Taylor, J., Smola, A. J., and Williamson, R. C. (2001). Estimating the support of a high-dimensional distribution. Neural computation, 13(7):1443–1471.
Waskom, M. L. (2021). Seaborn: statistical data visualization. Journal of Open Source Software, 6(60):3021.
Breunig, M. M., Kriegel, H.-P., Ng, R. T., and Sander, J. (2000). Lof: identifying density-based local outliers. ACM sigmod record, 29(2):93–104.
Chevtchenko, S. F., Rocha, E. D. S., Dos Santos, M. C. M., Mota, R. L., Vieira, D. M., De Andrade, E. C., and De Araújo, D. R. B. (2023a). Anomaly detection in industrial machinery using iot devices and machine learning: A systematic mapping. IEEE Access, 11:128288–128305.
Chevtchenko, S. F., Santos, M., Vieira, D. M., Mota, R. L., Rocha, E., Cruz, B. V., Araújo, D., Andrade, E., et al. (2023b). Predictive maintenance model based on anomaly detection in induction motors: A machine learning approach using real-time iot data. arXiv preprint arXiv:2310.14949.
Doe, J. and Smith, J. (2023). Performance evaluation of raspberry pi for mqtt under different request loads. Journal of IoT Applications, 12(3):45–58.
Dutta, D. and Mukhopadhyay, D. (2020). Edge AI: Machine Learning on Edge Devices. O’Reilly Media, Sebastopol, CA, 1 edition.
Foundation, R. P. (2019). Raspberry Pi 4 Model B: Technical Specifications. [link].
Garg, A., Zhang, W., Samaran, J., Savitha, R., and Foo, C.-S. (2022). An evaluation of anomaly detection and diagnosis in multivariate time series. IEEE Transactions on Neural Networks and Learning Systems, 33(6):2508–2517.
Ghazal, M., Basmaji, T., Yaghi, M., Alkhedher, M., Mahmoud, M., and El-Baz, A. S. (2020). Cloud-based monitoring of thermal anomalies in industrial environments using ai and the internet of robotic things. Sensors, 20(21):6348.
Hunter, J. D. (2007). Matplotlib: A 2D Graphics Environment, volume 9. IEEE.
Liu, F. T., Ting, K. M., and Zhou, Z.-H. (2008). Isolation forest. In 2008 Eighth IEEE International Conference on Data Mining, pages 413–422. IEEE.
McKinney, W. (2010). Data structures for statistical computing in python. [link].
Mian, T., Choudhary, A., Fatima, S., and Panigrahi, B. (2023). Artificial intelligence of things based approach for anomaly detection in rotating machines. Computers and Electrical Engineering, 109:108760.
Molina, A. L. B. (2022). Weapon: Uma arquitetura de aprendizado não supervisionado para detecção de anomalias de comportamento de usuários. Master’s thesis, Universidade de Brasília.
Mudaliar, M. D. and Sivakumar, N. (2020). Iot based real time energy monitoring system using raspberry pi. Internet of Things, 12:100292.
Mukherjee, I., Sahu, N. K., and Sahana, S. K. (2023). Simulation and modeling for anomaly detection in iot network using machine learning. International Journal of Wireless Information Networks, 30(2):173–189.
Powers, D. M. (2011). Evaluation: From precision, recall and f-measure to roc, informedness, markedness and correlation. Journal of Machine Learning Technologies, 2(1):37–63.
Schmidl, S., Wenig, P., and Papenbrock, T. (2022). Anomaly detection in time series: a comprehensive evaluation. Proceedings of the VLDB Endowment, 15(9):1779–1797.
Schölkopf, B., Platt, J. C., Shawe-Taylor, J., Smola, A. J., and Williamson, R. C. (2001). Estimating the support of a high-dimensional distribution. Neural computation, 13(7):1443–1471.
Waskom, M. L. (2021). Seaborn: statistical data visualization. Journal of Open Source Software, 6(60):3021.
Publicado
28/10/2025
Como Citar
ARAÚJO, Lucas; CHEVTCHENKO, Sérgio; ARAÚJO, Danilo; ANDRADE, Ermeson.
Evaluating Machine Learning Algorithms for Anomaly Detection in Industrial Engines on Edge Devices. In: SIMPÓSIO EM SISTEMAS COMPUTACIONAIS DE ALTO DESEMPENHO (SSCAD), 26. , 2025, Bonito/MS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 169-180.
DOI: https://doi.org/10.5753/sscad.2025.15872.
