A novel unsupervised method for anomaly detection in time series based on statistical features for industrial predictive maintenance
Tóm tắt
Industrial production processes are increasingly collecting data from machines in operation due to the cost reduction and popularization of sensor technologies. Valuable information is generated by using the right sensors and proper techniques on the machine’s current state in operation. This extraction allows detecting whether the machine is operating in a degraded state and then, if necessary, interrupts its operation before it goes into a broken state. The detection of the abnormal behavior of a machine is relevant since detection at the right time can reduce financial costs due to machine breakdown and production downtime. This work proposes a novel unsupervised method to detect anomalies in industrial machines and interrupt their operation before this machine goes into a state of breakdown. The proposed method receives as input a set of time series data from several sensors. Using a collection of statistical features, it calculates an indicator that characterizes the failure’s severity, issuing an alert to the machine operator if necessary. The method was evaluated in two benchmarks with known univariate data and two proprietary datasets with multivariate data. Conducted experiments revealed the low computational time spent on training and on evaluation. Overall results measured in Area Under the Receiver Operating Characteristic Curve (AUC) in Yahoo’s benchmark were 89.3%; in Numenta, it was 70.3%, and in the two multivariate datasets evaluated, it was 92.4% and 91.2%. These high AUC values reveal the potential of the proposed method applied in predictive maintenance in a large soybean oil production industry.
Tài liệu tham khảo
Ahmad, S., Lavin, A., Purdy, S., Agha, Z.: Unsupervised real-time anomaly detection for streaming data. Neurocomputing 262, 134–147 (2017)
Amarbayasgalan, T., Pham, V.H., Theera-Umpon, N., Ryu, K.H., et al.: Unsupervised anomaly detection approach for time-series in multi-domains using deep reconstruction error. Symmetry 12(8), 1251 (2020)
Anderson, M.J., Thompson, A.A.: Multivariate control charts for ecological and environmental monitoring. Ecol. Appl. 14(6), 1921–1935 (2004)
Attoui, I., Oudjani, B., Boutasseta, N., Fergani, N., Bouakkaz, M.S., Bouraiou, A.: Novel predictive features using a wrapper model for rolling bearing fault diagnosis based on vibration signal analysis. Int. J. Adv. Manuf. Technol. 106(7–8), 3409–3435 (2020)
Blanchard, B.S., Verma, D.C., Peterson, E.L.: Maintainability: A Key to Effective Serviceability and Maintenance Management, vol. 13. Wiley, Hoboken (1995)
Blázquez-García, A., Conde, A., Mori, U., Lozano, J.A.: A review on outlier/anomaly detection in time series data. arXiv preprint arXiv:2002.04236 (2020)
Carvalho, T.P., Soares, F.A., Vita, R., Francisco, Rd.P., Basto, J.P., Alcalá, S.G.: A systematic literature review of machine learning methods applied to predictive maintenance. Comput. Ind. Eng. 137, 106024 (2019)
Xy, Chen, Yy, Zhan: Multi-scale anomaly detection algorithm based on infrequent pattern of time series. J. Comput. Appl. Math. 214(1), 227–237 (2008)
Dias, C.G., da Silva, L.C., Chabu, I.E.: Fuzzy-based statistical feature extraction for detecting broken rotor bars in line-fed and inverter-fed induction motors. Energies 12(12), 2381 (2019)
Ding, N., Ma, H., Gao, H., Ma, Y., Tan, G.: Real-time anomaly detection based on long short-term memory and Gaussian mixture model. Comput. Electr. Eng. 79, 106458 (2019)
Fernandez-Temprano, M., Gardel-Sotomayor, P., Duque-Perez, O., Morinigo-Sotelo, D.: Broken bar condition monitoring of an induction motor under different supplies using a linear discriminant analysis. In: 9th IEEE International Symposium on Diagnostics for Electric Machines. Power Electronics and Drives (SDEMPED), pp. 162–168. IEEE (2013)
Hochenbaum, J., Vallis, O.S., Kejariwal, A.: Automatic anomaly detection in the cloud via statistical learning. arXiv preprint arXiv:1704.07706 (2017)
ISO: Condition monitoring and diagnostics of machines-general guidelines. Standard, International Organization for Standardization (2018)
Jimenez, J.J.M., Schwartz, S., Vingerhoeds, R., Grabot, B., Salaün, M.: Towards multi-model approaches to predictive maintenance: a systematic literature survey on diagnostics and prognostics. J. Manuf. Syst. 56, 539–557 (2020)
Kagermann, H., Wahlster, W., Helbig, J.: Recommendations for implementing the strategic initiative industrie 4.0. Report, ACATECH-National Academy of Science and Engineering. http://alvarestech.com/temp/tcn/CyberPhysicalSystems-Industrial4-0.pdf (2013)
Kim, T.H., White, H.: On more robust estimation of skewness and kurtosis. Financ. Res. Lett. 1(1), 56–73 (2004)
Laptev, N., Amizadeh, A., Billawala, Y.: Yahoo labs news: announcing a benchmark dataset for time series anomaly detection [online blog]. https://research.yahoo.com/news/announcing-benchmark-dataset-time-series-anomaly-detection (2015a)
Laptev, N., Amizadeh, S., Flint, I.: Generic and scalable framework for automated time-series anomaly detection. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1939–1947 (2015b)
Lavin, A., Ahmad, S.: Evaluating real-time anomaly detection algorithms–the numenta anomaly benchmark. In: IEEE 14th International Conference on Machine Learning and Applications (ICMLA), pp. 38–44. IEEE (2015)
Lee, J., Bagheri, B., Kao, H.: A cyber-physical systems architecture for industry 4.0-based manufacturing systems. Manuf. Lett. 3, 18–23 (2015)
Munir, M., Siddiqui, S.A., Dengel, A., Ahmed, S.: DeepAnT: a deep learning approach for unsupervised anomaly detection in time series. IEEE Access 7, 1991–2005 (2018)
Nemeth, T., Ansari, F., Sihn, W.: A maturity assessment procedure model for realizing knowledge-based maintenance strategies in smart manufacturing enterprises. Procedia Manuf. 39, 645–654 (2019)
Olive, D.J.: Applied robust statistics. Preprint M-02-006 (2008)
Shukla, S., Yadav, R., Sharma, J., Khare, S.: Analysis of statistical features for fault detection in ball bearing. In: IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), pp. 1–8. IEEE (2015)
Stern, S., Farioli, S., Eisenschmidt, E., Morachioli, S., Kienzler, C., Jeske, D., Schaal, N.: The future of maintenance for distributed fixed assets. Technical report, McKinsey Company In collaboration with Lumics (2020)
Sullivan, G. P, Pugh, R., Melendez, A. P.: Operations and maintenance best practices—a guide to achieving operational efficiency. Technical report, Pacific Northwest National Lab., Richland, WA (US) (2002)
Susto, G.A., Schirru, A., Pampuri, S., McLoone, S., Beghi, A.: Machine learning for predictive maintenance: a multiple classifier approach. IEEE Trans. Ind. Inf. 11(3), 812–820 (2014)
Wang, J., Zhao, R., Gao, R.X.: Probabilistic transfer factor analysis for machinery autonomous diagnosis cross various operating conditions. IEEE Trans. Instrum. Meas. 69, 5335–5344 (2020)
Wu, J., Zeng, W., Yan, F.: Hierarchical temporal memory method for time-series-based anomaly detection. Neurocomputing 273, 535–546 (2018)
Xia, Z., Xia, S., Wan, L., Cai, S.: Spectral regression based fault feature extraction for bearing accelerometer sensor signals. Sensors 12(10), 13694–13719 (2012)
Yaacob, A. H., Tan, I. K., Chien SF, Tan, H. K.: Arima based network anomaly detection. In: Second International Conference on Communication Software and Networks, pp. 205–209. IEEE (2010)
Zheng, D., Li, F., Zhao, T.: Self-adaptive statistical process control for anomaly detection in time series. Expert Syst. Appl. 57, 324–336 (2016)