Abstract
In intelligent manufacturing, detecting anomalous signals or time series subsequences and monitoring the process shift are two fundamental tasks to maintain manufacturing quality. Detecting the anomalous signals or process shifting as early as possible is a challenge. This chapter reviews the relevant research works in these two domains and presents the state-of-art methodologies that combine machine learning and data mining techniques to resolve the practical problem in production, named local recurrence rate with robust k-means (LRR-RKMeans) and long short-term memory real-time contrasts control chart (LSTM-RTC). The real-world data in manufacturing were used to evaluate the methods. The methods for anomalous subsequence detection on process monitoring and real-time contrasts control chart for quality control were applied to real-world semiconductor wafer and white wine production cases. The experimental results show that LRR-RKMeans can detect the defective wafer accurately, and LSTM-RTC has a low response delay in noticing process shift in white wine production. The possibility of combining the proposed data analysis framework with an edge-cloud computing system to alleviate the performance boundary in the computational time was further discussed.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhong, R.Y., Xu, X.W., Klotz, E., Newman, S.T.: Intelligent manufacturing in the context of industry 4.0: a review. Engineering 3, 616–630 (2017)
Chen, K.-C., Lien, S.-Y.: Machine-to-machine communications: technologies and challenges. Ad Hoc Netw. 18, 3–23 (2014)
Nain, G., Pattanaik, K.K., Sharma, G.: Towards edge computing in intelligent manufacturing: past, present and future. J. Manufact. Syst. 62, 588–611 (2022)
Yang, C.L., Sutrisno, H., Lo, N.W., et al.: Streaming data analysis framework for cyberphysical system of metal machining processes. In: 2018 IEEE Industrial Cyber-Physical Systems (ICPS), pp. 546–551 (2018)
Wang, Y., Perry, M., Whitlock, D., Sutherland, J.W.: Detecting anomalies in time series data from a manufacturing system using recurrent neural networks. J. Manufactur. Syst. 62, 823–834 (2022)
Wan, J., Tang, S., Li, D., et al.: A manufacturing big data solution for active preventive maintenance. IEEE Trans. Ind. Inform. 13, 2039–2047 (2017)
Zhang, Y.X., Chen, Y., Wang, J., Pan, Z.: Unsupervised deep anomaly detection for multisensor time-series signals. ArXiv, vol. abs/2107.12626 (2021)
Sutrisno, H., Yang, C.L.: Discovering defective products based on multivariate sensors data using local recurrence rate and robust k-means clustering. In: The 26th International Conference on Production Research (ICPR-26) (2021)
Yeh, C.-C.M., Zhu, Y., Ulanova, L., et al.: Matrix profile I: all pairs similarity joins for time series: a unifying view that includes motifs, discords and shapelets. In: 2016 IEEE 16th International Conference on Data Mining (ICDM), pp. 1317–1322 (2016)
Keogh, E.J., Lin, J., Fu, A.W.C.: Hot sax: efficiently finding the most unusual time series subsequence. In: Fifth IEEE International Conference on Data Mining (ICDM’05), vol. 8 (2005)
Wang, Z., Pi, D., Gao, Y.: A novel unsupervised time series discord detection algorithm in aircraft engine gearbox. In: ADMA (2018)
He, Q.P., Wang, J.: Statistical process monitoring as a big data analytics tool for smart manufacturing. J. Process Control 67, 35–43 (2018)
Cortez, P., Cerdeira, A.L., Almeida, F., Matos, T., Reis, J.: Modeling wine preferences by data mining from physicochemical properties. Decis. Support Syst. 47, 547–553 (2009)
Qu, Y.J., Ming, X.G., Liu, Z., Zhang, X., Hou, Z.: Smart manufacturing systems: state of the art and future trends. Int. J. Adv. Manufact. Technol. 1–18 (2019)
Khodabakhsh, A., Ari, I., Bakir, M., Ercan, A.O.: Multivariate sensor data analysis for oil refineries and multi-mode identification of system behavior in real-time. IEEE Access 6(64), 389–364 405 (2018)
El-Midany, T.T., El-baz, M.A., Abd-Elwahed, M.S.: A proposed framework for control chart pattern recognition in multivariate process using artificial neural networks. Expert Syst. Appl. 37, 1035–1042 (2010)
Sentürk, S., Erginel, N., Kaya, I., Kahraman, C.: Fuzzy exponentially weighted moving average control chart for univariate data with a real case application. Appl. Soft Comput. 22, 1–10 (2014)
Yang, C.L., Sutrisno, H.: Reducing response delay in multivariate process monitoring by a stacked long-short term memory network and real-time contrasts. Comput. Ind. Eng. 153, 107052 (2021)
Silva, A.F., Vercruysse, J., Vervaet, C., et al.: Process monitoring and evaluation of a continuous pharmaceutical twin-screw granulation and drying process using multivariate data analysis. Europ. J. Pharm. Biopharm. 128, 36–47 (2018)
Deng, H., Runger, G.C., Tuv, E.: System monitoring with real-time contrasts. J. Qual. Technol. 44, 27–29 (2012)
Wei, Q., Huang, W., Jiang, W., Zhao, W.: Real-time process monitoring using kernel distances. Int. J. Product. Res. 54, 6563–6578 (2016)
Jang, S., Park, S.H., Baek, J.-G.: Real-time contrasts control chart using random forests with weighted voting. Expert Syst. Appl. 71, 358–369 (2017)
He, S., Jiang, W., Deng, H.: A distance-based control chart for monitoring multivariate processes using support vector machines. Ann. Oper. Res. 263, 191–207 (2018)
Wang, F.-K., Bizuneh, B., Cheng, X.-B.: One-sided control chart based on support vector machines with differential evolution algorithm. Qual. Reliab. Eng. Int. 35, 1634–1645 (2019)
Hashemian, H.M., Bean, W.C.: State-of-the-art predictive maintenance techniques*. IEEE Trans. Instrum. Meas. 60, 3480–3492 (2011)
Shoeb, A.H., Guttag, J.V.: Application of machine learning to epileptic seizure detection. In: ICML, pp. 975–982 (2010)
Li, G., Bräysy, O., Jiang, L., Wu, Z., Wang, Y.: Finding time series discord based on bit representation clustering. Knowl. Based Syst. 54, 243–254 (2013)
Febrero, M., Galeano, P., Gonzalez Manteiga, W.: Outlier detection in functional data by depth measures, with application to identify abnormal NOx levels. Environmetrics 9(4), 331–345 (2008)
Rahmani, A., Afra, S., Zarour, O., et al.: Graph-based approach for outlier detection in sequential data and its application on stock market and weather data. Knowl. Based Syst. 61, 89–97 (2014)
Luo, W., Gallagher, M.R., Wiles, J.: Parameter-free search of time-series discord. J. Comput. Sci. Technol. 28, 300–310 (2013)
Wang, X., Lin, J., Patel, N., Braun, M.: Exact variable-length anomaly detection algorithm for univariate and multivariate time series. Data Mining Knowl. Discov. 32(6), 1806–1844 (2018). https://doi.org/10.1007/s10618-018-0569-7
Linardi, M., Zhu, Y., Palpanas, T., Keogh, E.J.: Matrix profile goes mad: variable-length motif and discord discovery in data series. Data Mining Knowledge Discov. 34, 1022–1071 (2020)
Luo, W., Gallagher, M.R.: Faster and parameter-free discord search in quasi-periodic time series. In: PAKDD (2011)
Hu, M., Feng, X., Ji, Z., Yan, K., Zhou, S.: A novel computational approach for discord search with local recurrence rates in multivariate time series. Inf. Sci. 477, 220–233 (2019)
Yang, C.-L., Darwin, F., Sutrisno, H.: Local recurrence rates with automatic time windows for discord search in multivariate time series. Procedia Manufact. 39, 1783–1792 (2019)
Lei, J., Jiang, T., Wu, K., Du, H., Zhu, G., Wang, Z.: Robust k-means algorithm with automatically splitting and merging clusters and its applications for surveillance data. Multimedia Tools Appl. 75, 12043–12059 (2016)
Yang, C.-L., Sutrisno, H.: A clustering-based symbiotic organisms search algorithm for high-dimensional optimization problems. Appl. Soft Comput. 97, 106722 (2020)
Choi, J.Y., Lee, B.: Combining LSTM network ensemble via adaptive weighting for improved time series forecasting. Math. Prob. Eng. (2018)
Ünlü, R.: Cost-oriented LSTM methods for possible expansion of control charting signals. Comput. Ind. Eng. 154, 107–163 (2021)
Olszewski, R.T.: Generalized feature extraction for structural pattern recognition in timeseries data, Report (2001)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sutrisno, H., Yang, CL. (2023). The Framework and Applications of Anomalous Subsequence Detection in Streaming Data Analysis and Process Monitoring in Intelligent Manufacturing. In: Huang, CY., Yoon, S.W. (eds) Systems Collaboration and Integration. ICPR1 2021. Automation, Collaboration, & E-Services, vol 14. Springer, Cham. https://doi.org/10.1007/978-3-031-44373-2_14
Download citation
DOI: https://doi.org/10.1007/978-3-031-44373-2_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44372-5
Online ISBN: 978-3-031-44373-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)