SSA-CAE-Based Abnormal Data Classification Method in Edge Intelligence Device of CNC Machine
Source abstract
Abstract
Smart factories and big data are important factors in the Fourth Industrial Revolution. Smart factories aim for automation and integration; however, the most important part is the application of data. Despite extensive research on the maintenance and quality management of big data-based production equipment, industrial data gathered for analysis contain more normal data than abnormal data. In addition, a significant amount of energy is expended in the data pre-processing process to analyze the acquired data. Therefore, to maintain production equipment and quality management, data classification technology that allows easy data analysis by classifying abnormal data into normal data is required. In this paper, we propose an abnormal data classification architecture for cycle data sets gathered from production facilities through SSA-CAE along with data storage methods for each product unit. SSA-CAE is a hybrid technique that combines singular spectrum analysis (SSA) techniques that are effective in reducing noise in time series data with convolutional auto encoder (CAE) that have performed well in time series.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Statistical and numerical algorithms · Currency Recognition and Detection · Fault Detection and Control Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Smart Factory Convergence, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon 16419, Korea
CyberTechFriend, 150 Jojeong-daero, Hanam-si 12930, Korea
Funding
National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) · the MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program
References (33)
Show source-provided references
1. An iterative learning control method with application for CNC machine tools10.1109/28.485814 ↗
2. Principal component analysis10.1002/wics.101 ↗
3. Hassoun, M.H. (1995). Fundamentals of Artificial Neural Networks, MIT Press.10.1109/JPROC.1996.503146 ↗
4. Michie, D., Spiegelhalter, D.J., and Taylor, C.C. (2022, January 05). Machine Learning, Neural and Statistical Classification. Available online: http://www1.maths.leeds.ac.uk/~charles/statlog/whole.pdf.
5. Machine learning: Trends, perspectives, and prospects10.1126/science.aaa8415 ↗
6. Murphy, K.P. (2012). Machine Learning: A Probabilistic Perspective, MIT Press.
7. Deep learning10.1038/nature14539 ↗
8. Canziani, A., Paszke, A., and Culurciello, E. (2016). An analysis of deep neural network models for practical applications. arXiv.
9. Evaluating the visualization of what a deep neural network has learned10.1109/TNNLS.2016.2599820 ↗
10. Anomaly detection based on convolutional recurrent autoencoder for IoT time series10.1109/TSMC.2020.2968516 ↗
11. Data driven fault diagnosis and fault tolerant control: Some advances and possible new directions10.3724/SP.J.1004.2009.00739 ↗
12. Ding, S.X. (2008). Model-Based Fault Diagnosis Techniques: Design Schemes, Algorithms, and Tools, Springer Science & Business Media.
13. Model-based fault-detection and diagnosis–status and applications10.1016/j.arcontrol.2004.12.002 ↗
14. Model-based fault diagnosis in technical processes10.1177/014233120002200104 ↗
15. Lu, H., Cheng, Q., Zhang, X., Liu, Q., Qiao, Y., and Zhang, Y. (2020). A novel geometric error compensation method for gantry-moving CNC machine regarding dominant errors. Processes, 8.10.3390/pr8080906 ↗
16. Kappaganthu, K., Nataraj, C., and Samanta, B. (October, January 27). Model Based Bearing Fault Detection Using Support Vector Machines. Proceedings of the Annual Conference of the PHM Society, San Diego, CA, USA.
17. Kim, J., Lee, H., Jeon, J.W., Kim, J.M., Lee, H.U., and Kim, S. (2020). Stacked auto-encoder based CNC tool diagnosis using discrete wavelet transform feature extraction. Processes, 8.10.3390/pr8040456 ↗
18. A GAN-based anomaly detection approach for imbalanced industrial time series10.1109/ACCESS.2019.2944689 ↗
19. Hassani, H. (2010). A brief introduction to singular spectrum analysis. Optimal Decisions in Statistics and Data Analysis, Cardiff School of Mathematics, Cardiff University.
20. CNN features with bi-directional LSTM for real-time anomaly detection in surveillance networks10.1007/s11042-020-09406-3 ↗
21. Big data analytics
22. Smart factory reference model for training on Industry 4.010.24191/jmeche.v16i2.15331 ↗
23. Metal cutting mechanics, machine tool vibrations, and CNC design
24. Edge intelligence: Paving the last mile of artificial intelligence with edge computing10.1109/JPROC.2019.2918951 ↗
25. Li, E., Zhou, Z., and Chen, X. (2018, January 20). Edge intelligence: On-demand deep learning model co-inference with device-edge synergy. Proceedings of the 2018 Workshop on Mobile Edge Communications, Budapest, Hungary.10.1145/3229556.3229562 ↗
26. Design and Performance Analysis for Edge Intelligence-Based F-PMIPv6 Mobility Support for Smart Manufacturing10.1155/2021/9970942 ↗
27. Elsner, J.B., and Tsonis, A.A. (1996). Singular Spectrum Analysis: A New Tool in Time Series Analysis, Springer Science & Business Media.10.1007/978-1-4757-2514-8 ↗
28. Singular spectrum analysis for time series: Introduction to this special issue10.4310/SII.2010.v3.n3.a1 ↗
29. Circulant Singular Spectrum Analysis: A new automated procedure for signal extraction10.1016/j.sigpro.2020.107824 ↗
30. Singular-spectrum analysis: A toolkit for short, noisy chaotic signals10.1016/0167-2789(92)90103-T ↗
31. Kieu, T., Yang, B., Guo, C., and Jensen, C.S. (2019, January 10–16). Outlier Detection for Time Series with Recurrent Autoencoder Ensembles. Proceedings of the International Joint Conference on Artificial Intelligence, Macao, China.10.24963/ijcai.2019/378 ↗
32. Novel deep learning-enabled lstm autoencoder architecture for discovering anomalous events from intelligent transportation systems10.1109/TITS.2020.3017882 ↗
33. Unsupervised anomaly detection with LSTM autoencoders using statistical data-filtering10.1016/j.asoc.2021.107443 ↗