Anomaly Detection in Yarn Tension Signal Using Independent Component Analysis

Abstract

Finding patterns in data that defy expected behavior is what anomaly detection entails. In many application fields, these incorrect patterns are referred to as contaminants, abnormalities, exceptions, or outliers. The significance of anomaly detection is that it helps to identify irregularities in data across a range of application domains and turns them into valuable information. When the yarn tension signals are inspected, anomaly states in the signals are seen in situations where it defect for whatever reason. This distinction makes it possible to predict whether the twister is malfunctioning. So, a bigger issue is avoided. The employment of Cluster-Based Algorithms, Statistical Method Algorithms, and other techniques to identify anomalies is common in the literature. The yarn tension signals in the twisting machines have been analyzed in this work using independent component analysis, and the problematic signal locations have been identified. The proposed method has been contrasted with other ways, and it has produced the highest success rate.

Keywords

• Anomaly detection
• defect diagnosis
• ICA
• twister
• yarn tension signal

References

1. Shih-Hsuan C and Lu C. Noise separation of the yarn tension signal on twister using FastICA. Mechanical systems and signal processing 2005; 19(6): 1326-1336.
2. Hwa Y. QAI–Yarn Quality Control System. User Guide 2003; 25-45.
3. Recep E, Mutlu H N and Celik O. Design and Realisation of A Yarn Tension Sensor Using Strain Gauge Type Load Cells. Uludag University Journal of The Faculty of Engineering 2019; 24(2): 751-768.
4. Two for One Yarn Twisting Machine, http://www.yarn-winding.com/twisting-machine/yarn-twisting-machine/two-for-one-yarn-twisting-machine.html, last accessed 2020/04/05.
5. Das R, Golatkar A and Awate S. Sparse Kernel PCA for Outlier Detection. In: 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), 2018; Florida, USA: IEEE. pp. 152-157.
6. Yanfeng G, Liu Y and Zhang Y. A selective kernel PCA algorithm for anomaly detection in hyperspectral imagery. In: 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings, 2006; France: IEEE.
7. Mei F, Zhao C, Wang L and Huo H. Anomaly detection in hyperspectral imagery based on kernel ICA feature extraction. In: 2008 Second International Symposium on Intelligent Information Technology Application, 2008; IEEE. pp. 869-873.
8. Katsumata S and Kanemoto D. Applying Outlier Detection and Independent Component Analysis for Compressed Sensing EEG Measurement Framework. In: 2019 IEEE Biomedical Circuits and Systems Conference (BioCAS): 2019; IEEE. pp. 1-4.

9. Zonglin L, Guangmin H and Xingmiao Y. Multi-dimensional traffic anomaly detection based on ICA. In: 2009 IEEE Symposium on Computers and Communications, 2009; IEEE. pp. 333-336.
10. Žunić E, Delalić S, Hodžić K, and Tucaković Z. Innovative GPS Data Anomaly Detection Algorithm inspired by QRS Complex Detection Algorithms in ECG Signals. In: IEEE EUROCON 2019-18th International Conference on Smart Technologies,2019; IEEE. pp. 1-6.
11. Zhang Y, Xu M, Fan Y, Zhang Y, and Dong Y. A Kernel Background Purification Based Anomaly Target Detection Algorithm for Hyperspectral Imagery. In: IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium, 2019; IEEE. pp. 441-444.
12. Johnson R J, Williams J P and Bauer K W. AutoGAD: An improved ICA-based hyperspectral anomaly detection algorithm. IEEE Transactions on Geoscience and Remote Sensing 2012; 51(6): 3492-3503.
13. A’dan Z’ye Anomaly Detection, Medium, https://medium.com/@oguzkircicek/adan-z-ye-anomaly-detection-62b54f6bdd63, last accessed 2020/04/05.
14. Chandola V, Banerjee A and Kumar V. Anomaly detection: A survey. ACM computing surveys (CSUR) 2009; 41(3): 1-58.
15. Jutten C and Herault J. Independent components analysis (INCA) versus principal components analysis. In: Fourth European Signal Processing Conference, 1988; Grenoble, France. pp. 643– 646.
16. Zhao C, Wang Y and Mei F. Kernel ICA feature extraction for anomaly detection in hyperspectral imagery. Chin J Electron 2012; 21(2): 265-269.
17. Xu L and Li H Z. An anomaly detection method for spacecraft using ICA technology. In: 2013 International Conference on Advanced Computer Science and Electronics Information (ICACSEI 2013), 2013.
18. Vecchio E, Lazzerini B, Boley S. Spacecraft Fault Analysis Using Data Mining Techniques. In: Proc of ISAIRAS Conference, 2005; pp. 5-8.
19. Agarwal L and Rajan K S. Integrating Mser into a Fast ICA Approach for Improving Building Detection Accuracy. In: IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium, 2018; IEEE. pp. 4831-4834.
20. Abidi A, Nouira I and Bedoui M H. Parallel Implementation on GPU for EEG Artifact Rejection by Combining FastICA and TQWT. In; 2018 IEEE/ACS 15th International Conference on Computer Systems and Applications (AICCSA), 2018; IEEE. pp. 1-8.