Journal of Information Processing Systems

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

An Anomaly Detection Algorithm for Cathode Voltage of Aluminum Electrolytic Cell

  • Cao, Danyang (School of Information Science and Technology, North China University of Technology) ;
  • Ma, Yanhong (School of Information Science and Technology, North China University of Technology) ;
  • Duan, Lina (School of Information Science and Technology, North China University of Technology)
  • Received : 2018.06.08
  • Accepted : 2019.02.20
  • Published : 2019.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

The cathode voltage of aluminum electrolytic cell is relatively stable under normal conditions and fluctuates greatly when it has an anomaly. In order to detect the abnormal range of cathode voltage, an anomaly detection algorithm based on sliding window was proposed. The algorithm combines the time series segmentation linear representation method and the k-nearest neighbor local anomaly detection algorithm, which is more efficient than the direct detection of the original sequence. The algorithm first segments the cathode voltage time series, then calculates the length, the slope, and the mean of each line segment pattern, and maps them into a set of spatial objects. And then the local anomaly detection algorithm is used to detect abnormal patterns according to the local anomaly factor and the pattern length. The experimental results showed that the algorithm can effectively detect the abnormal range of cathode voltage.

Keywords

Acknowledgement

This paper is supported by the National Natural Science Foundation of China (No. 41471303), Basic Scientific Research Plan Project of Beijing Municipal Commission of Education (2018), Special Research Foundation of North China University of Technology (No. PXM2017_014212_000014), Yuyou Talents Support Program of North China University of Technology (2019), and Beijing Natural Science Foundation (No. 4162022).

References

  1. J. Li, W. Liu, Y. Lai, Z. Wang, and Y. Liu, "Analysis of cathode voltage drop of aluminum electrolytic cell using electrical contact Model," Journal of Materials and Metallurgy, vol. 7, no. 2, pp. 99-102, 2008. https://doi.org/10.3969/j.issn.1671-6620.2008.02.005
  2. T. Kang and China Aluminum Qinghai Branch, "Methods research to lower the furnace bottom pressure-drop of pre-baked aluminum electrolytic cell," Non-ferrous Metallurgical Equipment, vol. 2014, no. 4, pp. 22-26, 2014.
  3. X. Guo, F. Li, and X. Song, "The outlier detection approach for multivariate time series based on PCA analysis," Journal of Jiangxi Normal University (Natural Sciences Edition), vol. 36, no. 3, pp. 280-283, 2012.
  4. D. Zhou, "Cluster of multivariable time series, similar query and anomaly detection," Tianjin University, Tianjin, China, 2009.
  5. E. M. Knorr and R. T. Ng, "A unified notion of outliers: properties and computation," in Proceedings of the 3rd International Conference on Knowledge Discovery and Data Mining (KDD), Newport Beach, CA, 1997, pp. 219-222.
  6. M. M. Breunig, H. P. Kriegel, R. T. Ng, and J. Sander, "LOF: identifying density-based local outliers," ACM Sigmod Record, vol. 29, no. 2, pp. 93-104, 2000. https://doi.org/10.1145/335191.335388
  7. L. Zhang, M. Yang, and D. Lei, "Outlier sub-sequences detection for importance points segmentation of time series," Computer Science, vol. 39, no. 5, pp. 183-186, 2012. https://doi.org/10.3969/j.issn.1002-137X.2012.05.043
  8. C. Bandt and B. Pompe, "Permutation entropy: a natural complexity measure for time series," Physical Review Letters, vol. 88, no. 17, article no. 174102, 2002.
  9. M. Zanin, L. Zunino, O. A. Rosso, and D. Papo, "Permutation entropy and its main biomedical and econophysics applications: a review," Entropy, vol. 14, no. 8, pp. 1553-1577, 2002.
  10. X. Zhao, "Time series of relevance and complexity of the study," Beijing Jiaotong University, Beijing, China, 2015.
  11. F. Feng, G. Rao, and A. Si, "Abnormality detection and diagnosis of rolling bearing based on permutation entropy and neural network," Noise and Vibration Control, vol. 33, no. 3, pp. 212-217, 2013.
  12. H. Xiao and F. Shang, "Representation of time series based on trend turning points," Science Technology and Engineering, vol. 10, no. 13, pp. 3254-3257, 2010.
  13. S. Chen, X. Lv, R. Qi, L. Wang, and L. Yu, "Linear representation method based on key points for time series, Computer Science, vol. 43, no. 5, pp. 234-237, 2016.
  14. X. Weng and J. Shen, "Outlier mining for multivariate time series based on sliding window," Computer Engineering, vol. 33, no. 12, pp. 102-104, 2007. https://doi.org/10.3969/j.issn.1000-3428.2007.12.036
  15. Y. Yu, Y. Zhu, D. Wan, and X. Guan, "Time series outlier detection based on sliding window prediction," Journal of Computer Applications, vol. 34, no. 8, pp. 2217-2220, 2014. https://doi.org/10.11772/j.issn.1001-9081.2014.08.2217
  16. H. Xiao, "Time series similarity query and anomaly detection," Fudan University, Shanghai, China, 2005.
  17. S. Li, W. Meng, and J. Qu, "GSWCLOF: density-based outlier detection algorithm on data stream," Computer Engineering and Applications, vol. 52, no. 19, pp. 7-11, 2016.
  18. Y. Chen, F. Wu, L. Wu, and B. Liu, "Research on time series based on anomaly detection," Computer Technology and Development, vol. 25, no. 4, pp. 166-170, 2015.
  19. X. Guo, F. Li, and H. Ye, "Outlier pattern research of multivariate time series," Journal of Xinyang Normal University (Natural Science Edition), vol. 25, no. 4, pp. 555-559, 2012. https://doi.org/10.3969/j.issn.1003-0972.2012.04.033
  20. X. Hui, "Time series anomaly detection based on user behavior pattern features," Ph.D. dissertation, Chongqing University, Chongqing, China, 2017.