Visual Monitoring of Industrial Operation States Based on Kernel Fisher Vector and Self-organizing Map Networks
- 5 Downloads
As industrial process becomes increasingly complicated and the correlation between industrial process variables tends to exhibit strong nonlinear characteristics, how to effectively and visually monitor industrial operation states is challenging. Amethod based on kernel Fisher vector and self-organizing map networks (KFV-SOM) is proposed to improve the visualization of process monitoring. InKFV-SOM, kernel Fisher discriminant analysis is first employed to map data into high-dimensional space by using a nonlinear function, and the optimal Fisher feature vector, which can represent industrial operation states fittingly, is extracted. Thatis, the normal state and different kinds of faults can be distinguished well in the Fisher feature vector space. Thetopological structure of the Fisher feature vector space is then visualized intuitively on the two-dimensional output map of self-organizing map (SOM) with the Fisher feature vector as the input of the SOM network. Thus, the KFV-SOM caneffectively realize the visualization of monitoring. Continuousstirred tank reactor process is applied to illustrate the capability of KFV-SOM. Resultshows that KFV-SOM caneffectively visualize monitoring, and it is better in showing the operation states of normal state and different kinds of faults on the output map of the SOM networkthan SOM, SOM integratedwith principal component analysis, SOM integratedwith correlative component analysis, SOM integratedwith Fisher discriminant analysis, and SOM integratedwith canonical variable analysis.
KeywordsContinuous stirred tank reactor process industrial operation state monitoring kernel Fisher discriminant analysis self-organizing map
Unable to display preview. Download preview PDF.
- H. Ma, H. J. Liang, H. J. Ma, and Q. Zhou, “Nussbaum gain adaptive backstepping control of non-linear strict-feedback systems with unmodeled dynamics and unknown dead zone,” International Journal of Robust and Nonlinear Control, vol. 28, no. 17, pp. 5326–5343, September 2018.MathSciNetCrossRefzbMATHGoogle Scholar
- Y. H. Zhang, J. Sun, H. J. Liang, and H. Y. Li, “Event-triggered adaptive tracking control for multi-agent systems with unknown disturbances,” IEEE Transactionson Cybernetics, pp. 1–12, September 2018. DOI: 10.1109/TCYB.2018.2869084Google Scholar
- T. Chopraand J. Vajpai, “Classification of faults in damadics benchmark process control system using self-organizing maps,” International Journal of Soft Computing & Engineering, vol. 1, no. 3, pp. 22312307, March 2011.Google Scholar
- H. Ishibashiand T. Furukawa, “Hierarchical tensor SOM networkfor multilevel-multigroup analysis,” Neural Process Letter, no. 1, pp. 1–15, June 2017.Google Scholar
- N. D. Hoang and D. T. Bui, “Predicting earthquake-induced soil liquefaction based on a hybridization of kernel Fisher discriminant analysis and a least squares support vector machine: a multi-dataset study,” Bulletin of Engineering Geology & the Environment, vol. 77, no. 1, pp. 191–204, February 2018.CrossRefGoogle Scholar
- S. Mika, G. Ratsch, J. Weston, B. Scholkopf, and K. R. Mullers, “Fisher discriminant analysis with kernels,” Neural Networks for Signal Processing IX: Proceedings of the IEEE SignalProcessing Society Workshop, pp. 41–48, 1999.Google Scholar