Evolved FCM framework for working condition classification in furnace system
- 221 Downloads
In this paper, an evolved FCM-based clustering method combined with entropy theory is proposed to develop a working condition classification model for the furnace system in coal-fired power plants. To overcome the disadvantage in beforehand determination of clustering number in basic FCM method, Silhouette index is selected as a parameter to evaluate clustering number adaptively in the process. Each time the FCM runs, the selected Silhouette index evaluates the clustering results considering both close and separation degree. Six datasets from UCI machine learning repository are used to certify the effectiveness of the evolved FCM method. Furthermore, pressure sequences from a 300-MW boiler are then discussed as the industrial case study. Three kinds of entropy values, featured from pressure sequence in time–frequency domain, are obtained for further clustering analysis. The clustering results show the strong relationship between boiler’s load and pressure sequences in furnace system. This method can be considered a reference method for data mining in other fluctuating and time-varying sequences.
KeywordsPressure sequence Entropy Silhouette index Evolved FCM
This work is granted by the National Natural Science Foundation of China (51176030) and Jiangsu Science and Technology Department (BY2015070-17).
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
- Calinski T (1968) A dendrite method for cluster analysis. Biometrics 24:207Google Scholar
- Caniego FJ, Martin MA, San Jose F (2001) Singularity features of pore-size soil distribution: singularity strength analysis and entropy spectrum. Fract Complex Geom Patterns Scaling Nat Soc 9:305–316Google Scholar
- Guevel TL, Thomas P (2003) Fuel flexibility and petroleum coke combustion at provence 250 MW CFB. In: Proceedings of 17th international conference on fluidized bed combustion, Florida, USA, pp 643–649Google Scholar
- Jia X, Lu Y (1996) Fuzzy information processing. National University of Defence Technology Press, ChangshaGoogle Scholar
- Krzanowski WJ, Lai YT (1988) A criterion for determining the number of groups in a data set using sum-of-squares clustering. Biometrics 44:23–34Google Scholar
- Pimentel BA, de Souza RMCR, IEEE (2012) Possibilistic approach to clustering of interval data. In: Proceedings 2012 IEEE international conference on systems, man, and cybernetics, pp 190–195Google Scholar
- Shaohua MA, Ying HUA, Xiaobai LI (2007) An analysis of flame signals in a boiler furnace based on a phase space reconstruction. J Eng Therm Energy Power 22(440–442):456Google Scholar
- Wang K-M, Zhong N, Zhou H-Y (2014) Activity analysis of depression electroencephalogram based on modified power spectral entropy. Acta Phys Sin 63:533–538Google Scholar
- Weira N (2009) Large scale pulverized coal boiler furnace pressure nonlinear characteristics research based on Fractal and chaos theory. Shandong University, ShandongGoogle Scholar