Evolved clustering analysis of 300 MW boiler furnace pressure sequence based on entropy characterization
详细信息 查看全文
- 作者：Hui Gu ; ShaoJun Ren ; FengQi Si ; ZhiGao Xu…
- 关键词：furnace pressure sequence ; entropy ; validity index ; fuzzy c ; means analysis method based on weighted validity index
- 刊名：SCIENCE CHINA Technological Sciences
- 出版年：2016
- 出版时间：April 2016
- 年：2016
- 卷：59
- 期：4
- 页码：647-656
- 全文大小：1,003 KB
- 参考文献：1.Lee C L, Jou C J G. Improving furnace energy efficiency through adjustment of damper angle. Int J Hydrogen Energ, 2013, 38: 2504–2509CrossRef
2.Luo Z, Zhou H C. A combustion-monitoring system with 3-D temperature reconstruction based on flame-image processing technique. IEEE T Instrum Meas, 2007, 56: 1877–1882CrossRef
3.Zhou H C, Lou C, Cheng Q, et al. Experimental investigations on visualization of three-dimensional temperature distributions in a large-scale pulverized-coal-fired boiler furnace. P Combust Inst, 2005, 30: 1699–1706CrossRef
4.Zhou Y G, Xu T M, Hui S E. Experimental and numerical study on the flow fields in upper furnace for large scale tangentially fired boilers. Appl Therm Eng, 2009, 29: 732–739CrossRef
5.Zanoli, S M, Barchiesi D, Astolfi G, et al. Advanced control solutions to increase efficiency of a furnace combustion process. In: European Control Conference (ECC), Switzerland: IEEE, 2013. 4316–4321
6.Estes M J, Sappey A D, Hofvander H, et al. Method and apparatus for monitoring combustion properties in an interior of a boiler. U.S. Patent 8,786,856. 2014–7-22
7.Piskova E, Morl L. Characterization of spouted bed regimes using pressure fluctuation signals. Chem Eng Sci, 2008, 63: 2307–2316CrossRef
8.Srdjan S, Leckner B, Johnsson F. Characterization of fluid dynamics of fluidized beds by analysis of pressure fluctuations. Prog Energ Combust, 2007, 33: 453–496CrossRef
9.Huang B, Luo Z, Zhou H. Optimization of combustion based on introducing radiant energy signal in pulverized coal-fired boiler. Fuel Process Technol, 2010, 91: 660–668CrossRef
10.Vikhansky A, Barziv E, Chudnovsky B, et al. Measurements and numerical simulations for optimization of the combustion process in a utility boiler. Int J Energ Res, 2004, 28: 391–401CrossRef
11.Ma S H, Hua Y, Li X B. An analysis of flame signals in a boiler furnace based on a phase space reconstruction. J Engin Therm Energ Pow, 2007, 22: 440–442
12.Ronquillo G, Romero C E, Yao Z, et al. On-line flame signal time series analysis for oil-fired burner optimization. Fuel, 2015, 58: 416–423CrossRef
13.Díez L, Cortes C, Arauzo I, et al. Combustion and heat transfer monitoring in large utility boilers. Int J Therm Sci, 2001, 40: 489–496CrossRef
14.Lim G P, Hur K B, Park D Y, et al. The development of boiler furnace pressure control algorithm and distributed control system for coal-fired power plant. T Korean Inst Electric Eng P, 2013, 62: 117–126
15.Zhong W, Zhang M. Characterization of dynamic behavior of a spout-fluid bed with Shannon entropy analysis. Powder Technol, 2005, 159: 121–126CrossRef
16.Hajmeer M, Basheer I. A probabilistic neural network approach for modeling and classification of bacterial growth/nogrowth data. J Microbiol Meth, 2002, 51: 217–226CrossRef
17.Rutkowski L. Adaptive probabilistic neural network for pattern classification in time-varying environment. IEEE T Neural Networ, 2004, 15: 811–827CrossRef
18.Teng Y Y, Chen J C, Lu C W, et al. Effects of the furnace pressure on oxygen and silicon oxide distributions during the growth of multi crystalline silicon ingots by the directional solidification process. J Cryst Growth, 2011, 318: 224–229CrossRef
19.Chen M S, Han J, Yu P S. Data mining: an overview from a database perspective. IEEE T Knowl Data En, 1996, 8: 866–883CrossRef
20.Liao T W. Clustering of time series data-a survey. Pattern Recogn, 2005, 38: 1857–1874CrossRef MATH
21.Bishnu P S, Bhattacherjee V. Software fault prediction using quad tree-based k-means clustering algorithm. IEEE T Knowl Data En, 2012, 24: 1146–1150CrossRef
22.Zadeh L A. Fuzzy sets. Inform Contr, 1965, 8: 338–353MathSciNet CrossRef MATH
23.Bezdek J C, Ehrlich R. Full W. FCM: The fuzzy c-means clustering algorithm. Comput Geosci-UK, 1984, 10: 191–203CrossRef
24.Agustin L E, Salcedo S, Jimenez S, et al. A new grouping genetic algorithm for clustering problems. Expert Syst Appl, 2012, 39: 9695–9703CrossRef
25.Samal N R, Konar A, Das S, et al. A closed loop stability analysis and parameter selection of the particle swarm optimization dynamics for faster convergence. In: IEEE Congress on Evolutionary Computation. Singapore: IEEE, 2007. 1769–1776
26.Nasir M, Das S, Maity D, et al. A dynamic neighborhood learning based particle swarm optimizer for global numerical optimization. Inform Sci, 2012, 209: 16–36MathSciNet CrossRef
27.Forsati R, Keikha A, Shamsfard M, et al. An improved bee colony optimization algorithm with an application to document clustering. Neurocomputing, 2015, 159: 9–26CrossRef
28.Bagirov A M, Mohebi E. Nonsmooth Optimization Based Algorithms in Cluster Analysis. Partitional Clustering Algorithms. Berlin: Springer International Publishing, 2015: 99–146
29.Cura T. A particle swarm optimization approach to clustering. Expert Syst Appl, 2012, 39: 1582–1588CrossRef
30.Rousseeuw P. Silhouettes: A graphical aid to the interpretation and validation of cluster analysis. J Comput Appl Math, 1987, 20: 53–65CrossRef MATH
31.Davies D, Bouldin D. A cluster separation measure. IEEE T Pattern Anal Mach Intell, 1979, 1: 224–227CrossRef
32.Calinski T, Harabasz J. A dendrite method for cluster analysis. Commun Stat-Theor M, 1974, 3: 1–27MathSciNet CrossRef MATH
33.Krzanowski W J, Lai Y T. A criterion for determining the number of groups in a data set using sum-of-squares clustering. Biometrics, 1988: 23–34
34.Srinivasan V, Eswaran C, Sriraam N. Artificial neural network based epileptic detection using time-domain and frequency-domain features. J Med Syst, 2005, 29: 647–660CrossRef
35.Zhang Y L. Zhang Q Y, Melodia T. A frequency-domain entropy-based detector for robust spectrum sensing in cognitive radio networks. IEEE Commun Lett, 2010, 14: 533–535CrossRef
36.Vakkuri A, Ylihankala A, Talja P, et al. Time-frequency balanced spectral entropy as a measure of anesthetic drug effect in central nervous system during sevoflurane, propofol, and thiopental anesthesia. Acta Anaesth Scand, 2004, 48: 145–153CrossRef
37.Asuncion A, Newman D. UCI machine learning repository. 2007. http://ergodicity.net/tag/machine-learning/
ShaoJun Ren (1)
FengQi Si (1)
ZhiGao Xu (1)
LingLing Zhao (1)
1. Key Laboratory of Energy Thermal Conversion and Control of Ministry of Education, Southeast University, Nanjing, 210096, China
Engineering, general
文摘
The furnace process is very important in boiler operation, and furnace pressure works as an important parameter in furnace process. Therefore, there is a need to analyze and monitor the pressure signal in furnace. However, little work has been conducted on the relationship with the pressure sequence and boiler’s load under different working conditions. Since pressure sequence contains complex information, it demands feature extraction methods from multi-aspect consideration. In this paper, fuzzy c-means analysis method based on weighted validity index (VFCM) has been proposed for the working condition classification based on feature extraction. To deal with the fluctuating and time-varying pressure sequence, feature extraction is taken as nonlinear analysis based on entropy theory. Three kinds of entropy values, extracted from pressure sequence in time-frequency domain, are studied as the clustering objects for work condition classification. Weighted validity index, taking the close and separation degree into consideration, is calculated on the base of Silhouette index and Krzanowski-Lai index to obtain the optimal clustering number. Each time FCM runs, the weighted validity index evaluates the clustering result and the optimal clustering number will be obtained when it reaches the maximum value. Four datasets from UCI Machine Learning Repository are presented to certify the effectiveness in VFCM. Pressure sequences got from a 300 MW boiler are then taken for case study. The result of the pressure sequence case study with an error rate of 0.5332% shows the valuable information on boiler’s load and pressure sequence in furnace. The relationship between boiler’s load and entropy values extracted from pressure sequence is proposed. Moreover, the method can be considered to be a reference method for data mining in other fluctuating and time-varying sequences.