Monitorización y diagnóstico de centrales térmicas
desarrollo de un detector visual de estados estacionarios
Palavras-chave:
Series temporales, Minería de datos, Diagnostico, Pronóstico, Generadores de vaporResumo
Se presenta el diseño y las prestaciones de una aplicación desarrollada en Matlab®, orientada a dar soporte de cálculo para el tratamiento de los valores medios aproximados de intervalos de tiempo que resultan de la selección visual de series temporales que es el formato con el que se consideran a los registros industriales. Los datos de entrada pueden provenir de registros históricos de procesos industriales (termo-energéticos) ó de aquellos generados mediante simulación directa a través de la aplicación Simulink. El objetivo de este estudio es la monitorización de los diferentes estados cuasi-estacionarios (QSS) en una central térmica, a fin de poder identificar y realizar la diagnosis de posibles fallos. Pueden ser visualizadas hasta 8 señales linealmente normalizadas y distribuidas y el usuario, mediante dos cursores, puede seleccionar ventanas cortas de señales almacenadas. En esta versión, se computan datos estadísticos que facilitan el modelado estático, los cuales podrán ser exportados a un fichero Excel. Es una aplicación abierta, por lo que permite la inclusión de nuevas prestaciones. Un comando específico facilita el modelado dinámico y su aplicabilidad se demuestra con un ejemplo de análisis de series temporales provenientes de una central térmica de 250 MWe.
Downloads
Referências
[2] S. Nihau, K. P. R. Vilankar and R. Rhinehart, “Type-II critical values for a steady-state identifier,” Journal of Process Control, vol. 20, nº 7, pp. 885-890, 2010.
[3] J. Finn, J. Wagner and H. Bassily ,“Monitoring strategies for a combined cycle electric power generator,” Applied Energy, vol. 87, nº 8, pp. 2621-2627, 2010.
[4] J. Ballester and T. Garcia-Armingol, “Diagnostic techniques for the monitoring and control of practical flames,” Progress in Energy and Combustion Science, vol. 36, nº 4, pp. 375-411, 2010.
[5] X. Z. Wang, “Knowledge discovery through mining process operational data, application of neural networks and other learning technologies,” Process Engineering, pp. 287-327, 2001.
[6] J. F. Macgregor, “Data-Based Latent Variable Methods for Process Analysis, Monitoring and Control," presented at the European Symposium on Computer Aided Process Engineering, 14, Lisbon, 2004.
[7] P. V. R. Carvalho, I. L. Dos Santos and M. R. S. Borges, “Micro incident analysis framework to assess safety and resilience in the operation of safe critical systems: a case study in a nuclear power plant,” Journal of Loss Prevention in the Process Industries, n° 21, pp. 277-286, 2008.
[8] M. R. Mano, R. Rengaswamy and A. Venkatasubramanian, “A signed directed graphbased systematic framework for steady-state malfunction diagnosis inside control loops,” Chemical Engineering Science, vol. 61, n° 6, pp. 1790-1810, 2006.
[9] M. W. Barry and N. B. Gallagher, “The process chemometrics approach monitoring and fault detection,”J. Proc. Cont., vol. 6, n° 6, pp. 329-348, 1996.
[10] K. J. Cios, W. Pedrycz and R. W. Swiniarski, Data mining methods for knowledge discovery. Boston: Kluwer Academic, 1998.
[11] J. Han and M. Kamber, Data mining: concepts and techniques. San Francisco: Morgan Kaufmann, 2001.
[12] S. Uson, A. Valero and L. Correas, “Energy efficiency assessment and improvement in energy intensive systems through thermoeconomic diagnosis of the operation,” Applied Energy, vol. 87, n° 6, pp. 1989-1995, 2010.
[13] Hand D, H. Mannila and P. Smyth, Principles of Data Mining. Cambridge: MIT Press, 2001.
[14] C. Apte, B. Liu, E. P. D. Pednault and P. Smyth “Business Applications of Data Mining. Communications of the ACM, vol. 45, n° 8, pp.49-53, 2008.
[15] U. M. Fayyad, G. Piatesky-Shapiro and P. Smyth, “From Data Mining to Knowledge Discovery: an overview,” in Advances in Knowledge Discovery and Data Mining. Menlo Park, Calif.: AAAI/MIT Press, 1996, pp. 1-34.
[16] M. Schladt and B. Hui, “Soft sensors on nonlinear steady-state data reconciliation in the process industry,” Chemical Engineering and Processing, n° 46, pp. 1107-1115, 2007.
[17] M. Kano, S. Hasebe, I. Hashimoto and H. Ohno, “A new multivariate statistical process monitoring method using principal component analysis,” Computers & Chemical Engineering, vol. 25, n° 7-8, pp. 1103-1113, 2001.
[18] J. F. MacGregor, “Data-based latent variable methods for process analysis, monitoring and control,” presented at the 37th. European Symposium of the Working Party on Computer-Aided Process Engineering, n° 18, pp. 87-98, 2004.
[19] P. Odiowei and Y. Cao, “Nonlinear dynamic process monitoring using canonical variate analysis and kernel density estimations, industrial informatics,” IEEE Transactions, vol. 6, n° 1, pp. 36-45, 2011.
[20] MATLAB/SIMULINK, http://www.mathworks.com, 2008.
[21] J. M. Blanco and F. Peña, “Analytical study of the effects of the clogging of a mechanical precipitator unit in air preheaters in a high-performance thermoelectric power plant based on available data,” ASME Journal of Engineering for Gas Turbines and Power, vol. 130, n° 2, pp. 22001-22007, 2008.
[22] C. Poma, V. Verda and S. Consonni “Design and performance evaluation of a waste-toenergy plant integrated with a combined cycle,” Energy, n° 35, pp. 786-793, 2010.
[23] J. M. Blanco and F. Peña “Optimizing preliminary design of industrial equipment involving different thermal engineering calculation procedures over a power plant”, in Thermal engineering research developments. New York: Nova Science Publishers, 2010, ch. 1.
Downloads
Publicado
Como Citar
Edição
Seção
Licença
Copyright (c) 2019 Luis Vázquez, Jesús María Blanco, Francisco Peña, José Manuel Rodríguez
Este trabalho está licenciado sob uma licença Creative Commons Attribution 4.0 International License.
