一种基于动态建模的磨煤机故障诊断方法

doi:10.11799/ce201804028

Abstract

Abstract: Taking the BBD3854 coal mill of 660-MW unit in Hequ power plant in Shanxi as the research object,the dynamic mathematical model is built to approximate the real system, and the model is verified by real data. In order to enrich the fault knowledge base and research on the fault diagnosis,the real fault of the pulverizing system is simulated, and the variation rule of the characteristic parameters under different faults is excavated.A new method of fault diagnosis based on the fault scaling factor search technique is proposed by summarizing the similarity rules of different severity faults.This method only needs to carry on the off-line training to each kind of fault in the typical fault sample,this makes the fault diagnosis and identification faster and more stable.The effectiveness of the proposed method is verified by an example of an auxiliary coal pulverizer.

CLC Number:

TD453

0
/ / Recommend

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

URL: http://www.coale.com.cn/EN/10.11799/ce201804028

http://www.coale.com.cn/EN/Y2018/V50/I4/110

References

[1]S. Guo, J. H. Wang, and J. L. Wei, “A new model based approach for power plant Tube-ball mill condition monitoring and fault detection ,” Energy Convers. Manag. , vol. 80, no. 2, pp. 10-19, 2014.
[2]N. Rees and F. Fan, “Modelling and control of pulverised fuel coal mills,” in Thermal Power Plant Simulation and Control, 1st ed., D. Flynn, Ed. London, U.K.: IEE, 2003.
[3]J. L. Wei, J. Wang, and Q. H. Wu, “Development of a multi-segment coal mill model using an evolutionary computation technique,” IEEE Trans. Energy Convers., vol. 22, no. 3, pp. 718-727, 2007.
[4]Fan G Q, Rees N W. An intelligent expert system (KBOSS) for power plant coal mill supervision and control [J]. Control Engineering Practice, 1997, 5(1):101-108.
[5]Odgaard P F, Lin B, J?rgensen S B. Observer-based and regression model-based detection of emerging faults in coal mills[J]. Fault Detection Supervision & Safety of Technical Processes, 2006, 39(13):687-692.
[6]Odgaard P F, Mataji B. Observer-based fault detection and moisture estimating in coal mills[J]. Control Engineering Practice, 2008, 16(8):909-921.
[7]V. Vapnik, Statistical Learning Theory, Springer, Berlin, 1998.
[8]Y. Pang, K. Zhang, Y. Yuan, and K. Wang, “Distributed object detection with linear SVMs,” IEEE Trans. Cybern., vol. 44, no. 11, pp. 2122–2133, Nov. 2014.
[9]J. Xu et al., “The generalization ability of SVM classification based on Markov sampling,” IEEE Trans. Cybern., vol. 45, no. 6, pp. 1169–1179, Jun. 2015.
[10]D. Iacoviello, A. Petracca, M. Spezialetti, and G. Placidi, “A classification algorithm for electroencephalography signals by self-induced emotional stimuli,” IEEE Trans. Cybern., vol. PP, no. 99, pp. 1-10, 2015.
[11]A. Dong, F. L. Chung, Z. H. Deng, and S. T. Wang, “Semi-supervised SVM with extended hidden features,” IEEE Trans. Cybern., vol. PP, no. 99, pp. 1-14, 2015.
[12]P. Costamagna, A. D. Giorgi, L. Magistri, et al, “A classification approach for model-based fault diagnosis in power generation systems based on solid oxide fuel cells,” IEEE Trans. Energy Convers., vol. 31, no. 2, pp. 676-687, 2016.
[13]Adankon M M, Cheriet M. Model selection for the LS-SVM. Application to handwriting recognition [J]. Pattern Recognition, 2009, 42(12):3264-3270.
[14]Zheng P P, Feng J, Li Z, et al. A novel SVD and LS-SVM combination algorithm for blind watermarking [J]. Neurocomputing, 2014, 142(1):520-528.
[15]Wang P, Tian J W, Gao C Q. Infrared small target detection using directional highpass filters based on LS-SVM[J]. Electronics Letters, 2009, 45(3):156-158.
[16]Zhou H R, Zheng P E, Zhao C X. LS-SVM parameters selection based on genetic algorithm and its application in economic forecasting [J]. Journal of Computer Applications, 2007, 27(6):1418-1417.

A Fault Diagnosis Method for Coal Mill Based on Dynamic Modeling

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 1

Recommended Articles

Metrics

Comments