THERMAL SCIENCE

International Scientific Journal

Thermal Science - Online First

online first only

Fault diagnosis analysis and health management of thermal performance of multi-source data fusion equipment based on fog computing model

ABSTRACT
Waste heat boiler will be restricted by the exhaust parameters of gas turbine, at the same time, it will affect the thermal characteristics of steam side, and its flue gas resistance will directly affect the power and efficiency of gas turbine cycle, which will have an important impact on the efficiency of combined cycle system. Therefore, it is necessary to monitor the running status of the equipment in time, identify the early signs of faults, and make accurate judgments on fault location, fault degree and development trend, so as to improve the reliability and availability of the unit. The thermal system is the main part of thermal power plant production, so the fault diagnosis of this part is particularly important. In this paper, a method of thermal performance fault diagnosis and health management for multi-source data fusion equipment based on fog computing model is proposed. Using the theory of multi-source data fusion analysis, the qualitative values of the parameters of the fog computing model are marked, and the causes of the failure of the failure variables are obtained. Complete the fault subspace identification, and comprehensively evaluate the equipment status according to multi-attribute decision. This method is conducive to the accurate identification of early faults and the accurate judgment of fault degree and fault trend
KEYWORDS
PAPER SUBMITTED: 2020-06-21
PAPER REVISED: 2020-08-28
PAPER ACCEPTED: 2020-09-23
PUBLISHED ONLINE: 2020-10-31
DOI REFERENCE: https://doi.org/10.2298/TSCI200621318W
REFERENCES
  1. He, B. et al., Leakage diagnosis of gas-steam combined cycle waste heat boiler based on principal component analysis. Guangdong Electric Power, 30(2017), 006, pp. 1-5.
  2. Zhao, Y. et al., Summary of Wind Turbine Condition Monitoring and Fault Diagnosis Technology. Thermal Power Generation, 45(2016), 010, pp. 1-5.
  3. Jin, X. et al., Summary of research on fault diagnosis and prediction technology of wind turbines. Chinese Journal of Scientific Instrument, 38(2017), 005, pp. 1041-1053.
  4. Chen, C. et al., Fault diagnosis of SCR flue gas denitrification system in a power plant. China Electric Power, 5 (2016), pp.63-66.
  5. Shi, Z., Signal detection and fault diagnosis of driving drum of large belt conveyor. Mining Machinery, 000(2016), 004, pp. 27-30.
  6. Huang, B. et al., Fault diagnosis of thermal equipment based on similarity modeling and fuzzy probability directed graph. Thermal Power Generation, 47(2018), 377, pp.108-113 .
  7. Shi, Z. et al., Fault diagnosis method of public bicycle system based on naive Bayes classifier. China Mechanical Engineering, 30(2019), 008, pp. 983-987.
  8. Pan, H. and Zhang, Y. Fault diagnosis of ammunition supply system based on texture features of SST time-frequency graph. Journal of Vibration and Shock, 39(2020), 6, pp. 132-137.
  9. Baldi, S. et al., Real-time monitoring energy efficiency and performance degradation of condensing boilers. Energy Conversion and Management, 136(2017), pp.329-339.
  10. Fouad, M. A., Early Failure of Waste Heat Boiler and Redesign to Overcome Premature Failure. Journal of Failure Analysis & Prevention, 17(2017), 3, pp. 395-399.
  11. He, J. et al., Typical fault diagnosis of SCR flue gas denitrification system operation in coal-fired power plants. China Electric Power, 8 (2016), pp.148-153.
  12. Li, W. et al., Thermal parameter sensor fault diagnosis based on dynamic data mining. Vibration, Testing and Diagnosis, 4(2016), pp. 694-699.
  13. Lei, Y. et al., Opportunities and challenges of mechanical intelligent fault diagnosis under big data. Chinese Journal of Mechanical Engineering, 054(2018), 005, pp. 94-104.
  14. Wang, L. et al., Fault diagnosis method of asynchronous motor using deep learning. Journal of Xi'an Jiaotong University, 51(2017), 010, pp. 128-134.
  15. Tu, Y. et al., Research on optimal fault diagnosis algorithm based on dimensionality reduction observer. Chinese Space Science and Technology, 37(2017), 223, pp.44-49.
  16. Imasato, K. et al., Exceptional thermoelectric performance in Mg3Sb0.6Bi1.4 for low-grade waste heat recovery. Energy & Environmental ence, 12(2019), 3, pp. 965-971.
  17. Zhao, Y. et al., Analysis of thermoelectric generation characteristics of flue gas waste heat from natural gas boiler. Energy Conversion and Management, 148(2017), 9, pp. 820-829.
  18. Wang, D. et al., Calculation and Analysis on Recovery of the Waste Heat of the Flue Gas in Gas Boiler in Cold Region. Journal of Jilin Institute of Civil Engineering and Architecture, 035(2018), 002, pp. 48 -52.
  19. Duan, A. et al., Heat exchanger simulation and recovery device design of waste heat boiler of gas turbine generator set on ocean platform. Journal of Intelligent and Fuzzy Systems, 38(2020), 2, pp.1257-1263.
  20. Liu, X. Cause analysis of damages of coalescer of waste heat boiler in petroleum refinery and countermeasures. Petroleum Refinery Engineering, 48(2018), 6, 49-52.
  21. Zhu, Q. B. and Li, Z., Application of Heat Pipe Boiler in Waste Heat Recovery from the System of Acid Making with Gas in a Copper Smelter. Energy saving in non-ferrous metallurgy, 035(2019), 003, 24-28.
  22. Zhang, C. L. et al., Intelligent fault diagnosis method of power transformer based on deep learning. Journal of Electronic Measurement and Instrument, 1 (2020), pp.81-89.
  23. Wang. et al., Power dispatch fault diagnosis based on warning signal text mining. Electric Power Automation Equipment, 039(2019), 004, pp. 126-132.