Science China Technological Sciences

, Volume 61, Issue 12, pp 1950–1958 | Cite as

Improved fast model migration method for centrifugal compressor based on bayesian algorithm and Gaussian process model

  • Fei ChuEmail author
  • BangWu Dai
  • NanNan Lu
  • XiaoPing Ma
  • FuLi Wang


Design and operation optimization of centrifugal compressor are always based on an accurate prediction model, however, due to the short time operation and lack of data information, it is difficult to get an accurate prediction model of a new centrifugal compressor in time. This paper applies an improved fast model migration method (FMM method) to develop the model of the new centrifugal compressor. The method adapts a Gaussian Process (GP) model from an old centrifugal compressor to fit a new and similar centrifugal compressor, and the adaptation is conducted by a scale-bias adjustment migration technology. In order to obtain the better estimated parameters of migration, Bayesian method, which takes the prior knowledge into consideration, is used in the sequential experiment. The approach is validated by a specific simulation bench. The results indicate that the applied approach can achieve a better prediction precision with fewer data of the new centrifugal compressor compared to pure GP method, and can model the new centrifugal compressor rapidly.


Bayesian centrifugal compressor Gaussian process model model migration performance prediction 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bianchini A, Carnevale E A, Biliotti D, et al. Development of a research test rig for advanced analyses in centrifugal compressors. Energy Procedia, 2015, 82: 230–236CrossRefGoogle Scholar
  2. 2.
    Lu Y, Wang F, Jia M, et al. Centrifugal compressor fault diagnosis based on qualitative simulation and thermal parameters. Mech Syst Signal Processing, 2016, 81: 259–273CrossRefGoogle Scholar
  3. 3.
    Wu S, Ríos-Mercado R Z, Boyd E A, et al. Model relaxations for the fuel cost minimization of steady-state gas pipeline networks. Math Comput Model, 2000, 31: 197–220CrossRefGoogle Scholar
  4. 4.
    De Marco F C G, Elias G P. Fuel consumption model on natural gas compression stations driven by two-shaft gas turbine. In: Group P S I, ed. In: Proceedings of the PSIG Annual Meeting. Napa Valley: Pipeline Simulation Interest Group, 2011Google Scholar
  5. 5.
    Botros K K. Transient phenomena in compressor stations during surge. J Eng Gas Turbines Power, 1994, 116: 133CrossRefGoogle Scholar
  6. 6.
    Greitzer E M. Surge and rotating stall in axial flow compressors—Part I: Theoretical compression system model. J Eng Power, 1976, 98: 190–198CrossRefGoogle Scholar
  7. 7.
    Greitzer E M. Surge and rotating stall in axial flow compressors—Part II: Experimental results and comparison with theory. J Eng Gas Turbines Power, 1976, 98: 199–211CrossRefGoogle Scholar
  8. 8.
    van Helvoirt J, de Jager B. Dynamic model including piping acoustics of a centrifugal compression system. J Sound Vib, 2007, 302: 361–378CrossRefGoogle Scholar
  9. 9.
    Moosania S M, Zheng X. Effect of internal heat leakage on the performance of a high pressure ratio centrifugal compressor. Appl Thermal Eng, 2017, 111: 317–324CrossRefGoogle Scholar
  10. 10.
    Chu F, Wang F L, Wang X G, et al. A model for parameter estimation of multistage centrifugal compressor and compressor performance analysis using genetic algorithm. Sci China Technol Sci, 2012, 55: 3163–3175CrossRefGoogle Scholar
  11. 11.
    Li B, Gu C W, Li X T, et al. Development and application of a throughflow method for high-loaded axial flow compressors. Sci China Technol Sci, 2016, 59: 93–108Google Scholar
  12. 12.
    Zhao H J, Wang Z H, Xi G. Unsteady flow structures in the tip region for a centrifugal compressor impeller before rotating stall. Sci China Technol Sci, 2017, 60: 924–934CrossRefGoogle Scholar
  13. 13.
    Javed A, Pecnik R, Olivero M, et al. Effects of manufacturing noise on microturbine centrifugal impeller performance. J Eng Gas Turbines Power, 2012, 134: 102302–1023029CrossRefGoogle Scholar
  14. 14.
    Xenos D P, Thornhill N F, Cicciotti M, et al. Preprocessing of raw data for developing steady-state data-driven models for optimizing compressor stations. In: Proceedings of the United-Kingdom-Automatic-Control-Council (UKACC) 10th International Conference on Control (CONTROL). Loughborough: IEEE, 2014. 438–443Google Scholar
  15. 15.
    Chu F, Wang F, Wang X, et al. Performance modeling of centrifugal compressor using kernel partial least squares. Appl Thermal Eng, 2012, 44: 90–99CrossRefGoogle Scholar
  16. 16.
    Sodemann A, Li Y, Lee J, et al. Data-driven surge map modeling for centrifugal air compressors. In: Proceedings of the International Mechanical Engineering Congress and Exposition. Chicago: American Society of Mechanical Engineers, 2015. 611–618Google Scholar
  17. 17.
    Cortés O, Urquiza G, Hernández J A. Optimization of operating conditions for compressor performance by means of neural network inverse. Appl Energy, 2009, 86: 2487–2493CrossRefGoogle Scholar
  18. 18.
    Ghorbanian K, Gholamrezaei M. An artificial neural network approach to compressor performance prediction. Appl Energy, 2009, 86: 1210–1221CrossRefGoogle Scholar
  19. 19.
    Sanaye S, Dehghandokht M, Mohammadbeigi H, et al. Modeling of rotary vane compressor applying artificial neural network. Int J Refrigeration, 2011, 34: 764–772CrossRefGoogle Scholar
  20. 20.
    Jafarian M, Ranjbar A M. Fuzzy modeling techniques and artificial neural networks to estimate annual energy output of a wind turbine. Renew Energy, 2010, 35: 2008–2014CrossRefGoogle Scholar
  21. 21.
    Kamal M M, Yu D W, Yu D L. Fault detection and isolation for PEM fuel cell stack with independent rbf model. Eng Appl Artificial Intelligence, 2014, 28: 52–63CrossRefGoogle Scholar
  22. 22.
    Lu J, Gao F. Process Modeling based on process similarity. Ind Eng Chem Res, 2008, 47: 1967–1974CrossRefGoogle Scholar
  23. 23.
    Lu J, Yao Y, Gao F. Model migration for development of a new process model. Ind Eng Chem Res, 2009, 48: 9603–9610CrossRefGoogle Scholar
  24. 24.
    Luo L, Yao Y, Gao F. Iterative improvement of parameter estimation for model migration by means of sequential experiments. Comput Chem Eng, 2015, 73: 128–140CrossRefGoogle Scholar
  25. 25.
    Rasmussen C E. Gaussian Processes in Machine Learning. Berlin, Heidelberg: Springer, 2004. 63–71zbMATHGoogle Scholar
  26. 26.
    Zhang C, Wei H, Zhao X, et al. A Gaussian process regression based hybrid approach for short-term wind speed prediction. Energy Convers Manage, 2016, 126: 1084–1092CrossRefGoogle Scholar
  27. 27.
    Aye S A, Heyns P S. An integrated gaussian process regression for prediction of remaining useful life of slow speed bearings based on acoustic emission. Mech Syst Signal Processing, 2017, 84: 485–498CrossRefGoogle Scholar
  28. 28.
    Loeppky J L, Sacks J, Welch W J. Choosing the sample size of a computer experiment: A practical guide. Technometrics, 2009, 51: 366–376MathSciNetCrossRefGoogle Scholar
  29. 29.
    Ye K Q, Li W, Sudjianto A. Algorithmic construction of optimal symmetric latin hypercube designs. J Statistical Planning Inference, 2000, 90: 145–159MathSciNetCrossRefzbMATHGoogle Scholar
  30. 30.
    Shields M D, Zhang J. The generalization of latin hypercube sampling. Reliability Eng Syst Saf, 2016, 148: 96–108CrossRefGoogle Scholar
  31. 31.
    Box G E, Hunter W G, Hunter J S. Statistics for Experimenters: Design, Innovation, and Discovery. New York: Wiley, 2005zbMATHGoogle Scholar
  32. 32.
    Wyss G D, Jorgensen K H. A User’s Guide to LHS: Sandia’s Latin Hypercube Sampling Software. 1998CrossRefGoogle Scholar
  33. 33.
    Mckay M D, Beckman R J, Conover W J. A comparison of three methods for selecting values of input variables in the analysis of output from a computer code. Technometrics, 2000, 42: 55–61CrossRefzbMATHGoogle Scholar
  34. 34.
    Lindley D V. On a measure of the information provided by an experiment. Ann Math Statist, 1956, 27: 986–1005MathSciNetCrossRefzbMATHGoogle Scholar
  35. 35.
    Fisher R A. The design of experiments. Nature, 1936, 137: 252–254CrossRefGoogle Scholar
  36. 36.
    Roy A, Ghosal S, Rosenberger W F. Convergence properties of sequential Bayesian D-optimal designs. J Statistical Planning Inference, 2009, 139: 425–440MathSciNetCrossRefzbMATHGoogle Scholar
  37. 37.
    Yu Y. On a Multiplicative algorithm for computing bayesian D-optimal designs. 2010, arXiv:1005.2355.Google Scholar
  38. 38.
    Rasmussen C E, Nickisch H. Gaussian processes for machine learning (GPML) toolbox. J Mach Learn Res, 2010, 11: 3011–3015MathSciNetzbMATHGoogle Scholar

Copyright information

© Science in China Press and Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  • Fei Chu
    • 1
    Email author
  • BangWu Dai
    • 1
  • NanNan Lu
    • 1
  • XiaoPing Ma
    • 1
  • FuLi Wang
    • 2
  1. 1.School of Information and Control EngineeringChina University of Mining and TechnologyXuzhouChina
  2. 2.State Key Laboratory of Integrated Automation for Process IndustriesNortheastern UniversityShenyangChina

Personalised recommendations