Simulating Characteristics of Vaneless Diffusers Using Neural Networks

To calculate flow parameters of a vaneless diffuser of the centrifugal compressor stage, it is sufficient to determine the loss coefficient and the flow direction at the outlet. The paper presents the results of modeling the characteristics of these two parameters using neural networks and CFD methods. To obtain mathematical models, ANSYS calculation data was used for vaneless diffusers with a relative width of 0.014–0.1, relative outlet diameter of 1.4–2.0, inlet flow angle of 10–90° and velocity coefficient of 0.39–0.82, with the Reynolds number being in the range of 87 500–1 030 000. A comparison with the theory showed the regularity of gas-dynamic characteristics, and comparison with well-known experiments showed the correspondence of the flow structure. In order to improve the accuracy of simulation using neural networks, various recommendations on the preparation and processing of the initial data were collected and tested: identification of conflict examples and outliers, data normalization, improving the quality of the neural network training under the insufficient amount of sampling, etc. The application of the aforementioned recommendations significantly improved the accuracy of simulation. A simulation experiment based on neural models for studying the influence of dimensions, diffuser shape and similarity criteria on the diffuser gas dynamic characteristics made it possible to verify physical adequacy of the mathematical models, obtain new data on energy conversion processes and produce a set of recommendations on the optimal design of vaneless diffusers.

References

[1] Ris V.F. Tsentrobezhnyye kompressornyye mashiny [Centrifugal compressor machines]. Leningrad, Mashinostroyeniye publ., 1981. 351 p.

[2] Den G.N. Proyektirovaniye protochnoy chasti tsentrobezhnykh kompressorov [Design of the flow part of centrifugal compressors]. Leningrad, Mashinostroyeniye, Leningradskoye otdeleniye publ., 1980. 230 p.

[3] Shnepp V.B. Konstruktsiya i raschet tsentrobezhnykh kompressornykh mashin [Design and calculation of centrifugal compressor machines]. Moscow, Mashinostroyeniye publ., 1995. 240 p.

[4] Khisameyev I.G., Maksimov V.A., Batkis G.S., Guzel’bayev Ya.Z. Proyektirovaniye i ekspluatatsiya promyshlennykh tsentrobezhnykh kompressorov [Design and operation of industrial centrifugal compressors]. Kazan, Fen publ., 2012. 671 p.

[5] Aungier R.H. Centrifugal compressors: a strategy for aerodynamic design and analysis. New York, ASME Press, 2000. 320 p.

[6] Japikse D., Krivitzky E.M. Radial stages with non-uniform pressures at diffuser inlet. Proceedings of the ASME Turbo Expo, 2016, vol. 2D-2016, doi: 10.1115/GT2016-57956

[7] Schiff J. A preliminary design tool for radial compressors. Thesis for the Degree of Master of Science, LTH Lund University, 2013. 171 p.

[8] Wang Y., Lin F., Nie C., Engeda A. Design and performance evaluation of a very low flow coefficient centrifugal compressor. International Journal of Rotating Machinery, 2013, vol. 2013, no. 293486, doi: 10.1155/2013/293486

[9] Vasil’yev Yu.S., Rodionov P.I., Sokolovskiy M.I. New generation high performance centrifugal compressors. Scientific principles of calculation, development of optimal design methods and production development. Nauka i promyshlennost’ Rossii, 2000, no. 10–11, pp. 78–85 (in Russ.).

[10] Galerkin Yu.B., Rekstin A.F., Soldatova K.V., Drozdov A.A., Popov Yu.A. Development of the scientific school of turbocompressor engineering LPI-SPbPU of Peter the Great, the results of cooperation with compressor builders. 17-aya Mezhdunar. nauch.-tekhn. konf. po kompressornoy tekhnike [17th International Scientific and Technical Conference on Compressor Engineering]. Kazan, 2017, pp. 19–29.

[11] Galerkin Yu.B. Turbokompressory. Rabochiy protsess, raschet i proyektirovaniye protochnoy chasti [Turbochargers. Workflow, calculation and design of the flow part]. Moscow, KKHT publ., 2010. 596 p.

[12] Seleznev K.P., Galerkin Yu.B. Tsentrobezhnyye kompressory [Centrifugal compressors.]. Leningrad, Mashinostroyeniye publ., 1982. 271 p.

[13] Marenina L.N. CFD Wind Tunnel Tests of Centrifugal Stage Return Channel Vane Cascades. Kompressornaya tekhnika i pnevmatika, 2016, no. 3, pp. 27–35 (in Russ.).

[14] Gamburger D.M. Chislennoye modelirovaniye techeniya vyazkogo gaza v tsentrobezhnoy kompressornoy stupeni: metodika i rezul’taty [Numerical modeling of viscous gas flow in a centrifugal compressor stage: methodology and results]. Sankt-Petersburg, SPbGPU publ., 2009. 190 p.

[15] Meduri U.K., Selvam K., Nawrocki G. CFD analysis of centrifugal compressor stage range extension using internal flow recirculation. Proceedings of the ASME Turbo Expo, 2015, vol. 2C, doi: 10.1115/GT2015-42592

[16] Galerkin Y., Voinov I., Drozdov A. Comparison of CFD-calculations of centrifugal compressor stages by NUMECA Fine/Turbo and ANSYS CFX programs. IOP Conference Series: Materials Science and Engineering, 2017, vol. 232(1), no. 012044, doi: 10.1088/1757-899X/232/1/012044

[17] Galerkin Yu.B., Solov’yeva O.A. Improvement of vaneless diffuser calculations based on CFD experiment. Kompressornaya tekhnika i pnevmatika, 2014, no. 3, pp. 35–41 (in Russ.).

[18] Galerkin Yu.B., Solov’yeva O.A. Improvement of vaneless diffuser calculations based on CFD experiment. Kompressornaya tekhnika i pnevmatika, 2014, no. 3, pp. 15–21 (in Russ.).

[19] Rekstin A.F., Drozdov A.A., Solovyeva O.A., Galerkin Y.B. Two mathematical models centrifugal compressor stage vaneless diffuser comparison. Oil and Gas Engineering. AIP Conf. Proc., 2007, Omsk, 2018, pp. 030035-1–030035-12, doi: https://doi.org/10.1063/1.5051896

[20] Solov’yeva O.A. Matematicheskaya model’ dlya rascheta gazodinamicheskikh kharakteristik i optimizatsii bezlopatochnykh diffuzorov tsentrobezhnykh kompressornykh stupeney. Kand. Diss. [A mathematical model for calculating the gas-dynamic characteristics and optimizing the bezelobnyh diffusers of centrifugal compressor stages. Cand. Diss.]. Sankt-Petersburg, 2018. 162 p.

[21] Nikiforov A., Popova D., Soldatova K. A network application for modeling a centrifugal compressor performance map. IOP Conference Series: Materials Science and Engineering, 2017, vol. 232(1), no. 012046, doi: 10.1088/1757-899X/232/1/012046

[22] Yasnitskiy L.N. Intellektual’nyye sistemy [Intelligent systems]. Moscow, Laboratoriya znaniy publ., 2016. 221 p.

[23] Kazantsev P.A. Razrabotka i issledovaniye marshruta proyektirovaniya neyrosetevogo prilozheniya s apparatnoy podderzhkoy. Kand. Diss. [Development and research of a design route for a neural network application with hardware support. Cand. Diss.]. Moscow, 2008. 117 p.

[24] Dagayeva M.V., Suleymanov M.A., Kataseva D.V., Katasev A.S., Kirpichnikov A.P. Technology of construction of fault-tolerant neural-network handwriting recognition models in biometric authentication systems. Vestnik Tekhnologicheskogo universiteta, 2018, vol. 21, no. 2, pp. 133–138 (in Russ.).

[25] Shkodyrev V.P., Yagafarov K.I., Bashtovenko V.A., Il’ina E.E. Overview of Anomaly Detection Methods in Data Streams. Trudy konferentsii po programmnoy inzhenerii i informatsionnomu upravleniyu [Proc. of the Second Conference on Software Engineering and Information Management]. Sankt-Petersburg, 2017, vol. 1864. 7 p.

[26] Jayalakshmi T., Santhakumaran Dr.A. Statistical Normalization and Back Propagation for Classification. International Journal of Computer Theory and Engineering, 2011, vol. 3, no. 1, pp. 89–93.

[27] Ogasawara E., Martinez L.C., De Oliveira D., Zimbrao G., Pappa G.L., Mattoso M. Adaptive Normalization: A Novel Data Normalization Approach for Non-Stationary Time Series. Proceedings of the International Joint Conference on Neural Networks, 2010, no. 5596746, doi: 10.1109/IJCNN.2010.5596746

[28] Nayak S.C., Misra B.B., Behera H.S. Impact of Data Normalization on Stock Index Forecasting. International Journal of Computer Information Systems and Industrial Management Applications, 2014, vol. 6, pp. 257–269.

[29] Osovskiy S. Neyronnyye seti dlya obrabotki informatsii [Neural networks for information processing]. Moscow, Finansy i statistika publ., 2002. 344 p.

[30] Borisov V.V., Fedulov A.S., Zernov M.M. Osnovy gibridizatsii nechetkikh modeley [Basics of hybridization of fuzzy models]. Moscow, Goryachaya liniya-Telekom publ., 2017. 100 p.