Research on Optimization of Profile Parameters in Screw Compressor Based on BP Neural Network and Genetic Algorithm

Tao Wang, Qiang Qi, Wei Zhang () and Dengyi Zhan
Additional contact information
Tao Wang: School of Energy and Power Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China
Qiang Qi: School of Energy and Power Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China
Wei Zhang: School of Energy and Power Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China
Dengyi Zhan: School of Energy and Power Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China

Energies, 2023, vol. 16, issue 9, 1-17

Abstract: In order to accurately calculate the geometric characteristics of the twin-screw compressor and obtain the optimal profile parameters, a calculation method for the geometric characteristics of twin-screw compressors was proposed to simplify the profile parameter design in this paper. In this method, the database of geometric characteristics is established by back-propagation (BP) neural network, and the genetic algorithm is used to find the optimal profile design parameters. The effects of training methods and hidden layers on the calculation accuracy of neural network are discussed. The effects of profile parameters, including inner radius of the male rotor, protection angle, radius of the elliptic arc, outer radius of the female rotor on the comprehensive evaluation value composed of length of the contact line, blow hole area and area utilization rate, are analyzed. The results show that the time consumed for the database established by BP neural network is 92.8% shorter than that of the traditional method and the error is within 1.5% of the traditional method. Based on the genetic algorithm, compared with the original profile, the blow hole area of the screw compressor profile optimized by genetic algorithm is reduced by 54.8%, the length of contact line is increased by 1.57% and the area utilization rate is increased by 0.32%. The CFD numerical model is used to verify the optimization method, and it can be observed that the leakage through the blow hole of the optimized model is reduced, which makes the average mass flow rate increase by 5.2%, indicating the effectiveness of the rotor profile parameter optimization method.

Keywords: screw compressor; geometric characteristics; genetic algorithm; BP neural network (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/16/9/3632/pdf (application/pdf)
https://www.mdpi.com/1996-1073/16/9/3632/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:16:y:2023:i:9:p:3632-:d:1130978

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().