Research on Optimization of Profile Parameters in Screw Compressor Based on BP Neural Network and Genetic Algorithm
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,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/16/9/3632 |
| _version_ | 1797602764690292736 |
|---|---|
| author | Tao Wang Qiang Qi Wei Zhang Dengyi Zhan |
| author_facet | Tao Wang Qiang Qi Wei Zhang Dengyi Zhan |
| author_sort | Tao Wang |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-11T04:20:14Z |
| format | Article |
| id | doaj.art-7fae189f9cdc478a996c0390b5fc45e6 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-11T04:20:14Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-7fae189f9cdc478a996c0390b5fc45e62023-11-17T22:49:43ZengMDPI AGEnergies1996-10732023-04-01169363210.3390/en16093632Research on Optimization of Profile Parameters in Screw Compressor Based on BP Neural Network and Genetic AlgorithmTao Wang0Qiang Qi1Wei Zhang2Dengyi Zhan3School of Energy and Power Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, ChinaSchool of Energy and Power Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, ChinaSchool of Energy and Power Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, ChinaSchool of Energy and Power Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, ChinaIn 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.https://www.mdpi.com/1996-1073/16/9/3632screw compressorgeometric characteristicsgenetic algorithmBP neural network |
| spellingShingle | Tao Wang Qiang Qi Wei Zhang Dengyi Zhan Research on Optimization of Profile Parameters in Screw Compressor Based on BP Neural Network and Genetic Algorithm Energies screw compressor geometric characteristics genetic algorithm BP neural network |
| title | Research on Optimization of Profile Parameters in Screw Compressor Based on BP Neural Network and Genetic Algorithm |
| title_full | Research on Optimization of Profile Parameters in Screw Compressor Based on BP Neural Network and Genetic Algorithm |
| title_fullStr | Research on Optimization of Profile Parameters in Screw Compressor Based on BP Neural Network and Genetic Algorithm |
| title_full_unstemmed | Research on Optimization of Profile Parameters in Screw Compressor Based on BP Neural Network and Genetic Algorithm |
| title_short | Research on Optimization of Profile Parameters in Screw Compressor Based on BP Neural Network and Genetic Algorithm |
| title_sort | research on optimization of profile parameters in screw compressor based on bp neural network and genetic algorithm |
| topic | screw compressor geometric characteristics genetic algorithm BP neural network |
| url | https://www.mdpi.com/1996-1073/16/9/3632 |
| work_keys_str_mv | AT taowang researchonoptimizationofprofileparametersinscrewcompressorbasedonbpneuralnetworkandgeneticalgorithm AT qiangqi researchonoptimizationofprofileparametersinscrewcompressorbasedonbpneuralnetworkandgeneticalgorithm AT weizhang researchonoptimizationofprofileparametersinscrewcompressorbasedonbpneuralnetworkandgeneticalgorithm AT dengyizhan researchonoptimizationofprofileparametersinscrewcompressorbasedonbpneuralnetworkandgeneticalgorithm |