Optimization of a Stirling Engine by Variable-Step Simplified Conjugate-Gradient Method and Neural Network Training Algorithm
The present study develops a novel optimization method for designing a Stirling engine by combining a variable-step simplified conjugate gradient method (VSCGM) and a neural network training algorithm. As compared with existing gradient-based methods, like the conjugate gradient method (CGM) and sim...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-10-01
|
Series: | Energies |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1073/13/19/5164 |
_version_ | 1797551848129822720 |
---|---|
author | Chin-Hsiang Cheng Yu-Ting Lin |
author_facet | Chin-Hsiang Cheng Yu-Ting Lin |
author_sort | Chin-Hsiang Cheng |
collection | DOAJ |
description | The present study develops a novel optimization method for designing a Stirling engine by combining a variable-step simplified conjugate gradient method (VSCGM) and a neural network training algorithm. As compared with existing gradient-based methods, like the conjugate gradient method (CGM) and simplified conjugate gradient method (SCGM), the VSCGM method is a further modified version presented in this study which allows the convergence speed to be greatly accelerated while the form of the objective function can still be defined flexibly. Through the automatic adjustment of the variable step size, the optimal design is reached more efficiently and accurately. Therefore, the VSCGM appears to be a potential and alternative tool in a variety of engineering applications. In this study, optimization of a low-temperature-differential gamma-type Stirling engine was attempted as a test case. The optimizer was trained by the neural network algorithm based on the training data provided from three-dimensional computational fluid dynamic (CFD) computation. The optimal design of the influential parameters of the Stirling engine is yielded efficiently. Results show that the indicated work and thermal efficiency are increased with the present approach by 102.93% and 5.24%, respectively. Robustness of the VSCGM is tested by giving different sets of initial guesses. |
first_indexed | 2024-03-10T15:51:55Z |
format | Article |
id | doaj.art-9d36d22a332c406897131a28aeb4d1c2 |
institution | Directory Open Access Journal |
issn | 1996-1073 |
language | English |
last_indexed | 2024-03-10T15:51:55Z |
publishDate | 2020-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Energies |
spelling | doaj.art-9d36d22a332c406897131a28aeb4d1c22023-11-20T16:00:46ZengMDPI AGEnergies1996-10732020-10-011319516410.3390/en13195164Optimization of a Stirling Engine by Variable-Step Simplified Conjugate-Gradient Method and Neural Network Training AlgorithmChin-Hsiang Cheng0Yu-Ting Lin1Department of Aeronautics and Astronautics, National Cheng Kung University, No.1, University Road, Tainan 70101, TaiwanDepartment of Aeronautics and Astronautics, National Cheng Kung University, No.1, University Road, Tainan 70101, TaiwanThe present study develops a novel optimization method for designing a Stirling engine by combining a variable-step simplified conjugate gradient method (VSCGM) and a neural network training algorithm. As compared with existing gradient-based methods, like the conjugate gradient method (CGM) and simplified conjugate gradient method (SCGM), the VSCGM method is a further modified version presented in this study which allows the convergence speed to be greatly accelerated while the form of the objective function can still be defined flexibly. Through the automatic adjustment of the variable step size, the optimal design is reached more efficiently and accurately. Therefore, the VSCGM appears to be a potential and alternative tool in a variety of engineering applications. In this study, optimization of a low-temperature-differential gamma-type Stirling engine was attempted as a test case. The optimizer was trained by the neural network algorithm based on the training data provided from three-dimensional computational fluid dynamic (CFD) computation. The optimal design of the influential parameters of the Stirling engine is yielded efficiently. Results show that the indicated work and thermal efficiency are increased with the present approach by 102.93% and 5.24%, respectively. Robustness of the VSCGM is tested by giving different sets of initial guesses.https://www.mdpi.com/1996-1073/13/19/5164neural networksoptimizationstirling enginesVSCGM |
spellingShingle | Chin-Hsiang Cheng Yu-Ting Lin Optimization of a Stirling Engine by Variable-Step Simplified Conjugate-Gradient Method and Neural Network Training Algorithm Energies neural networks optimization stirling engines VSCGM |
title | Optimization of a Stirling Engine by Variable-Step Simplified Conjugate-Gradient Method and Neural Network Training Algorithm |
title_full | Optimization of a Stirling Engine by Variable-Step Simplified Conjugate-Gradient Method and Neural Network Training Algorithm |
title_fullStr | Optimization of a Stirling Engine by Variable-Step Simplified Conjugate-Gradient Method and Neural Network Training Algorithm |
title_full_unstemmed | Optimization of a Stirling Engine by Variable-Step Simplified Conjugate-Gradient Method and Neural Network Training Algorithm |
title_short | Optimization of a Stirling Engine by Variable-Step Simplified Conjugate-Gradient Method and Neural Network Training Algorithm |
title_sort | optimization of a stirling engine by variable step simplified conjugate gradient method and neural network training algorithm |
topic | neural networks optimization stirling engines VSCGM |
url | https://www.mdpi.com/1996-1073/13/19/5164 |
work_keys_str_mv | AT chinhsiangcheng optimizationofastirlingenginebyvariablestepsimplifiedconjugategradientmethodandneuralnetworktrainingalgorithm AT yutinglin optimizationofastirlingenginebyvariablestepsimplifiedconjugategradientmethodandneuralnetworktrainingalgorithm |