Artificial Neural Network Structure Optimisation in the Pareto Approach on the Example of Stress Prediction in the Disk-Drum Structure of an Axial Compressor
The article presents the process of selecting and optimising artificial neural networks based on the example of determining the stress distribution in a disk-drum structure compressor stage of an aircraft turbine engine. The presented algorithm allows the determination of von Mises stress values whi...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Materials |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1944/15/13/4451 |
| _version_ | 1797434109116547072 |
|---|---|
| author | Adam Kozakiewicz Rafał Kieszek |
| author_facet | Adam Kozakiewicz Rafał Kieszek |
| author_sort | Adam Kozakiewicz |
| collection | DOAJ |
| description | The article presents the process of selecting and optimising artificial neural networks based on the example of determining the stress distribution in a disk-drum structure compressor stage of an aircraft turbine engine. The presented algorithm allows the determination of von Mises stress values which can be part of the penalty function for further mass optimization of the structure. A method of a parametric model description of a compressor stage is presented in order to prepare a reduced stress distribution for training artificial neural networks. A comparative analysis of selected neural network training algorithms combined with the optimisation of their structure is presented. A genetic algorithm was used to determine the optimal number of hidden layers and neurons in a layer. The objective function was to minimise the absolute value of the relative error and standard deviation of stresses determined by FEM and artificial neural networks. The results are presented in the form of the Pareto front due to the stochastic optimisation process. |
| first_indexed | 2024-03-09T10:27:32Z |
| format | Article |
| id | doaj.art-c45c1fc262a649c3a8dac06a196a6842 |
| institution | Directory Open Access Journal |
| issn | 1996-1944 |
| language | English |
| last_indexed | 2024-03-09T10:27:32Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Materials |
| spelling | doaj.art-c45c1fc262a649c3a8dac06a196a68422023-12-01T21:33:59ZengMDPI AGMaterials1996-19442022-06-011513445110.3390/ma15134451Artificial Neural Network Structure Optimisation in the Pareto Approach on the Example of Stress Prediction in the Disk-Drum Structure of an Axial CompressorAdam Kozakiewicz0Rafał Kieszek1Faculty of Mechatronics, Armament and Aerospace, Institute of Aviation Technology, Military University of Technology, 00-908 Warsaw, PolandFaculty of Mechatronics, Armament and Aerospace, Institute of Aviation Technology, Military University of Technology, 00-908 Warsaw, PolandThe article presents the process of selecting and optimising artificial neural networks based on the example of determining the stress distribution in a disk-drum structure compressor stage of an aircraft turbine engine. The presented algorithm allows the determination of von Mises stress values which can be part of the penalty function for further mass optimization of the structure. A method of a parametric model description of a compressor stage is presented in order to prepare a reduced stress distribution for training artificial neural networks. A comparative analysis of selected neural network training algorithms combined with the optimisation of their structure is presented. A genetic algorithm was used to determine the optimal number of hidden layers and neurons in a layer. The objective function was to minimise the absolute value of the relative error and standard deviation of stresses determined by FEM and artificial neural networks. The results are presented in the form of the Pareto front due to the stochastic optimisation process.https://www.mdpi.com/1996-1944/15/13/4451artificial neural networksoptimizationgenetic algorithmturbine enginesaxial compressorspredictive model |
| spellingShingle | Adam Kozakiewicz Rafał Kieszek Artificial Neural Network Structure Optimisation in the Pareto Approach on the Example of Stress Prediction in the Disk-Drum Structure of an Axial Compressor Materials artificial neural networks optimization genetic algorithm turbine engines axial compressors predictive model |
| title | Artificial Neural Network Structure Optimisation in the Pareto Approach on the Example of Stress Prediction in the Disk-Drum Structure of an Axial Compressor |
| title_full | Artificial Neural Network Structure Optimisation in the Pareto Approach on the Example of Stress Prediction in the Disk-Drum Structure of an Axial Compressor |
| title_fullStr | Artificial Neural Network Structure Optimisation in the Pareto Approach on the Example of Stress Prediction in the Disk-Drum Structure of an Axial Compressor |
| title_full_unstemmed | Artificial Neural Network Structure Optimisation in the Pareto Approach on the Example of Stress Prediction in the Disk-Drum Structure of an Axial Compressor |
| title_short | Artificial Neural Network Structure Optimisation in the Pareto Approach on the Example of Stress Prediction in the Disk-Drum Structure of an Axial Compressor |
| title_sort | artificial neural network structure optimisation in the pareto approach on the example of stress prediction in the disk drum structure of an axial compressor |
| topic | artificial neural networks optimization genetic algorithm turbine engines axial compressors predictive model |
| url | https://www.mdpi.com/1996-1944/15/13/4451 |
| work_keys_str_mv | AT adamkozakiewicz artificialneuralnetworkstructureoptimisationintheparetoapproachontheexampleofstresspredictioninthediskdrumstructureofanaxialcompressor AT rafałkieszek artificialneuralnetworkstructureoptimisationintheparetoapproachontheexampleofstresspredictioninthediskdrumstructureofanaxialcompressor |