Plane Cascade Aerodynamic Performance Prediction Based on Metric Learning for Multi-Output Gaussian Process Regression
Multi-output Gaussian process regression measures the similarity between samples based on Euclidean distance and assigns the same weight to each feature. However, there are significant differences in the aerodynamic performance of plane cascades composed of symmetric and asymmetric blade shapes, and...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-09-01
|
Series: | Symmetry |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-8994/15/9/1692 |
_version_ | 1797576612811636736 |
---|---|
author | Lin Liu Chunming Yang Honghui Xiang Jiazhe Lin |
author_facet | Lin Liu Chunming Yang Honghui Xiang Jiazhe Lin |
author_sort | Lin Liu |
collection | DOAJ |
description | Multi-output Gaussian process regression measures the similarity between samples based on Euclidean distance and assigns the same weight to each feature. However, there are significant differences in the aerodynamic performance of plane cascades composed of symmetric and asymmetric blade shapes, and there are also significant differences between the geometry of the plane cascades formed by different blade shapes and the experimental working conditions. There are large differences in geometric and working condition parameters in the features, which makes it difficult to accurately measure the similarity between different samples when there are fewer samples. For this problem, a metric learning for the multi-output Gaussian process regression method (ML_MOGPR) for aerodynamic performance prediction of the plane cascade is proposed. It shares parameters between multiple output Gaussian distributions during training and measures the similarity between input samples in a new embedding space to reduce bias and improve overall prediction accuracy. For the analysis of ML_MOGPR prediction results, the overall prediction accuracy is significantly improved compared with multi-output Gaussian process regression (MOGPR), backpropagation neural network (BPNN), and multi-task learning neural network (MTLNN). The experimental results show that ML_MOGPR is effective in predicting the performance of the plane cascade, and it can quickly and accurately make a preliminary estimate of the aerodynamic performance and meet the performance parameter estimation accuracy requirements in the early stage. |
first_indexed | 2024-03-10T21:54:25Z |
format | Article |
id | doaj.art-4569da820c8348f580b29be2028beeb5 |
institution | Directory Open Access Journal |
issn | 2073-8994 |
language | English |
last_indexed | 2024-03-10T21:54:25Z |
publishDate | 2023-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Symmetry |
spelling | doaj.art-4569da820c8348f580b29be2028beeb52023-11-19T13:11:19ZengMDPI AGSymmetry2073-89942023-09-01159169210.3390/sym15091692Plane Cascade Aerodynamic Performance Prediction Based on Metric Learning for Multi-Output Gaussian Process RegressionLin Liu0Chunming Yang1Honghui Xiang2Jiazhe Lin3School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang 621010, ChinaSchool of Computer Science and Technology, Southwest University of Science and Technology, Mianyang 621010, ChinaAECC Sichuan Gas Turbine Establishment, Mianyang 621000, ChinaChina Aerodynamics Research and Development Center, Computational Aerodynamic Research Institute, Mianyang 621000, ChinaMulti-output Gaussian process regression measures the similarity between samples based on Euclidean distance and assigns the same weight to each feature. However, there are significant differences in the aerodynamic performance of plane cascades composed of symmetric and asymmetric blade shapes, and there are also significant differences between the geometry of the plane cascades formed by different blade shapes and the experimental working conditions. There are large differences in geometric and working condition parameters in the features, which makes it difficult to accurately measure the similarity between different samples when there are fewer samples. For this problem, a metric learning for the multi-output Gaussian process regression method (ML_MOGPR) for aerodynamic performance prediction of the plane cascade is proposed. It shares parameters between multiple output Gaussian distributions during training and measures the similarity between input samples in a new embedding space to reduce bias and improve overall prediction accuracy. For the analysis of ML_MOGPR prediction results, the overall prediction accuracy is significantly improved compared with multi-output Gaussian process regression (MOGPR), backpropagation neural network (BPNN), and multi-task learning neural network (MTLNN). The experimental results show that ML_MOGPR is effective in predicting the performance of the plane cascade, and it can quickly and accurately make a preliminary estimate of the aerodynamic performance and meet the performance parameter estimation accuracy requirements in the early stage.https://www.mdpi.com/2073-8994/15/9/1692machine learningaerodynamic analysismultiple outputsGaussian process regressionmetric learning |
spellingShingle | Lin Liu Chunming Yang Honghui Xiang Jiazhe Lin Plane Cascade Aerodynamic Performance Prediction Based on Metric Learning for Multi-Output Gaussian Process Regression Symmetry machine learning aerodynamic analysis multiple outputs Gaussian process regression metric learning |
title | Plane Cascade Aerodynamic Performance Prediction Based on Metric Learning for Multi-Output Gaussian Process Regression |
title_full | Plane Cascade Aerodynamic Performance Prediction Based on Metric Learning for Multi-Output Gaussian Process Regression |
title_fullStr | Plane Cascade Aerodynamic Performance Prediction Based on Metric Learning for Multi-Output Gaussian Process Regression |
title_full_unstemmed | Plane Cascade Aerodynamic Performance Prediction Based on Metric Learning for Multi-Output Gaussian Process Regression |
title_short | Plane Cascade Aerodynamic Performance Prediction Based on Metric Learning for Multi-Output Gaussian Process Regression |
title_sort | plane cascade aerodynamic performance prediction based on metric learning for multi output gaussian process regression |
topic | machine learning aerodynamic analysis multiple outputs Gaussian process regression metric learning |
url | https://www.mdpi.com/2073-8994/15/9/1692 |
work_keys_str_mv | AT linliu planecascadeaerodynamicperformancepredictionbasedonmetriclearningformultioutputgaussianprocessregression AT chunmingyang planecascadeaerodynamicperformancepredictionbasedonmetriclearningformultioutputgaussianprocessregression AT honghuixiang planecascadeaerodynamicperformancepredictionbasedonmetriclearningformultioutputgaussianprocessregression AT jiazhelin planecascadeaerodynamicperformancepredictionbasedonmetriclearningformultioutputgaussianprocessregression |