Modeling radial turbine performance under pulsating flow by machine learning method

This work presents the development and application of a machine learning model to predict the unsteady performance of a turbocharger radial turbine subject to on-engine pulsating flow conditions. The model proposed, based on a fully connected neural network, predicts the instantaneous turbine torque...

Full description

Bibliographic Details
Main Authors: Roberto Mosca, Marco Laudato, Mihai Mihaescu
Format: Article
Language:English
Published: Elsevier 2022-12-01
Series:Energy Conversion and Management: X
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2590174522001234
_version_ 1811190228545699840
author Roberto Mosca
Marco Laudato
Mihai Mihaescu
author_facet Roberto Mosca
Marco Laudato
Mihai Mihaescu
author_sort Roberto Mosca
collection DOAJ
description This work presents the development and application of a machine learning model to predict the unsteady performance of a turbocharger radial turbine subject to on-engine pulsating flow conditions. The model proposed, based on a fully connected neural network, predicts the instantaneous turbine torque and circumferentially-averaged relative inflow angle when given, as only inputs, the total pressure and temperature pulses and the time derivative of the total pressure pulse upstream of the turbine.The training data set for the model is obtained from an experimentally-validated Reynolds-averaged Navier–Stokes model and consists of various operating conditions characterized by different pulse amplitudes and frequencies. Heat transfer effects are neglected by the use of adiabatic boundary conditions while the rotational speed of the rotor is otherwise maintained fixed. Based on the results obtained, the model is shown capable of accurately predicting the turbine torque and local properties of the flow, such as the relative inflow angle, with a high degree of accuracy (coefficient of determination larger than 0.98). At first, the model is tested for both interpolation and extrapolation conditions. Given a training data set constituted by only three pulses characterized by different amplitudes, the model accurately predicts the turbine performance both for conditions inside and outside the range of amplitudes of the training data set. Lastly, the model is trained with a larger data set, including both variations of the pulse amplitude and frequency, in order to predict the performance of the turbine subject to a more general pulse shape. The error indicators show an improvement with respect to the extrapolation case due to the larger size of the training data set, showing also a great capability of the model to predict the unsteady performance of the turbine for a more general pulse shape. The model represents a fast and efficient approach for predicting the unsteady turbine performance as compared to more complex experimental set-ups and time-consuming 3D numerical simulations and a valid alternative to the more common 0D-1D models.
first_indexed 2024-04-11T14:46:44Z
format Article
id doaj.art-0b8ac5354f8c4cfbb417758c7b924160
institution Directory Open Access Journal
issn 2590-1745
language English
last_indexed 2024-04-11T14:46:44Z
publishDate 2022-12-01
publisher Elsevier
record_format Article
series Energy Conversion and Management: X
spelling doaj.art-0b8ac5354f8c4cfbb417758c7b9241602022-12-22T04:17:35ZengElsevierEnergy Conversion and Management: X2590-17452022-12-0116100300Modeling radial turbine performance under pulsating flow by machine learning methodRoberto Mosca0Marco Laudato1Mihai Mihaescu2Competence Center for Gas Exchange (CCGEx), KTH Royal Institute of Technology, SE-10044 Stockholm, Sweden; Department of Engineering Mechanics, KTH Royal Institute of Technology, SE-10044 Stockholm, Sweden; Corresponding author at: Competence Center for Gas Exchange (CCGEx), SSE-10044 Stockholm, Sweden.Department of Engineering Mechanics, KTH Royal Institute of Technology, SE-10044 Stockholm, SwedenCompetence Center for Gas Exchange (CCGEx), KTH Royal Institute of Technology, SE-10044 Stockholm, Sweden; Department of Engineering Mechanics, KTH Royal Institute of Technology, SE-10044 Stockholm, SwedenThis work presents the development and application of a machine learning model to predict the unsteady performance of a turbocharger radial turbine subject to on-engine pulsating flow conditions. The model proposed, based on a fully connected neural network, predicts the instantaneous turbine torque and circumferentially-averaged relative inflow angle when given, as only inputs, the total pressure and temperature pulses and the time derivative of the total pressure pulse upstream of the turbine.The training data set for the model is obtained from an experimentally-validated Reynolds-averaged Navier–Stokes model and consists of various operating conditions characterized by different pulse amplitudes and frequencies. Heat transfer effects are neglected by the use of adiabatic boundary conditions while the rotational speed of the rotor is otherwise maintained fixed. Based on the results obtained, the model is shown capable of accurately predicting the turbine torque and local properties of the flow, such as the relative inflow angle, with a high degree of accuracy (coefficient of determination larger than 0.98). At first, the model is tested for both interpolation and extrapolation conditions. Given a training data set constituted by only three pulses characterized by different amplitudes, the model accurately predicts the turbine performance both for conditions inside and outside the range of amplitudes of the training data set. Lastly, the model is trained with a larger data set, including both variations of the pulse amplitude and frequency, in order to predict the performance of the turbine subject to a more general pulse shape. The error indicators show an improvement with respect to the extrapolation case due to the larger size of the training data set, showing also a great capability of the model to predict the unsteady performance of the turbine for a more general pulse shape. The model represents a fast and efficient approach for predicting the unsteady turbine performance as compared to more complex experimental set-ups and time-consuming 3D numerical simulations and a valid alternative to the more common 0D-1D models.http://www.sciencedirect.com/science/article/pii/S2590174522001234Machine learningTurbomachineryRadial turbinePulsating flow
spellingShingle Roberto Mosca
Marco Laudato
Mihai Mihaescu
Modeling radial turbine performance under pulsating flow by machine learning method
Energy Conversion and Management: X
Machine learning
Turbomachinery
Radial turbine
Pulsating flow
title Modeling radial turbine performance under pulsating flow by machine learning method
title_full Modeling radial turbine performance under pulsating flow by machine learning method
title_fullStr Modeling radial turbine performance under pulsating flow by machine learning method
title_full_unstemmed Modeling radial turbine performance under pulsating flow by machine learning method
title_short Modeling radial turbine performance under pulsating flow by machine learning method
title_sort modeling radial turbine performance under pulsating flow by machine learning method
topic Machine learning
Turbomachinery
Radial turbine
Pulsating flow
url http://www.sciencedirect.com/science/article/pii/S2590174522001234
work_keys_str_mv AT robertomosca modelingradialturbineperformanceunderpulsatingflowbymachinelearningmethod
AT marcolaudato modelingradialturbineperformanceunderpulsatingflowbymachinelearningmethod
AT mihaimihaescu modelingradialturbineperformanceunderpulsatingflowbymachinelearningmethod