Cavitation Model Calibration Using Machine Learning Assisted Workflow
Conventional cavitation assessment methodology in industrial and scientific applications generally depends on cavitation models utilizing homogeneous mixture assumption. These models have been extensively assessed, modified and expanded to account for deficiencies of their predecessors. Unfortunatel...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-11-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/8/12/2107 |
| _version_ | 1797546808850776064 |
|---|---|
| author | Ante Sikirica Zoran Čarija Ivana Lučin Luka Grbčić Lado Kranjčević |
| author_facet | Ante Sikirica Zoran Čarija Ivana Lučin Luka Grbčić Lado Kranjčević |
| author_sort | Ante Sikirica |
| collection | DOAJ |
| description | Conventional cavitation assessment methodology in industrial and scientific applications generally depends on cavitation models utilizing homogeneous mixture assumption. These models have been extensively assessed, modified and expanded to account for deficiencies of their predecessors. Unfortunately, none of the proposed models can be classified as the universal solution for all engineering applications, with usage mainly directed by experience or general availability of the models. In this study we propose a workflow through which the empirical constants governing the phase change of the Kunz mixture cavitation model can be calibrated for a given application or a series of problems, with machine learning as a tool for parameter estimation. The proposed approach was validated on a three-dimensional propeller test case with results in excellent agreement for the case in question. Results for thrust and torque were within 2% with cavity extents differing by up to 20%. This is a significant improvement when compared to previously proposed parameters. Despite the lack of generalization due to the limited nature of the dataset on which the model was trained, the proposed parameters entail acceptable results for similar cases as well. The overall methodology is applicable to other problems as well and should lead to more accurate cavitation predictions. |
| first_indexed | 2024-03-10T14:35:26Z |
| format | Article |
| id | doaj.art-de979b4d47eb4ff0b773927b54151a4f |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-10T14:35:26Z |
| publishDate | 2020-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-de979b4d47eb4ff0b773927b54151a4f2023-11-20T22:17:53ZengMDPI AGMathematics2227-73902020-11-01812210710.3390/math8122107Cavitation Model Calibration Using Machine Learning Assisted WorkflowAnte Sikirica0Zoran Čarija1Ivana Lučin2Luka Grbčić3Lado Kranjčević4Center for Advanced Computing and Modelling, University of Rijeka, Radmile Matejčić 2, 51000 Rijeka, CroatiaCenter for Advanced Computing and Modelling, University of Rijeka, Radmile Matejčić 2, 51000 Rijeka, CroatiaCenter for Advanced Computing and Modelling, University of Rijeka, Radmile Matejčić 2, 51000 Rijeka, CroatiaCenter for Advanced Computing and Modelling, University of Rijeka, Radmile Matejčić 2, 51000 Rijeka, CroatiaCenter for Advanced Computing and Modelling, University of Rijeka, Radmile Matejčić 2, 51000 Rijeka, CroatiaConventional cavitation assessment methodology in industrial and scientific applications generally depends on cavitation models utilizing homogeneous mixture assumption. These models have been extensively assessed, modified and expanded to account for deficiencies of their predecessors. Unfortunately, none of the proposed models can be classified as the universal solution for all engineering applications, with usage mainly directed by experience or general availability of the models. In this study we propose a workflow through which the empirical constants governing the phase change of the Kunz mixture cavitation model can be calibrated for a given application or a series of problems, with machine learning as a tool for parameter estimation. The proposed approach was validated on a three-dimensional propeller test case with results in excellent agreement for the case in question. Results for thrust and torque were within 2% with cavity extents differing by up to 20%. This is a significant improvement when compared to previously proposed parameters. Despite the lack of generalization due to the limited nature of the dataset on which the model was trained, the proposed parameters entail acceptable results for similar cases as well. The overall methodology is applicable to other problems as well and should lead to more accurate cavitation predictions.https://www.mdpi.com/2227-7390/8/12/2107cavitation modelingKunz modelmarine propellerrandom forest |
| spellingShingle | Ante Sikirica Zoran Čarija Ivana Lučin Luka Grbčić Lado Kranjčević Cavitation Model Calibration Using Machine Learning Assisted Workflow Mathematics cavitation modeling Kunz model marine propeller random forest |
| title | Cavitation Model Calibration Using Machine Learning Assisted Workflow |
| title_full | Cavitation Model Calibration Using Machine Learning Assisted Workflow |
| title_fullStr | Cavitation Model Calibration Using Machine Learning Assisted Workflow |
| title_full_unstemmed | Cavitation Model Calibration Using Machine Learning Assisted Workflow |
| title_short | Cavitation Model Calibration Using Machine Learning Assisted Workflow |
| title_sort | cavitation model calibration using machine learning assisted workflow |
| topic | cavitation modeling Kunz model marine propeller random forest |
| url | https://www.mdpi.com/2227-7390/8/12/2107 |
| work_keys_str_mv | AT antesikirica cavitationmodelcalibrationusingmachinelearningassistedworkflow AT zorancarija cavitationmodelcalibrationusingmachinelearningassistedworkflow AT ivanalucin cavitationmodelcalibrationusingmachinelearningassistedworkflow AT lukagrbcic cavitationmodelcalibrationusingmachinelearningassistedworkflow AT ladokranjcevic cavitationmodelcalibrationusingmachinelearningassistedworkflow |