Predicting the cavitating marine propeller noise at design stage: A deep learning based approach

Miglianti, Leonardo; Cipollini, Francesca; Oneto, Luca; Tani, Giorgio; Gaggero, Stefano; Coraddu, Andrea; Viviani, Michele

doi:10.1016/j.oceaneng.2020.107481

Cited by 37 publications

(16 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The research presented here can potentially impact the aerospace ad ocean engineering industry by optimally morphing the shape design of aerofoils and hydrofoils. The urgent need for online shape optimization of marine propellers to deal with cavitation and underwater radiated noise is already documented [37,38,39]. Thus, the present CNN-based shape optimization approach can be a promising avenue for real-time marine propeller optimization over a spectrum of hydrofoil shapes and underwater flow conditions.…”

Section: Contributionsmentioning

confidence: 93%

A parametric level set method with convolutional encoder-decoder network for shape optimization with fluid flow

Mallik¹,

Jaiman²,

Jelovica³

2023

Preprint

View full text Add to dashboard Cite

In this article, we present a new data-driven shape optimization approach for implicit hydrofoil morphing via a polynomial perturbation of parametric level set representations. Without introducing any change in topology, the hydrofoil morphing is achieved by six shape design variables associated with the amplitude and shape of the perturbed displacements. The proposed approach has three to four times lower design variables than shape optimization via free-form deformation techniques and almost two orders lower design variables compared to topology optimization via traditional parametric level sets. Using the fixed uniform Cartesian level set mesh, we also integrate deep convolutional encoder-decoder networks as a surrogate of high-fidelity Reynolds-averaged Navier-Stokes (RANS) simulations for learning the flow field around morphed hydrofoil shapes. We show that an efficient shape representation via parametric level sets can enable online convolutional encoderdecoder application for the shape optimization of hydrofoils. The generalized flow field prediction of the convolutional encoder-decoder is demonstrated by the mean structural similarity index measure (SSIM) of 0.985 and a minimum SSIM of 0.95 for the predicted solutions compared to the true solutions for

show abstract

Section: Contributionsmentioning

confidence: 93%

A parametric level set method with convolutional encoder-decoder network for shape optimization with fluid flow

Mallik¹,

Jaiman²,

Jelovica³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The author compared the predicted value of laminar diffusion flame and swirling stable flame with the real three-dimensional image using a deep learning method (CNN-LSTM), and their predictions well agreed with the three-dimensional image obtained by reconstructing the two-dimensional experimental image [34]. The author took advantage of data-driven method and combined the datasets obtained in a cavitation tunnel to predict the cavitation marine propeller generated noise spectra at the design-exploiting stage [35]. The author proposed a data-driven model to predict the velocity field of a scramjet isolator through the pressure field using a CNN and a super-resolution CNN [36].…”

Section: Introductionmentioning

confidence: 90%

“…Deep learning methods have been employed in rotating machinery [35,48,49]. Most of them use a single neural network, such as CNN and long and short-term memory network (LSTM).…”

Section: Hybrid Deep Learning Model Cnn-bi-lstmmentioning

confidence: 99%

Prediction of Cavitation Performance over the Pump-Jet Propulsor Using Computational Fluid Dynamics and Hybrid Deep Learning Method

Qiu

Huang

Pan

2022

JMSE

View full text Add to dashboard Cite

The cavitation performance of an oblique flow field is different from that under a pure axial flow field. This study analyzed the hydrodynamic performance, bearing force, and tip clearance flow field under different rotating speeds and different cavitation numbers in an oblique flow field. Furthermore, this study proposed a hybrid deep learning model CNN-Bi-LSTM to quickly and accurately predict the bearing force of a pump-jet propulsor (PJP), which will solve the problem of time-consuming calculation and consumption of considerable computing resources in traditional computational fluid dynamics. The Shear–Stress–Transport model and Reynolds-averaged Navier–Stokes equations were utilized to procure the training and testing datasets. The training and testing datasets were reasonably divided in the ratio of 7:3. The results show that the propulsion efficiency decreased more obviously under higher rotating speed conditions, with a maximum decrease of up to 13.59%. The small cavitation numbers 1.4721 and high oblique angle significantly impacted the efficiency reduction; the maximum efficiency loss exceeded 20%. Thus, a small cavitation number 1.4721 is extremely detrimental to the propulsion efficiency of the PJP due to the large cavitation area. Moreover, the intensity of the tip clearance vortex continuously increased with the rotating speed. The CNN-Bi-LSTM deep model successfully predicted the phase difference and trend change of the propulsor bearing force under different conditions. The prediction difference was large at the crest and trough of the bearing force, but it is within the acceptable error range.

show abstract

“…Among PMs, Mean Value Engine Models (MVEMs) are a common choice when low computational effort is required (Maroteaux and Saad 2015; Guzzella and Onder 2009;He and Lin 2007;Lee et al 2013;Miglianti et al 2020Miglianti et al , 2019. MVEMs are approximate first-principle models that adequately predict engine performance parameters, and are prevalent in applications in which the engine is considered as just one component of a wider system, or for control strategies development (Malkhede et al 2005;Guan et al 2014;Theotokatos 2010;Grimmelius et al 2010;Theotokatos 2008;Nikzadfar and Shamekhi 2015;Geertsma et al 2017;Theotokatos et al 2018;Geertsma et al 2018;Guzzella and Onder 2009).…”

Section: Physical Modelsmentioning

confidence: 99%

“…HMs are a quite recent modelling approach, especially in the maritime field, and just very few works showed the advantages of a hybrid approach, with respect to pure PMs and DDMs (Coraddu et al 2021a(Coraddu et al , 2018Miglianti et al 2019Miglianti et al , 2020. For instance, in Coraddu et al (2017) the authors show that it is possible to effectively predict fuel consumption with HMs.…”

Section: Hybrid Modelsmentioning

confidence: 99%

Physical and Data-Driven Models Hybridisation for Modelling the Dynamic State of a Four-Stroke Marine Diesel Engine

Coraddu

Kalikatzarakis

Theotokatos

et al. 2021

Energy, Environment, and Sustainability

Self Cite

View full text Add to dashboard Cite

Accurate, reliable, and computationally inexpensive models of the dynamic state of combustion engines are a fundamental tool to investigate new engine designs, develop optimal control strategies, and monitor their performance. The use of those models would allow to improve the engine cost-efficiency trade-off, operational robustness, and environmental impact. To address this challenge, two state-of-the-art alternatives in literature exist. The first one is to develop high fidelity physical models (e.g., mean value engine, zero-dimensional, and one-dimensional models) exploiting the physical principles that regulate engine behaviour. The second one is to exploit historical data produced by the modern engine control and automation systems or by high-fidelity simulators to feed data-driven models (e.g., shallow and deep machine learning models) able to learn an accurate digital twin of the system without any prior knowledge. The main issues of the former approach are its complexity and the high (in some case prohibitive) computational require-

show abstract

Predicting the cavitating marine propeller noise at design stage: A deep learning based approach

Abstract: carried out with a Boundary Element Method. The performance of the proposed approaches are analysed considering different scenarios and different definitions of the input and output variable used during the modelisation.

Cited by 37 publications

References 43 publications

A parametric level set method with convolutional encoder-decoder network for shape optimization with fluid flow

A parametric level set method with convolutional encoder-decoder network for shape optimization with fluid flow

Prediction of Cavitation Performance over the Pump-Jet Propulsor Using Computational Fluid Dynamics and Hybrid Deep Learning Method

Physical and Data-Driven Models Hybridisation for Modelling the Dynamic State of a Four-Stroke Marine Diesel Engine

Contact Info

Product

Resources

About