Andrea Serani

Andrea Serani
Italian National Research Council | CNR · Institute of Marine Engineering INM

Ph.D. in Mechanical and Industrial Engineering

About

105
Publications
29,879
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
894
Citations
Introduction
His main areas of research interest are dimensionality reduction, machine learning, and optimization algorithms for application in computational fluid dynamics. He has been member of several NATO Science and Technology Organisation, Applied Vehicle Technology, Research Task Groups on deterministic and stochastic design optimization of military vehicles. He is authors of more than 50 papers in international journals and conference proceedings.
Additional affiliations
April 2018 - November 2019
Italian National Research Council
Position
  • PostDoc Position
January 2017 - March 2018
Italian National Research Council
Position
  • PostDoc Position
January 2016 - December 2016
Italian National Research Council
Position
  • Research Associate
Education
January 2013 - June 2016
Università Degli Studi Roma Tre
Field of study
  • Mechanical and Industrial Engineering
January 2010 - February 2012
Università Degli Studi Roma Tre
Field of study
  • Aeronautical Engineering
October 2004 - December 2009
Università Degli Studi Roma Tre
Field of study
  • Mechanical Engineering

Publications

Publications (105)
Article
Simulation-based design optimization methods integrate computer simulations, design modification tools, and optimization algorithms. In hydrodynamic applications, often ob- jective functions are computationally expensive and noisy, their derivatives are not directly provided, and the existence of local minima cannot be excluded a priori, which moti...
Article
Deterministic optimization algorithms are very attractive when the objective function is computationally expensive and therefore the statistical analysis of the optimization outcomes becomes too expensive. Among deterministic methods, deterministic particle swarm optimization (DPSO) has several attractive characteristics such as the simplicity of t...
Chapter
Full-text available
A novel nature-inspired, deterministic, global, and derivative-free optimization method, namely the dolphin pod optimization (DPO), is presented for solving simulation-based design optimization problems with costly objective functions. DPO is formulated for unconstrained single-objective minimization and based on a simplified social model of a dolp...
Article
Full-text available
The paper shows how cost-reduction methods can be synergistically combined to enable high-fidelity hull-form optimization under stochastic conditions. Specifically, a multi-objective hull-form optimization is presented, where (a) physics-informed design-space dimensionality reduction, (b) adaptive metamodeling, (c) uncertainty quantification (UQ) m...
Article
Computational fluid dynamics (CFD) simulations and stochastic validation of free-running 5415M in irregular stern-quartering sea state 7 and Froude number 0.33 are presented. Unsteady Reynolds-averaged Navier-Stokes (URANS) computations are validated against experimental fluid dynamics (EFD) tests. EFD static stability, forward speed, wave directio...
Conference Paper
Full-text available
Two data-driven hybrid machine learning architectures are presented to improve knowledge and forecasting capabilities for ships operating in waves. These are based on methodological extensions of both dynamic mode decomposition (DMD) and recurrent-type neural network (RNN). Namely, a full-rank DMD approach is augmented by the use of time derivative...
Conference Paper
Full-text available
Despite recent advances in machine learning, simulation-driven design optimization using high-fidelity simulations may still be prohibitively expensive for practical applications. This paper investigates improvements in multi-fidelity surrogate-based hydrodynamic optimization , which are intended to make the process faster and more efficient. Speci...
Conference Paper
The efficiency of simulation-driven design optimization based on surrogate models, depends strongly on the suitability of the surrogate model for the simulation data on which it is based. We investigate adaptive surrogate modelling methods that maximize the efficiency and the robustness for any optimization problem. Specific techniques include: ada...
Article
In this work, we propose and test a method to expedite Global Sensitivity Analysis (GSA) in the context of shape optimisation of free-form shapes. To leverage the computational burden that is likely to occur in engineering problems, we construct a Shape-Signature-Vector (SSV) and propose to use it as a substitute for physics. SSV is composed of sha...
Article
Full-text available
In shape optimisation problems, subspaces generated with conventional dimension reduction approaches often fail to extract the intrinsic geometric features of the shape that would allow the exploration of diverse but valid candidate solutions. More importantly, they also lack incorporation of any notion of physics against which shape is optimised....
Preprint
Full-text available
The paper presents a collection of analytical benchmark problems specifically selected to provide a set of stress tests for the assessment of multifidelity optimization methods. In addition, the paper discusses a comprehensive ensemble of metrics and criteria recommended for the rigorous and meaningful assessment of the performance of multifidelity...
Preprint
Methodologies for reducing the design-space dimensionality in shape optimization have been recently developed based on unsupervised machine learning methods. These methods provide reduced dimensionality representations of the design space, capable of maintaining a certain degree of the original design variability. Nevertheless, they usually do not...
Article
Full-text available
This paper presents a comparison of two multi-fidelity methods for the forward uncertainty quantification of a naval engineering problem. Specifically, we consider the problem of quantifying the uncertainty of the hydrodynamic resistance of a roll-on/roll-off passenger ferry advancing in calm water and subject to two operational uncertainties (ship...
Preprint
Full-text available
A multi-fidelity (MF) active learning method is presented for design optimization problems characterized by noisy evaluations of the performance metrics. Namely, a generalized MF surrogate model is used for design-space exploration, exploiting an arbitrary number of hierarchical fidelity levels, i.e., performance evaluations coming from different m...
Article
Full-text available
The paper presents a multi-fidelity extension of a local line-search-based derivative-free algorithm for nonsmooth constrained optimization (MF-CS-DFN). The method is intended for use in the simulation-driven design optimization (SDDO) context, where multi-fidelity computations are used to evaluate the objective function. The proposed algorithm sta...
Conference Paper
Full-text available
In this work, we proposed a computationally inexpensive Parametric Sensitivity Analysis (PSA), which, to evaluate parameters' sensitivity, substitutes design's physical quantities by the geometric ones, such as geometric moments and their invariants. Physical quantities rely strongly on design's geometry, and the evaluation of geometric properties...
Conference Paper
Full-text available
Despite the increased computational resources, the simulation-based design optimization (SBDO) procedure can be very expensive from a computational viewpoint, especially if high-fidelity solvers are required. Multi-fidelity metamodels have been successfully applied to reduce the computational cost of the SBDO process. In this context, the paper pre...
Preprint
Full-text available
Despite the increased computational resources, the simulation-based design optimization (SBDO) procedure can be very expensive from a computational viewpoint, especially if high-fidelity solvers are required. Multi-fidelity metamodels have been successfully applied to reduce the computational cost of the SBDO process. In this context, the paper pre...
Chapter
In shape optimization of complex industrial products (such as aerial vehicles or ship hulls), there exists an inherent similarity between global optimization (GO) and uncertainty quantification (UQ): They rely on an extensive exploration of the design and operational spaces, respectively; often, they need local refinements to ensure accurate identi...
Conference Paper
Full-text available
A multi-fidelity Gaussian process (MF-GP) is presented for the forward uncertainty quantification (UQ) of the performance of an autonomous surface vehicle (ASV) subject to uncertain operating conditions. The ASV is a shallow water autonomous multipurpose platform (SWAMP), designed for the acquisition of the environmental parameters in the extremely...
Conference Paper
Full-text available
The prediction capability of recurrent-type neural networks is investigated for realtime short-term prediction (nowcasting) of ship motions in high sea state. Specifically, the performance of recurrent neural networks, long-short term memory, and gated recurrent units models are assessed and compared using a data set coming from computational fluid...
Conference Paper
Full-text available
A data-driven and equation-free approach is proposed and discussed to model ships maneuvers in waves, based on the dynamic mode decomposition (DMD). DMD is a dimensionality-reduction/reduced-order modeling method, which provides a linear finite-dimensional representation of a possibly nonlinear system dynamics by means of a set of modes with associ...
Conference Paper
Full-text available
The performance of surrogate-based optimization is highly affected by how the surrogate training set is defined. This is especially true for multi-fidelity surrogate models, where different training sets exist for each fidelity. Adaptive sampling methods have been developed to improve the fitting capabilities of surrogate models, avoiding to define...
Conference Paper
The performance of surrogate-based optimization are highly affected by how the surrogate training set is defined. This is especially true for multi-fidelity surrogate models, where different training sets exist for each fidelity. Adaptive sampling methods have been developed to improve the fitting capabilities of surrogate models, avoiding to defin...
Preprint
Full-text available
This paper presents a comparison of two multi-fidelity methods for the forward uncertainty quantification of a naval engineering problem. Specifically, we consider the problem of quantifying the uncertainty of the hydrodynamic resistance of a roll-on/roll-off passengers ferry advancing in calm water and subject to two operational uncertainties (shi...
Preprint
Full-text available
The prediction capability of recurrent-type neural networks is investigated for real-time short-term prediction (nowcasting) of ship motions in high sea state. Specifically, the performance of recurrent neural networks, long-short term memory, and gated recurrent units models are assessed and compared using a data set coming from computational flui...
Preprint
Full-text available
A data-driven and equation-free approach is proposed and discussed to model ships maneuvers in waves, based on the dynamic mode decomposition (DMD). DMD is a dimensionality-reduction/reduced-order modeling method, which provides a linear finite-dimensional representation of a possibly nonlinear system dynamics by means of a set of modes with associ...
Article
Full-text available
This paper describes a class of novel initializations in Deterministic Particle Swarm Optimization (DPSO) for approximately solving costly unconstrained global optimization problems. The initializations are based on choosing specific dense initial positions and velocities for particles. These choices tend to induce in some sense orthogonality of pa...
Conference Paper
Full-text available
The paper presents a multi-fidelity coordinate-search derivative-free algorithm for non-smooth constrained optimization (MF-CS-DFN), in the context of simulation-based design optimization (SBDO). The objective of the work is the development of an optimization algorithm able to improve the convergence speed of the SBDO process. The proposed algorith...
Conference Paper
Full-text available
High-dimensional parametric design problems cause optimisers and physics simulations to suffer from the curse-of-dimensionality, resulting in high computational cost. In this work, to release this computational burden, we adopted a two-step feature-to-feature learning methodology to discover a lower-dimensional latent space, based on the combinatio...
Article
Full-text available
In this work, we propose and test a method to expedite Global Sensitivity Analysis (GSA) in the context of shape optimisation of free-form shapes. To leverage the computational burden that is likely to occur in engineering problems, we construct a Shape-Signature-Vector (SSV) and propose to use it as a substitute for physics. SSV is composed of sha...
Conference Paper
Full-text available
In shape optimization of complex industrial products (such as aerial vehicles or ship hulls), there exists an inherent similarity between global optimization (GO) and uncertainty quantification (UQ): they rely on an extensive exploration of the design and operational spaces, respectively; often, they need local refinements to ensure accurate identi...
Conference Paper
Full-text available
Spatial and snapshot clustering approaches are presented and discussed for particle image velocimetry (PIV) data of high-Reynolds number uniform and buoyant jets and 4-and 7-bladed propeller wakes respectively. Data clustering is based on the k-means algorithm, along with the identification of the optimal number of clusters based on three metrics,...
Conference Paper
Full-text available
The focus of the present paper is the assessment of deterministic and stochastic methods for the prediction of large amplitude ship motions in heavy weather, including comparison with experimental fluid dynamics (EFD) data. The research was conducted under the auspices of NATO AVT-280 on "Evaluation of Prediction Methods for Ship Performance in Hea...
Conference Paper
Full-text available
A generalized multi-fidelity (MF) metamodel of CFD (computational fluid dynamics) computations is presented for design-and operational-space exploration, based on machine learning from an arbitrary number of fidelity levels. The method is based on stochastic radial basis functions (RBF) with least squares regression and in-the-loop optimization of...
Conference Paper
Full-text available
An adaptive N-fidelity approach to metamodeling from noisy data is presented for uncertainty quantification and design-space exploration. Computational fluid dynamics (CFD) simulations with different numerical accuracy provides meta-model training sets affected by unavoidable numerical noise. The N-fidelity approximation is built by an additive cor...
Conference Paper
Full-text available
The focus of the present work is the assessment of stochastic validation methods for the prediction of large amplitude ship motions in heavy weather, including comparison with experimental fluid dynamics (EFD) data. Stochastic validation is assessed for course keeping of a naval destroyer hull form by free-running CFD (URANS) simulations in irregul...
Conference Paper
Full-text available
This extended abstract is a summary of [4], where a comparison of two methods for the forward uncertainty quantification (UQ) of complex industrial problems is presented. Specifically, the performance of Multi-Index Stochastic Colloca-tion (MISC) and adaptive multi-fidelity Stochastic Radial Basis Functions (SRBF) surrogates is assessed for the UQ...
Conference Paper
This paper overviews the efforts of a technical team within the NATO Applied Vehicle Technology Panel to apply multi-fidelity methods to vehicle design. The objectives of the team are to understand the potential benefits of multi-fidelity methods in vehicle design and to assess the relative strengths and weaknesses of different multi-fidelity metho...
Conference Paper
Full-text available
An adaptive-fidelity approach to metamodeling from noisy data is presented for design-space exploration and design optimization. Computational fluid dynamics (CFD) simulations with different numerical accuracy (spatial discretization) provides metamodel training sets affected by unavoidable numerical noise. The-fidelity approximation is built by an...
Conference Paper
Full-text available
This paper presents a comparison of two methods for the forward uncertainty quantification (UQ) of complex industrial problems. Specifically, the performance of Multi-Index Stochastic Collocation (MISC) and adaptive multi-fidelity Stochastic Radial Basis Functions (SRBF) surrogates is assessed for the UQ of a roll-on/roll-off passengers ferry advan...
Conference Paper
Full-text available
The study presents the statistical assessment and validation of ship response in heavy weather using the moving block bootstrap method. Computational fluid dynamic results are validated versus experimental fluid dynamics data. The test case is a free-running model of a naval destroyer in heavy weather, namely the 5415M model in irregular stern-quar...
Preprint
Full-text available
This paper presents a comparison of two methods for the forward uncertainty quantification (UQ) of complex industrial problems. Specifically, the performance of Multi-Index Stochastic Collocation (MISC) and adaptive multi-fidelity Stochastic Radial Basis Functions (SRBF) surrogates is assessed for the UQ of a roll-on/roll-off passengers ferry advan...
Article
Full-text available
The paper presents a multi-objective derivative-free and deterministic global/local hybrid algorithm for the efficient and effective solution of simulation-based design optimization (SBDO) problems. The objective is to show how the hybridization of two multi-objective derivative-free global and local algorithms achieves better performance than the...
Article
A method based on the Karhunen-Loève expansion (KLE) is formulated for the assessment of arbitrary design spaces in shape optimization, assessing the shape modification variability and providing the definition of a reduced-dimensionality global model of the shape modification vector. The method is based on the concept of geometric variance and does...
Article
The article presents an exploratory study on the application to ship hydrodynamics of unsupervised nonlinear design-space dimensionality reduction methods, assessing the interaction of shape and physical parameters. Nonlinear extensions of the principal component analysis (PCA) are applied, namely local PCA (LPCA) and kernel PCA (KPCA). An artifici...
Article
The paper presents a study on four adaptive sampling methods of a multi-fidelity (MF) metamodel, based on stochastic radial basis functions (RBF), for global design optimisation based on expensive CFD computer simulations and adaptive grid refinement. The MF metamodel is built as the sum of a low-fidelity-trained metamodel and an error metamodel, b...
Conference Paper
Full-text available
A hydrodynamic design procedure is presented, combining multi-objective sampling, metamodeling, and optimization. A design study of a flapped surface for a passenger hydrofoil is discussed. Hydrodynamics, stability and control are optimized with focus on maximum lift, minimum drag, and maneuverability/stability performance during takeoff and turnin...
Conference Paper
Full-text available
An adaptive N-fidelity (NF) metamodel is presented for the solution of simulation-based design optimization and uncertainty quantification problems. A multi-fidelity approximation is built by an additive correction of a low-fidelity metamodel with metamodels of hierarchical differences (errors) between higher-fidelity levels. The metamodel is based...
Conference Paper
Full-text available
A hydrodynamic design procedure is presented, combining multi-objective sampling, metamodeling, and optimisation. A design study of a flapped surface for a passenger hydrofoil is discussed. Hydrodynamics, stability and control are optimised with focus on maximum lift, minimum drag, and manoeuvrability/stability performance during takeoff and turnin...