Documents published in Scipedia

• ψ − flow: A Novel Physics-Constrained Architecture to Enforce Incompressibility and Boundary Conditions for Fast and Accurate Flow Predictions

  M. Cabral, B. Font, G. Weymouth

  ECCOMAS 2024.

  
  

  Abstract

  Deeplearning models have demonstrated remarkable capabilities at producing fast predictions of complex flow fields. However, incorporating known physics is essential to ensure that physical solutions can generalize to flow regimes not used for training. In this study, a formulation that, by construction, enforces flow incompressibility and respects the invariance of physical laws across different unit systems is introduced. We demonstrate that this approach can achieve performance improvements of up to 100 times compared to purely data-driven methods, all while maintaining fidelity to other crucial physical quantities. Moreover, we show that for canonical flow test cases, such a physics-constrained model can yield accurate results even with training datasets as small as a few hundred points and neural networks containing only a handful of neurons. It is also shown, however, that physics-constrained machine learning models are not silver bullets out of the box, and require careful consideration in their application and integration with other constraints. Specifically, this study addresses how a problem that is mathematically simple may not necessarily be straightforward in machine learning terms, and discusses ongoing efforts to bridge this gap. We conclude by discussing the place of physics-constrained machine learning models within a landscape primarily dominated by physics-informed approaches, in particular in the context of real-world problems where data and computational resources are often limited

  Abstract
  Deeplearning models have demonstrated remarkable capabilities at producing fast predictions of complex flow fields. However, incorporating known physics is essential to ensure [...]

  • 195
  •  read

• On the Usage of PANS for the CFD Simulation of Wind Turbines

  T. Gomes, G. Vaz, A. Maximiano, L. Sileo, V. Krasilnikov

  ECCOMAS 2024.

  
  

  Abstract

  With the rapid evolution of o↵shore wind energy, engineering tools are crucial to catalyze technological developments and increase their maturity, therefore leading to lower costs. Complex turbine-turbine interactions require a good knowledge of the physics of the flow on, around and down/upstream of each turbine, which can be provided using high-fidelity CFD simulations. Turbulence models play a critical role on this matter and an adequate balance between accuracy and computational e ort is necessary. While RANS approaches are quite e cient, LES should provide the most accurate result. Yet, even nowadays, LES blade-resolved simulations are still computationally prohibitive for industrial purposes. A middle-ground exists in SRS formulations, such as hybrid ones as DDES, or bridging ones such as PANS. In the present work emphasis is placed on PANS, since numerical and modelling errors can be studied and quantified independently, as opposite to other SRS approaches. Using as a benchmark the UNAFLOWwindturbine, it is found that traditional RANS and DDES turbulence formulations are able to predict integral forces, but partially fail in capturing wake mixing. Nevertheless, PANS, while enabling the user to select the ratio of turbulent quantities modelled, is not able to properly capture the integral forces due to premature separation in the blades. Several causes are discussed, including insu cient mesh refinement in the near-wall region and lack of turbulent content of the numerical inlet, preventing laminar to turbulent flow transition. Future work should focus on inlet synthetic turbulence generation, in line with existent literature, in order to improve the shortcomings faced in properly resolving the near-wall flow.

  Abstract
  With the rapid evolution of o↵shore wind energy, engineering tools are crucial to catalyze technological developments and increase their maturity, therefore leading [...]

  • 134
  •  read

• Cas Ametller Origen: cap a una cadena de subministrament centralitzada, circular i semiautomàtica

  A. Boar, E. Palau Pinyana

  4rceec (2025). Vol. La musculatura del sistema empresarial català, 133

  
  

  • 81
  •  read

• Research on similarity law of nonlinear shock response of ship plate frame structure under underwater explosion

  J. Wang, D. Shi, X. Yao, Z. Wang

  WCCM2024.

  
  

  Abstract

  The anti-explosion ability of ship grillage structure is an important index to evaluate the vitality of ships. Its model test is a low-cost and effective method to evaluate the vitality of ships and guide the design of ship anti impact structures. In view of the nonlinear and nonstationary process of underwater explosion damage to ship grillage, this paper breaks through the nonlinear effect of transient explosion impact that is not considered in the traditional scale model design, focuses on the one-dimensional nonlinear impact response of ship grillage structure, and carries out the characterization study of the similarity between model experiments and real ships. Considering that the vertical motion of the prototype and the model grillage structure in the model test obey the random walking model, the vertical impact response of the deck grillage is characterized as one-dimensional nonlinear non-stationary Brownian motion, which is described by Hurst index. Based on the classical similarity law, the similarity transformation relationship between the range R and the mean square deviation S is derived, and the Hurst index of the model and the prototype meets the equal relationship; Take a section of grillage structure on a real ship and conduct prototype, 1/2, 1/3, 1/4 and 1/5 one-dimensional nonlinear explosion impact scale simulation tests respectively. The numerical response results show obvious nonlinear characteristics, and the Hurst index of displacement, velocity and acceleration response of the model within the pulse width range is less than 5% compared with the prototype. According to the scale invariance of fractional Brownian motion, the similarity conversion relationship of multiple parameters (displacement, velocity, acceleration and mean square response) is obtained. With the mean square response as the characteristic parameter, the response value of the prototype is converted through this relationship, and compared with the model simulation results, the multi parameter response error under each scale ratio is less than 20%. It provides theoretical and technical support for conducting similar experiments on nonlinear response of underwater explosion shock of ships

  Abstract
  The anti-explosion ability of ship grillage structure is an important index to evaluate the vitality of ships. Its model test is a low-cost and effective method to evaluate [...]

  • 23
  •  read

• A new approach to combine physics-based and data-driven models using a localised trustworthiness metric

  L. Bogaerts, A. Persoons, M. Faes, D. Moens

  WCCM2024.

  
  

  Abstract

  Artificial Neural Networks (ANNs) can solve many (un)supervised learning tasks by virtue of the universal approximation theorem. In the context of on-line process control for manufacturing processes, ANNs are an ideal approach for e.g., on-line monitoring or prediction tasks. However, since they are trained on experimental input-output pairs, the governing physical relations are only implicitly included. This, for instance, can cause inaccuracies when extrapolating to out-of-sample data-points [1]. On the other hand, the numerical approximation of the governing physical laws via numerical methods holds strong potential for the accurate simulation of physical phenomena that occur during manufacturing processes. However, the corresponding computational effort is an impediment that arises with the need for numerous simulations [2]. This makes the application of such numerical schemes computationally intractable within an on-line monitoring context. As such, it is clear that ANNs and numerical simulation models have strong potential, but are fundamentally different models. However, their combination serves as a potentially efficient and accurate aggregated predictor, the so called grey-box model. Such grey-box model is based on highly efficient machine learning algorithms, the black-box member, and backed by validated data with respect to physics generated by the numerical model, the white-box member. A grey-box model capable of defining a trustworthy prediction, including a measurement of uncertainty on the estimator, remains challenging.

  Abstract
  Artificial Neural Networks (ANNs) can solve many (un)supervised learning tasks by virtue of the universal approximation theorem. In the context of on-line process control [...]

  • 49
  •  read

• Enhancing predictive modeling in reactor building dose distribution: A neural network-aided approach

  J. Liu, K. Koyamada, H. Natsukawa, S. Kamioka

  WCCM2024.

  
  

  Abstract

  Ensuring the safety of nuclear reactor decommissioning workers requires accurate, real-time predictions of radiation dose rates within reactor buildings. However, due to the complexity of these structures, such predictions are computationally intensive and time consuming. In this paper, we propose constructing a surrogate model using deep learning to predict radiation dose rates based on simulation results in a space containing a square pillar and a radiation source. The accuracy of the surrogate model's predictions was verified and visualized. Additionally, by applying the principle of superposition, we demonstrated that the distribution of radiation dose rates in spaces with a pillar and multiple radiation sources can be obtained by summing the surrogate model results for each radiation source. We also examined the application of the surrogate model to predicting radiation dose rates in spaces containing multiple square pillars and multiple radiation sources. This approach shows the potential for surrogate models to accurately and efficiently predict radiation dose rates in reactor buildings with complex structures and multiple radiation sources in real time.

  Abstract
  Ensuring the safety of nuclear reactor decommissioning workers requires accurate, real-time predictions of radiation dose rates within reactor buildings. However, due to the [...]

  • 53
  •  read

• Fuzzy statistics-aided inference in experimental design

  R. Dwornicka, A. Gądek-Moszczak, R. Ulewicz, N. Radek

  WCCM2024.

  
  

  Abstract

  Conducting research based on active influence on the examined object or process requires distinguishing an explained quantity, measured quantitatively, the possible changes of which will be considered as influencing it through a group of quantities considered as explanatory quantities. This approach implicitly postulates the existence of a cause-and-effect relationship between the explanatory quantities and the explained quantity. In practice, especially industrial practice, explanatory quantities are often called controlled factors. Knowledge of possible cause-and-effect relationships can be graded, from the most comfortable situation of the existence of appropriate binding equations and their exact solutions, through the existence of binding equations but without knowing the exact solutions, to the absence of such equations. While in the first case, experimental research serves to refine the results originally calculated for idealized models, in the second case, it is a necessary stage of identifying the parameters of the postulated model, and in the third case, it is a necessary stage of collecting data for which the simplest possible forecasting model will be constructed

  Abstract
  Conducting research based on active influence on the examined object or process requires distinguishing an explained quantity, measured quantitatively, the possible changes [...]

  • 140
  •  read

• Accurate solution of linear operator approximations using green's functions by a multi-level neural network approach

  Z. Aldirany, C. Bilodeau, R. Cottereau, M. Laforest

  WCCM2024.

  
  

  Abstract

  Lately, the approximation of operators for partial differential equations using deep learning has been extensively investigated. However, these deep learning approaches have limitations in terms of accuracy. In this work, we present a multi-level approach to accurately approximate linear operators using physics-informed Green operator networks. This method allows for the iterative reduction of the approximation errors through a sequence of operators, each targeting errors of increasing complexity at progressively smaller scales. Numerical examples for the one-dimensional Poisson problem will be presented to demonstrate the effectivenessof the proposed multi-level approach.

  Abstract
  Lately, the approximation of operators for partial differential equations using deep learning has been extensively investigated. However, these deep learning approaches have [...]

  • 55
  •  read

• Symbolic regression via neural networks

  J. Moehlis, N. Boddupalli, T. Matchen

  WCCM2024.

  
  

  Abstract

  Mathematical models allow researchers to understand, analyze, and predict the behavior of systems of physical, biological, and technological interest, and are required for many techniques from dynamical systems and control theory to be used. Unfortunately, it is often impossible to derive mathematical models from first principles, and in such cases system identification is a powerful tool which can be used to deduce models from observed data. Many existing system identification techniques require pre-specification of a dictionary of possible terms in a mathematical model, limiting their ability to give models with the nonlinearities which can arise for biological and other complex systems. We present a methodology which overcomes this limitation by dynamically generating the terms in a model with the necessary complexity and nonlinearity to accurately describe a system’s dynamics. This uses a multilayered, operation-based symbolic regression approach, with the capacity to learn combinations and compositions of operations by training artificial neural networks. Our approach provides a powerful alternative to genetic programming strategies for symbolic regression, and can exploit many of the attractive features of artificial neural networks such as a straightforward learning strategy.

  Abstract
  Mathematical models allow researchers to understand, analyze, and predict the behavior of systems of physical, biological, and technological interest, and are required for [...]

  • 39
  •  read

• Structural optimization through generative adversarial networks

  L. Pereira, L. Driemeier

  WCCM2024.

  
  

  Abstract

  The finite element method (FEM) is a well known approach to solve partial differential equations. It has important applications in structural engineering, such as in topology optimization (TO). TO involves, at each iteration, the solution of structural problems via FEM, which can add up to a high computational cost. Therefore, a line of research to accelerate TO emerged over the years focusing on machine learning (ML) approaches. Particularly, Artificial Neural Networks (ANNs) have been proposed to significantly speed-up the process by eliminating the iterative algorithm, which is intrinsic to TO. Since ANN is a supervised ML method, first a dataset is generated, containing finite element analysis (FEA) inputs, volume fraction, postprocessing, and final topologies. Then, with the Wasserstein Generative Adversarial Networks (WGANs) is trained on this dataset to map fields of physical quantities, such as the von Mises stress, to the final optimized structure. The final designs obtained via ML are quantitatively analyzed according to the metrics.

  Abstract
  The finite element method (FEM) is a well known approach to solve partial differential equations. It has important applications in structural engineering, such as in topology [...]

  • 94
  •  read