Simulation of Wave Propagation
http://hdl.handle.net/20.500.11824/8
2023-12-09T18:43:38ZBridge damage identification under varying environmental and operational conditions combining Deep Learning and numerical simulations
http://hdl.handle.net/20.500.11824/1703
Bridge damage identification under varying environmental and operational conditions combining Deep Learning and numerical simulations
Fernandez-Navamuel, A.; Pardo, D.; Garcia-Sanchez, D.; Zamora-Sánchez, D.; Magalhães, F.; Omella, Ángel J.
This work proposes a novel supervised learning approach to identify damage in operating bridge structures. We propose a method to introduce the effect of environmental and operational conditions into the synthetic damage scenarios employed for training a Deep Neural Network, which is applicable to large-scale complex structures. We apply a clustering technique based on Gaussian Mixtures to effectively select Q representative measurements from a long-term monitoring dataset. We employ these measurements as the target response to solve various Finite Element Model Updating problems before generating different damage scenarios. The synthetic and experimental measurements feed two Deep Neural Networks that assess the structural health condition in terms of damage severity and location. We demonstrate the applicability of the proposed method with a real full-scale case study: the Infante Dom Henrique bridge in Porto. A comparative study reveals that neglecting different environmental and operational conditions during training detracts the damage identification task. By contrast, our method provides successful results during a synthetic validation.
2023-10-01T00:00:00ZMemory-Based Monte Carlo Integration for Solving Partial Differential Equations Using Neural Networks
http://hdl.handle.net/20.500.11824/1697
Memory-Based Monte Carlo Integration for Solving Partial Differential Equations Using Neural Networks
Uriarte, C.; Taylor, J.M.; Pardo, D.; Rodríguez, O.A.; Vega
Monte Carlo integration is a widely used quadrature rule to solve Partial Differential Equations with neural networks due to its ability to guarantee overfitting-free solutions and high-dimensional scalability. However, this stochastic method produces noisy losses and gradients during training, which hinders a proper convergence diagnosis. Typically, this is overcome using an immense (disproportionate) amount of integration points, which deteriorates the training performance. This work proposes a memory-based Monte Carlo integration method that produces accurate integral approximations without requiring the high computational costs of processing large samples during training.
2023-01-01T00:00:00ZConstant probe orientation for fast contact-based inspection of 3D free-form surfaces using (3+2)-axis inspection machines
http://hdl.handle.net/20.500.11824/1694
Constant probe orientation for fast contact-based inspection of 3D free-form surfaces using (3+2)-axis inspection machines
Sliusarenko, O.; Gomez Escudero, G.; Gonzalez, H.; Calleja, A.; Barton, M.; Ortega, N.; López de Lacalle, L.N.
A new probe optimization method for contact based (3+2)-axis inspection machines is proposed. Given an inspection path of a stylus on a free-form surface, an optimal orientation of the stylus is computed such that (i) the inclination angle of the stylus is within a given angular range with respect to the surface normal, (ii) the motion of the stylus is globally collision free, and (iii) the stylus remains constant in the coordinate system of the measuring machine. The last condition guarantees that the inspection motion requires only the involvement of the three translational axes of the measuring machine. The numerical simulations were validated through physical experiments on a testcase of a tooth of a bevel gear due to the surface complexity and probe accessibility. This optimized method was compared to 3-axis and 5-axis inspection strategies, showing that the fixed (3+2)-axis stylus returns more accurate inspection results compared to the traditional 3-axis approach and similar to 5-axis approach.
2023-01-01T00:00:00ZSolving Boundary Value Problems Via the Nyström Method Using Spline Gauss Rules
http://hdl.handle.net/20.500.11824/1693
Solving Boundary Value Problems Via the Nyström Method Using Spline Gauss Rules
Hashemian, A.; Sliusarenko, H.; Remogna, S.; Barrera, D.; Barton, M.
We propose to use spline Gauss quadrature rules for solving boundary value problems (BVPs) using the Nyström method. When solving BVPs, one converts the corresponding partial differential equation inside a domain into the Fredholm integral equation of the second kind on the boundary in the sense of boundary integral equation (BIE). The Fredholm integral equation is then solved using the Nyström method, which involves a use of a particular quadrature rule, thus, converting the BIE problem to a linear system. We demonstrate this concept on the 2D Laplace problem over domains with smooth boundary as well as domains containing corners. We validate our approach on benchmark examples and the results indicate that, for a fixed number of quadrature points (i.e., the same computational effort), the spline Gauss quadratures return an approximation that is by one to two orders of magnitude more accurate compared to the solution obtained by traditional polynomial Gauss counterparts.
2022-01-01T00:00:00Z