Wyniki wyszukiwania - Biblioteka Nauki

Ten serwis zostanie wyłączony 2025-02-11.

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

Znaleziono wyników: 3

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: parametric

Sortuj według:

Ogranicz wyniki do:

Parametric elastic full waveform inversion with convolutional neural network

100%

Guo K. , Zong Z. , Yang J. , Tan Y.

tom Vol. 72, no. 2

673--687

Elastic full waveform inversion (EFWI) is a powerful tool for estimating elastic models by reducing the misfit between multi-component seismic records and simulated data. However, when multiple parameters are updated simultaneously, the gradients of the loss function with respect to these parameters will be coupled together, the effect exacerbate the nonlinear problem. We propose a parametric EFWI method based on convolutional neural networks (CNN-EFWI). The parameters that need to be updated are the weights in the neural network rather than the elastic models. The convolutional kernel in the network can increase spatial correlations of elastic models, which can be regard as a regularization strategy to mitigate local minima issue. Furthermore, the representation also can mitigate the cross-talk between parameters due to the reconstruction of Frechét derivatives by neural networks. Both forward and backward processes are implemented using a time-domain finite-difference solver for elastic wave equation. Numerical examples on overthrust models, fluid saturated models and 2004 BP salt body models demonstrate that CNN-EFWI can partially mitigate the local minima problem and reduce the dependence of inversion on the initial models. Mini-batch configuration is used to speed up the update and achieve fast convergence. In addition, the inversion of noisy data further verifies the robustness of CNN-EFWI.

Goal programming approach for solving heptagonal fuzzy transportation problem under budgetry constraint

100%

KHALIFA H. A. E.-w.

nr 1

85-96

Transportation problem (TP) is a special type of linear programming problem (LPP) where the objective is to minimize the cost of distributing a product from several sources (or origins) to some destinations. This paper addresses a transportation problem in which the costs, supplies, and demands are represented as heptagonal fuzzy numbers. After converting the problem into the corresponding crisp TP using the ranking method, a goal programming (GP) approach is applied for obtaining the optimal solution. The advantage of GP for the decision-maker is easy to explain and implement in real life transportation. The stability set of the first kind corresponding to the optimal solution is determined. A numerical example is given to highlight the solution approach.

Influence of an Energy Source on Regular and Chaotic Vibrations of Coupled Nonlinear Oscillators

84%

Warmiński J.

Machine Dynamics Problems

2007

tom Vol. 31, No. 1

101-119

Regular and chaotic vibrations of the system composed of two parametrically and self-excited oscillators are analysed in the paper. The considered system is excited by a non-ideal energy source represented by DC motor with limited power supply. Interactions between different vibration types, bifurcation and the synchronisation regions are found by analytical and numerical methods. Influence of the most important parameters on transition through resonance areas is presented. Possible chaotic motions are determined by Lyapunov exponent criterion.