An approach for load frequency control enhancement in two-area hydro-wind power systems using LSTM + GA-PID controller with augmented lagrangian methods [PDF]
Scientific ReportsThis paper proposes an advanced Load Frequency Control (LFC) strategy for two-area hydro-wind power systems, using a hybrid Long Short-Term Memory (LSTM) neural network combined with a Genetic Algorithm-optimized PID (GA-PID) controller.
Ritesh Dash +4 more
doaj +2 more sources
Physics-informed neural networks with hybrid Kolmogorov-Arnold network and augmented Lagrangian function for solving partial differential equations [PDF]
Scientific ReportsPhysics-informed neural networks (PINNs) have emerged as a fundamental approach within deep learning for the resolution of partial differential equations (PDEs).
Zhaoyang Zhang +4 more
doaj +2 more sources
Using a Factored Dual in Augmented Lagrangian Methods for Semidefinite Programming
Operations Research Letters, 2018 In the context of augmented Lagrangian approaches for solving semidefinite programming problems, we investigate the possibility of eliminating the positive semidefinite constraint on the dual matrix by employing a factorization. Hints on how to deal with
De Santis, Marianna +2 more
core +3 more sources
A Novel Low-Rank Embedded Latent Multi-View Subspace Clustering Approach [PDF]
SensorsNoises and outliers often degrade the final prediction performance in practical data processing. Multi-view learning by integrating complementary information across heterogeneous modalities has become one of the core techniques in the field of machine ...
Sen Wang +3 more
doaj +2 more sources
A General Purpose Variational Formulation for Boundary Value Problems of Orders Greater than Two [PDF]
Journal of Applied and Computational Mechanics, 2021 We develop a new general purpose variational formulation, particularly suitable for solving boundary value problems of orders greater than two. The functional related to this variational formulation requires only Η1 regularity in order to be well-defined.
Xuefeng Li
doaj +1 more source
Augmented Lagrangian method for imposing nonlinear multi freedom constraints in static analysis for frames using FEM [PDF]
E3S Web of Conferences, 2021 This paper focuses on the treatment of nonlinear multi freedom constraints using an augmented Lagrangian method in finite element analysis of frames. The process of imposing boundary constraints is developed by changing the assembly stiffness equation to
Bich Quyen Vu Thi +3 more
doaj +1 more source
Alexandria Engineering Journal, 2022 The maintenance of power system equipment, specifically, the maintenance of generating units, is implicitly related to the reliability and economic operation of the power system.
M.R. Qader
doaj +1 more source
Multilevel augmented Lagrangian solvers for overconstrained contact formulations* [PDF]
ESAIM: Proceedings and Surveys, 2021 Multigrid methods for two-body contact problems are mostly based on special mortar discretizations, nonlinear Gauss-Seidel solvers, and solution-adapted coarse grid spaces. Their high computational efficiency comes at the cost of a complex implementation
Krause Rolf, Weiser Martin
doaj +1 more source
Combining Deep Image Prior and Second-Order Generalized Total Variance for Image Denoising
IEEE Access, 2023 Deep image prior is a classical unsupervised deep learning method that does not require plenty of training samples, because in some practical applications, like medical imaging, collecting tons of training samples is not always viable.
Jianlou Xu +3 more
doaj +1 more source
Finite Element Solutions of Cantilever and Fixed Actuator Beams Using Augmented Lagrangian Methods [PDF]
Journal of Applied and Computational Mechanics, 2018 In this paper we develop a numerical procedure using finite element and augmented Lagrangian meth-ods that simulates electro-mechanical pull-in states of both cantilever and fixed beams in microelectromechanical systems (MEMS) switches.
Dongming Wei, Xuefeng Li
doaj +1 more source