1,721,158 research outputs found
Optimisation and management of energy power flow in hybrid electrical vehicles
No full textThe use of optimization algorithm for the management of
energy on vehicles electrical, is an innovative argument in the
field of the transports. In this context, beginning from an
accurate model of electrical device, is necessary to identify
the performances so as to reproduce the physical behavior of
the considered vehicle.
Particularly it is necessary to start from a model that takes
into account several details including Battery and all the
electrical loads
A topological Optimization Through Reinforcement Learning: An Electromagnetic Case Study
No full textOver the past decade, Reinforcement Learning has been investigated for tackling optimization challenges. Specifi-cally, Reinforcement Learning algorithms have been exploited as optimization algorithms in intricate black-box inverse problems, determining the optimal values of the manipulated variables to achieve a specific target. The Reinforcement Learning algorithms train a meta-model, called agent, by exploring the problem space. Then, the agent is used to determine the best values of the handled variables that match the objective. In the literature, the agent is usually trained over a single objective target. Just like other optimization algorithms, if the objective target changes, it is necessary to retrain the agent. In this article, Deep Reinforcement Learning is proposed as an optimization tool capable to learn and optimize the control variables to meet different targets with a single training process. The approach involves the training of a set of Artificial Neural Networks to associate different optimization targets with the corresponding control variable values. To assess its efficacy, the methodology is applied to a case study involving the topology optimization of a 2-D axisymmetric coil using an electromagnetic finite element method. The results highlight comparable performances with an advanced data-driven global optimization algorithm and superior performances than gradient descent, genetic, and particle swarm algorithms for different objectives
A Methodology for Non Destructive Reconstruction of Multilayer PCBs Using Thermal Waves
No full textThis paper proposes a new active thermogra-phy methodology for the non-destructive investigation and reconstruction of internal structures in multilayered printed circuit boards through the digital image processing of superficial thermal records. The methodology relies on the sequential composition of three digital signal processing techniques standing for the raw-data signal reconstruction, the transformation of the thermal information in a virtual acoustic wave, and the virtual wave analysis for the source spatial reconstruction. The methodology is validated through finite element simulations which proves that this imaging methodology is capable of localizing and reconstructing the shape of the traces. The main novelty is the application of a recent new algorithm for thermal imaging for the monitoring of internal traces in multilayered printed circuits and the design-from-PCB
3D Source Simulation Method for Static Current Field in Inhomogeneous Media including lumped parameters
No full text
Hardware-in-the-Loop Framework for Validation of Ancillary Service in Microgrids: Feasibility, Problems and Improvement
Full text linkTesting complex micro-networks requires the availability of specialized laboratories and interconnected devices. This paper describes the development of a controller-hardware-in-the-loop simulation in the context of the microgrid. This approach provides genuine testing and debugging environment for converter controllers in microgrid under various test conditions by means of real-time simulation. It is also viable to test microgrid dispatching strategies. The platform structure and real-time simulation issues including modeling, circuit partition, and multi-rate design are studied, demonstrating the rationality, and transferability of the design scheme. In the interest of studying the integration of distributed energy resources, a novel low-level control method, which enables the power converters to function as both grid-supplying and grid-supporting, is tested. Some practical implementation issues of the theoretical control algorithm are exposed and alleviated, which shows the value of hardware-in-the-loop simulation, and at the same time contributes evidence to modifying theoretical algorithms in industrial applications
- …
