The behavior of a piezoelectric element can be reproduced with high accuracy using numerical simulations. However, simulations are limited by knowledge of the parameters in the piezoelectric model. The identification of the piezoelectric model can be addressed using different techniques but is still a problem for manufacturers and end users. In this paper, we present the use of a machine learning approach to determine the parameters in the model. In this first work, the main sensitive parameters, c11, c13, c33, c44 and e33 were predicted using a neural network numerically trained by using finite element simulations. Close to one million simulations were performed by changing the value of the selected parameters by ±10% around the starting point. To train the network, the values of a PZT 27 piezoelectric ceramic with a diameter of 20 mm and thickness of 2 mm were used as the initial seed. The first results were very encouraging, and provided the original parameters with a difference of less than 0.6% in the worst case. The proposed approach is extremely fast after the training of the neural network. It is suitable for manufacturers or end users that work with the same material and a fixed number of geometries.
18 September 2024 in IEEE Transactions on Robotics
Despite the prevalence of wireless connectivity in urban areas around the globe, there remain numerous and diverse situations where connectivity is insufficient or unavailable. To address this, we introduce mobile wireless infrastructure on demand , a system of UAVs that can be rapidly deployed to establish an ad-hoc wireless network. This network has the capability of reconfiguring itself dynamically to satisfy and maintain the required quality of communication. The system optimizes the positions of the UAVs and the routing of data flows throughout the network to achieve this quality of service (QoS). By these means, task agents using the network simply request a desired QoS, and the system adapts accordingly while allowing them to move freely. We have validated this system both in simulation and in real-world experiments. The results demonstrate that our system effectively offers mobile wireless infrastructure on demand, extending the operational range of task agents and supporting complex mobility patterns, all while ensuring connectivity and being resilient to agent failures.
This article presents the implementation and use of a two-wheel autonomous robot and its effectiveness as a tool for studying the recently discovered use of grid cells as part of mammalian’s brains space-mapping circuitry (specifically the medial entorhinal cortex). A proposed discrete-time algorithm that emulates the medial entorhinal cortex is programed into the robot. The robot freely explores a limited laboratory area in the manner of a rat or mouse and reports information to a PC, thus enabling research without the use of live individuals. Position coordinate neural maps are achieved as mathematically predicted although for a reduced number of implemented neurons (i.e., 200 neurons). However, this type of computational embedded system (robot’s microcontroller) is found to be insufficient for simulating huge numbers of neurons in real time (as in the medial entorhinal cortex). It is considered that the results of this work provide an insight into achieving an enhanced embedded systems design for emulating and understanding mathematical neural network models to be used as biologically inspired navigation system for robots.
16 November 2017 in Advances in Applied Ceramics: Structural, Functional and Bioceramics
Piezoelectric ceramic properties change with time. Detected aging effects for PZT ceramics are; the difference in the value of the dielectric constants diminishes, whereas dielectric losses and elastic stiffness increases. In this work, an optimisation technique based on adjusting a finite element model to reproduce the complex impedance curves of a resonant piezoceramic disk is analysed aiming to detect changes due to aging. This technique allows estimating all material parameters, both their real and imaginary parts. The optimisation uses the constitutive equations of the piezoelectric effect in the linear regime. The evolution of elastic, piezoelectric and dielectric constants is evaluated after 5 years of aging. To compute the ten complex parameters, the piezoelectric model is adjusted to minimise the difference between finite element simulations and the experimental data. Results presented here, show that the proposed technique is sensitive enough to detect changes in the individual parameters due to aging process.
Mobile Infrastructure on Demand (MIoD) involves deploying a mobile ad-hoc network through a team of network agents to provide communication infrastructure for another group of mobile agents serving a specific application. This study aims to determine the optimal locations for these network agents. Previous approaches have focused on maximizing graph connectivity or directly utilizing communication indicators. However, these methods often overlook the shared nature of the wireless communication medium, leading to suboptimal results. In this study, we incorporate shared access restrictions into our optimization model, addressing the inherent challenges in wireless communication. By leveraging the natural equivariance to translations and rotations of communication indicators, we employ E(n)-Equivariant Graph Neural Networks (EGNNs) to approximate the dependency of our indicator on node positions. We then use a gradient ascent algorithm to find optimal positions for the network agents. Our methodology demonstrates superior performance compared to traditional approaches, as evidenced by a higher figure of merit for the final configurations. These findings highlight the critical importance of considering the shared nature of the wireless medium for effective topology control in MIoD systems. The key contributions of this work include the incorporation of shared access restrictions into the optimization model, allowing for a more accurate representation of the problem, and the proposal of an EGNN-based Black Box Optimization approach to solve the resulting topology control problem.
We propose a method for providing communication network infrastructure in autonomous multi-agent teams. In particular, we consider a set of communication agents that are placed alongside regular agents from the system in order to improve the rate of information transfer between the latter. In order to find the optimal positions to place such agents, we define a flexible performance function that adapts to network requirements for different systems. We provide an algorithm based on shadow prices of a related convex optimization problem in order to drive the configuration of the complete system towards a local maximum. We apply our method to three different performance functions associated with three practical scenarios in which we show both the performance of the algorithm and the flexibility it allows for optimizing different network requirements.