Search results for "work"
showing 10 items of 14511 documents
Model-based Engineering for the Integration of Manufacturing Systems with Advanced Analytics
2016
To employ data analytics effectively and efficiently on manufacturing systems, engineers and data scientists need to collaborate closely to bring their domain knowledge together. In this paper, we introduce a domain-specific modeling approach to integrate a manufacturing system model with advanced analytics, in particular neural networks, to model predictions. Our approach combines a set of meta-models and transformation rules based on the domain knowledge of manufacturing engineers and data scientists. Our approach uses a model of a manufacturing process and its associated data as inputs, and generates a trained neural network model as an output to predict a quantity of interest. This pape…
Extreme Learning Machines for Data Classification Tuning by Improved Bat Algorithm
2018
Single hidden layer feed forward neural networks are widely used for various practical problems. However, the training process for determining synaptic weights of such neural networks can be computationally very expensive. In this paper we propose a new learning algorithm for learning the synaptic weights of the single hidden layer feedforward neural networks in order to reduce the learning time. We propose combining the upgraded bat algorithm with the extreme learning machine. The proposed approach reduces the number of evaluations needed to train a neural network and efficiently finds optimal input weights and the hidden biases. The proposed algorithm was tested on standard benchmark clas…
Kinematic synthesis of a new 3D printing solution
2016
Low-cost production of metal parts is a challenge nowadays in the Additive Manufacturing world and new methods are being developed. The MIM technique is an innovative approach for 3D printing. This method requires a machine with suitable kinematics capable of generating the adequate movements. The object of this article is the kinematic synthesis of a 5Dofs robot, based on two PKM machines, for additive manufacturing in order to compliant with the requirements of this new technology. Robot kinematics have been optimized by genetic algorithm in order to cover the required workspace and the design of the robot and outline of the control system are also given.
Efficient Transport Protocol for Networked Haptics Applications
2008
The performance of haptic application is highly sensitive to communication delays and losses of data. It implies several constraints in developing networked haptic applications. This paper describes a new internet protocol called Efficient Transport Protocol (ETP), which aims at developing distributed interactive applications. TCP and UDP are transport protocols commonly used in any kind of networked communication, but they are not focused on real time application. This new protocol is focused on reducing roundtrip time (RTT) and interpacket gap (IPG). ETP is, therefore, optimized for interactive applications which are based on processes that are continuously exchanging data. ETP protocol i…
An Auto-Operated Telepresence System for the Nao Humanoid Robot
2013
International audience; This paper presents the development process of an auto-operated telepresence system for the Nao humanoid robot with the main functionality of directing the robot autonomously to an operator-defined target location within a static workspace. The workspace is observed by an array of top-view cameras, which are used to localize the robot by means of a color-based marker detection technique. The system is accessible world-wide to the remote operator through any Internet-capable device via a web-based control interface. The web server responsible for coordinating the communication between system and operator is hosted on a cloud-based infrastructure online. The system was…
Sensorless Speed Control for Double-Sided Linear Induction Motor Applications
2019
In this work, a flux and speed observer for double-sided linear induction motor applications is presented and experimentally validated. More in detail, from a Double-Sided Linear Induction Motor (DLIM) prototype, the complete modelling and the determination of the related parameters are here reported. Furthermore, the equations for a d-flux and q-flux observer are conceived and several simulation tests are performed. From the good agreements between the trends over time of the speed estimated by the observer and the simulated one, it can be stated that the observer is well designed. Moreover, in order to experimentally validate the proposed observer, a test bench is set-up for the DLIM/obse…
Networked Bio-Inspired Evolutionary Dynamics on a Multi-Population
2019
We consider a multi-population, represented by a network of groups of individuals. Every player of each group can choose between two options, and we study the problem of reaching consensus. The dynamics not only depend on the dynamics within the group, but they also depend on the topology of the network, so neighboring groups influence individuals as well. First, we develop a mathematical model of this networked bio-inspired evolutionary behavior and we study its steady-state. We look at the special case where the underlying network topology is a regular and unweighted graph and show that the steady-state is a consensus equilibrium. A sufficient condition for exponential stability is given.…
Graph-theoretical derivation of brain structural connectivity
2020
Brain connectivity at the single neuron level can provide fundamental insights into how information is integrated and propagated within and between brain regions. However, it is almost impossible to adequately study this problem experimentally and, despite intense efforts in the field, no mathematical description has been obtained so far. Here, we present a mathematical framework based on a graph-theoretical approach that, starting from experimental data obtained from a few small subsets of neurons, can quantitatively explain and predict the corresponding full network properties. This model also changes the paradigm with which large-scale model networks can be built, from using probabilisti…
A predictive learning approach to optimal load sharing in energy management systems
2019
Given the total power demand, $P_{d}$ , current practice of equal load sharing in the process industry is to distribute the load among power supply units and machines (e.g., diesel/aas/wind turbines) in proportion to the maximum power, i.e., $P_{i}=\frac{p_{\max}^{i}}{\sum_{j}P_{\max}^{j}}P_{d}$ , where $P_{\max}^{i}$ denotes the maximum power of the ithunit. However, the efficiency of power supply units, vary in time and are highly individual, even in the case of units from same brand and model. Thus, by considering and utilizing these individual differences, it is possible to share the load in a more fuel/cost/energy optimal manner. To capture this potential, the work presented in this pa…
Friction Model for Tool/Work Material Contact Applied to Surface Integrity Prediction in Orthogonal Cutting Simulation
2017
Abstract Tribological behavior at both tool/chip and tool/work material interfaces should be highly considered while simulating the machining process. In fact, it is no longer accurate to suppose one independent constant friction coefficient at the tool/chip interface, since in reality it depends on the applied contact conditions, including the sliding velocity and pressure. The contact conditions at both above mentioned interfaces may affect the thermal and mechanical phenomena and consequently the surface integrity predictions. In this article, the influence of contact conditions (sliding velocity) on the tribological behavior of uncoated tungsten carbide tool against OFHC copper work mat…