73,837 Hits in 6.7 sec

Determination of multi-component flow process parameters based on electrical capacitance tomography data using artificial neural networks

J Mohamad-Saleh, B S Hoyle
2002 Measurement science and technology  
The results demonstrate the feasibility of the application of artificial neural networks for flow process parameter estimations based upon tomography data.  ...  The networks were then tested with patterns consisting of unlearned simulated ECT data of various flows and, with real ECT data of gas-water flows.  ...  Novel techniques are presented for component fraction estimation of two-component as well as threecomponent flows using the neural network approach based on ECT data.  ... 
doi:10.1088/0957-0233/13/12/303 fatcat:6ognit42g5e6bjli6addt3esva

Exploration of Artificial Intelligence-oriented Power System Dynamic Simulators [article]

Tannan Xiao, Ying Chen, Jianquan Wang, Shaowei Huang, Weilin Tong, Tirui He
2022 arXiv   pre-print
Tests of this prototype are carried out under four scenarios including sample generation, AI-based stability prediction, data-driven dynamic component modeling, and AI-aided stability control, which prove  ...  with neural network supportability and flexible external and internal application programming interfaces (APIs).  ...  A test case of modeling a generator with the published neural ODE module is conducted. The generator at bus 31 is modeled with the classical generator model.  ... 
arXiv:2110.00931v4 fatcat:ylr2b7ksqnf2feld5tuofyvibe

E2N: Error Estimation Networks for Goal-Oriented Mesh Adaptation [article]

Joseph G. Wallwork, Jingyi Lu, Mingrui Zhang, Matthew D. Piggott
2022 arXiv   pre-print
and trained neural network.  ...  We demonstrate that this approach is able to obtain the same accuracy with a reduced computational cost, for adaptive mesh test cases related to flow around tidal turbines, which interact via their downstream  ...  Acknowledgements The authors would like to thank members of the Applied Modelling and Computation Group (AMCG) at Imperial College London for the many interesting discussions regarding this work, in particular  ... 
arXiv:2207.11233v1 fatcat:hm7hr62dw5b6xkpafu6ty2yhhe

Implementation of a Neural Network Tool for Evaluation of Thermal Performance in a Heat Exchanger by using Double Elliptical Leaf Angle Strips with same Orientation and Same Direction

2019 International Journal of Engineering and Advanced Technology  
From these obtained results neural network tool was designed for evaluating the thermal performance named the generalized regression neural network (GRNN).In this process certain input parameters are given  ...  (temperatures, mass flow rate) and instantly predefined output parameters (heat transfer rate, pressure drop) are obtained.  ...  Based on the equation used the In this investigation statistical tool of generalized regression neural network is used which is an application of artificial neural network.  ... 
doi:10.35940/ijeat.f8925.088619 fatcat:ytin4qxmdjaghpzw3r7ibrtwsq

Unsupervised Recurrent All-Pairs Field Transforms for Particle Image Velocimetry

Christian Lagemann, Michael Klaas, Wolfgang Schröder
2021 14th International Symposium on Particle Image Velocimetry  
Therefore, we propose URAFT-PIV, an unsupervised deep neural network architecture for optical flow estimation in PIV applications and show that our combination of state-of-the-art deep learning pipelines  ...  Our tests also suggest that current state-of-the-art loss functions might be a limiting factor for the performance of unsupervised optical flow estimation.  ...  Acknowledgements The authors gratefully acknowledge the Gauss Centre for Supercomputing e.V.  ... 
doi:10.18409/ispiv.v1i1.120 fatcat:fissge226fcxviohyizizotra4

A Finite Element/Neural Network Framework for Modeling Suspensions of Non-spherical Particles

Martyna Minakowska, Thomas Richter, Sebastian Sager
2021 Vietnam Journal of Mathematics  
Based on resolved numerical simulations of prototypical particles we generate data to train a neural network which allows us to quickly estimate the hydrodynamic forces experienced by a specific particle  ...  fluid flow.  ...  Non-spherical Particles in Medical Flow Problems Funding Open Access funding enabled and organized by Projekt DEAL.  ... 
doi:10.1007/s10013-021-00477-9 fatcat:drhc23pupnd5zl2ofbg2i2kfcq

Learning 3D Granular Flow Simulations [article]

Andreas Mayr, Sebastian Lehner, Arno Mayrhofer, Christoph Kloss, Sepp Hochreiter, Johannes Brandstetter
2021 arXiv   pre-print
Here, we present a Graph Neural Networks approach towards accurate modeling of complex 3D granular flow simulation processes created by the discrete element method LIGGGHTS and concentrate on simulations  ...  Finally, we compare the machine learning based trajectories to LIGGGHTS trajectories in terms of particle flows and mixing entropies.  ...  Red arrows in plots R1-R4 visualize neural network predictions. Neural network predictions are based on wall representations that are oriented the same way as in the training phase.  ... 
arXiv:2105.01636v1 fatcat:svsyqp2rmvaw5gusvsrwwbq4ba

Alternative Artificial Neural Network Structures for Turbulent Flow Velocity Field Prediction

Koldo Portal-Porras, Unai Fernandez-Gamiz, Ainara Ugarte-Anero, Ekaitz Zulueta, Asier Zulueta
2021 Mathematics  
In this paper, a Convolutional Neural Network (CNN) for predicting different magnitudes of turbulent flows around different geometries by approximating the equations of the Reynolds-Averaged Navier-Stokes  ...  For that reason, in recent years, turbulence modelling using Artificial Neural Networks (ANNs) is becoming increasingly popular.  ...  Acknowledgments: The authors are grateful for the support provided by SGIker of UPV/EHU.  ... 
doi:10.3390/math9161939 fatcat:3fjz255w6jcnhdby6uujiuaa4a

Identification of system models from potential-stream equations on the basis of deep learning on experimental data

I. E. Starostin, S. P. Khalyutin
2020 Naučnyj Vestnik MGTU GA  
The neural network model for the angular velocity of the electric motor is synthesized basing on the approach described in the article [14].  ...  In order to model physicochemical processes in the general case, the authors previously developed a potential-flow method based on an experimental study (on the results of system tests) of the properties  ...  Deep learning methods (particularly, based on neural networks), unlike the traditional ones, do not require the preparatory data handling (in that case there are system data amounts, generated by means  ... 
doi:10.26467/2079-0619-2020-23-2-47-58 fatcat:epn7vja44vckdbjfggg67gcai4

Data-Driven Bending Angle Prediction of Soft Pneumatic Actuators with Embedded Flex Sensors

Khaled Elgeneidy, Niels Lohse, Michael Jackson
2016 IFAC-PapersOnLine  
ACKNOWLEDGMENTS The reported work has been partially funded by the EPSRC Centre for Innovated Manufacturing in Intelligent Automation (EP/IO33467/1). The support of which is gratefully acknowledged.  ...  Neural Networks A more advanced data-driven modelling technique investigated here is the use of artificial neural networks (ANN).  ...  It is obvious from comparing tables 1 and 2 that neural networks are able to generate more accurate predictions at the three tested orientations, with a notable reduction in the deviation from actual values  ... 
doi:10.1016/j.ifacol.2016.10.654 fatcat:pw7vil4ghfherh2pcpdejkaiyy

A Novel Neural Network based Model Predictive Controller for Congestion Prevention in IP Networks

Rashmi Baweja
2020 International Journal of Advanced Trends in Computer Science and Engineering  
Design of a neural network based model predictive controller for UDP(User Datagram Protocol) flow caused congestion, in IP( Internet protocol) networks is proposed in this paper.  ...  In this paper a neural network utilizing Levenberg-Marquardt learning algorithm for on-line identification of non-linear plant(network) model is implemented and combined with a model predictive optimization  ...  ACKNOWLEDGEMENT The author thankfully acknowledge department of Electronics Engineering, Rajasthan Technical University, Kota, for providing research opportunity.  ... 
doi:10.30534/ijatcse/2020/151932020 fatcat:i2y73rcblfdtxfnj3abbosigs4


Mehmet Yuceer, Ridvan Berber
2006 IFAC Proceedings Volumes  
Then the neural network model was restructured and inversely trained by assuming the exit fructose concentration as the input variable and the feed flow rate as the output variable.  ...  This work presents an approach to modelling of a real industrial isomerization reactor by artificial neural networks (ANN) pre-processed with principal component analysis (PCA).  ...  Acknowledgement: We truly acknowledge the industrial data provided by CARGILL Inc. Orhangazi-Turkey through Yontem Beyazkus and Ercan Erdas.  ... 
doi:10.3182/20060402-4-br-2902.00783 fatcat:sjksq7hp5zhevd3p5wtqdkvuju


Kamal Shah, Kekre HB
2008 International Journal on Information Sciences and Computing  
The goal of this project is to create neural network-based face detection system to identify people from a video sequence.  ...  The face space is described by a set of feature vectors obtained using the discrete cosine transform (DCT).This DCT feature vector is then fed into Artificial Neural Networks(ANN) which are used to recognize  ...  International Journal on , Vol.2, No.1, July 2008 Information Sciences and Computing found to be robust enough to account for changes in facial expressions and addition of accessories .  ... 
doi:10.18000/ijisac.50020 fatcat:mf5afurakfhddeo4xqupjz6u5y

A finite element / neural network framework for modeling suspensions of non-spherical particles. Concepts and medical applications [article]

Martyna Minakowska, Thomas Richter, Sebastian Sager
2020 arXiv   pre-print
Based on resolved numerical simulations of prototypical particles we generate data to train a neural network which allows us to quickly estimate the hydrodynamic forces experienced by a specific particle  ...  fluid flow.  ...  Testing To test the accuracy of the trained network we apply it to a set of testing data that was not used in the training of the network.  ... 
arXiv:2009.10818v1 fatcat:5xtvtymt2rblbgmuxfihqvt32a

Conversation Learner – A Machine Teaching Tool for Building Dialog Managers for Task-Oriented Dialog Systems [article]

Swadheen Shukla, Lars Liden, Shahin Shayandeh, Eslam Kamal, Jinchao Li, Matt Mazzola, Thomas Park, Baolin Peng, Jianfeng Gao
2020 arXiv   pre-print
Traditionally, industry solutions for building a task-oriented dialog system have relied on helping dialog authors define rule-based dialog managers, represented as dialog flows.  ...  It combines the best of both approaches by enabling dialog authors to create a dialog flow using familiar tools, converting the dialog flow into a parametric model (e.g., neural networks), and allowing  ...  One benefit provided by using a neural network model is that the network infers a latent representation of dialog state, eliminating the need for explicitly specifying dialog states.  ... 
arXiv:2004.04305v2 fatcat:moatbjxzwjbwvo4pblki55jyuu
« Previous Showing results 1 — 15 out of 73,837 results