scholarly journals Automated Neural Network-Based Multiphysics Parametric Modeling of Microwave Components

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 141153-141160
Author(s):  
Weicong Na ◽  
Wanrong Zhang ◽  
Shuxia Yan ◽  
Feng Feng ◽  
Wei Zhang ◽  
...  
Keyword(s):  
Neural Network ◽  
Parametric Modeling ◽  
Microwave Components

scholarly journals A Novel Deep Neural Network Topology for Parametric Modeling of Passive Microwave Components

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 82273-82285 ◽  
Author(s):  
Jing Jin ◽  
Feng Feng ◽  
Jianan Zhang ◽  
Shuxia Yan ◽  
Weicong Na ◽  
...  
Keyword(s):  
Neural Network ◽  
Network Topology ◽  
Deep Neural Network ◽  
Parametric Modeling ◽  
Passive Microwave ◽  
Microwave Components ◽  
Passive Microwave Components

Space Mapping Approach to Electromagnetic Centric Multiphysics Parametric Modeling of Microwave Components

2018 ◽  
Vol 66 (7) ◽  
pp. 3169-3185 ◽  
Author(s):  
Wei Zhang ◽  
Feng Feng ◽  
Venu-Madhav-Reddy Gongal-Reddy ◽  
Jianan Zhang ◽  
Shuxia Yan ◽  
...  
Keyword(s):  
Parametric Modeling ◽  
Space Mapping ◽  
Mapping Approach ◽  
Microwave Components

scholarly journals Dynamic Modeling and Parameters Optimization of Large Vibrating Screen with Full Degree of Freedom

2019 ◽  
Vol 2019 ◽  
pp. 1-12 ◽  
Author(s):  
Xiaodong Yang ◽  
Jida Wu ◽  
Haishen Jiang ◽  
Wenqiang Qiu ◽  
Chusheng Liu
Keyword(s):  
Neural Network ◽  
Elastic Deformation ◽  
Parametric Modeling ◽  
Parameters Optimization ◽  
Degree Of Freedom ◽  
Design Parameters ◽  
Response Analysis ◽  
Lateral Plate ◽  
Beam Position ◽  
Vibrating Screen

Dynamic characteristic and reliability of the vibrating screen are important indicators of large vibrating screen. Considering the influence of coupling motion of each degree of freedom, the dynamic model with six degrees of freedom (6 DOFs) of the vibrating screen is established based on the Lagrange method, and modal parameters (natural frequencies and modes of vibration) of the rigid body are obtained. The finite element modal analysis and harmonic response analysis are carried out to analyze the elastic deformation of the structure. By using the parametric modeling method, beam position is defined as a variable, and an orthogonal experiment on design is performed. The BP neural network is used to model the relationship between beam position and maximal elastic deformation of the lateral plate. Further, the genetic algorithm is used to optimize the established neural network model, and the optimal design parameters are obtained.

scholarly journals Flexible, non-parametric modeling using regularized neural networks

2022 ◽  
Author(s):  
Oskar Allerbo ◽  
Rebecka Jörnsten
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Heterogeneous Data ◽  
Parametric Modeling ◽  
Additive Models ◽  
Adaptive Lasso ◽  
Complex Data ◽  
Data Set ◽  
Model Complex ◽  
Non Parametric

AbstractNon-parametric, additive models are able to capture complex data dependencies in a flexible, yet interpretable way. However, choosing the format of the additive components often requires non-trivial data exploration. Here, as an alternative, we propose PrAda-net, a one-hidden-layer neural network, trained with proximal gradient descent and adaptive lasso. PrAda-net automatically adjusts the size and architecture of the neural network to reflect the complexity and structure of the data. The compact network obtained by PrAda-net can be translated to additive model components, making it suitable for non-parametric statistical modelling with automatic model selection. We demonstrate PrAda-net on simulated data, where we compare the test error performance, variable importance and variable subset identification properties of PrAda-net to other lasso-based regularization approaches for neural networks. We also apply PrAda-net to the massive U.K. black smoke data set, to demonstrate how PrAda-net can be used to model complex and heterogeneous data with spatial and temporal components. In contrast to classical, statistical non-parametric approaches, PrAda-net requires no preliminary modeling to select the functional forms of the additive components, yet still results in an interpretable model representation.

Sign in / Sign up

Export Citation Format

Share Document