An Improved Compound Gradient Vector Based Neural Network On-Line Training Algorithm

2007 ◽  
pp. 316-325
Author(s):  
Zaiping Chen ◽  
Chao Dong ◽  
Qiuqian Zhou ◽  
Shujun Zhang
Keyword(s):  
Neural Network ◽  
Training Algorithm ◽  
Gradient Vector ◽  
On Line

scholarly journals A fast on-line neural-network training algorithm for a rectifier regulator

1998 ◽  
Vol 13 (2) ◽  
pp. 366-371 ◽  
Author(s):  
F. Kamran ◽  
R.G. Harley ◽  
B. Burton ◽  
T.G. Habetler ◽  
M.A. Brooke
Keyword(s):  
Neural Network ◽  
Neural Network Training ◽  
Training Algorithm ◽  
Network Training ◽  
On Line

scholarly journals Elman neural network for modeling and predictive control of delayed dynamic systems

2016 ◽  
Vol 26 (1) ◽  
pp. 117-142 ◽  
Author(s):  
Antoni Wysocki ◽  
Maciej Ławryńczuk
Keyword(s):  
Neural Network ◽  
Nonlinear Optimization ◽  
Predictive Control ◽  
Neural Model ◽  
Training Algorithm ◽  
Elman Neural Network ◽  
Quadratic Optimization Problem ◽  
Strongly Nonlinear ◽  
On Line ◽  
Sampling Instant

The objective of this paper is to present a modified structure and a training algorithm of the recurrent Elman neural network which makes it possible to explicitly take into account the time-delay of the process and a Model Predictive Control (MPC) algorithm for such a network. In MPC the predicted output trajectory is repeatedly linearized on-line along the future input trajectory, which leads to a quadratic optimization problem, nonlinear optimization is not necessary. A strongly nonlinear benchmark process (a simulated neutralization reactor) is considered to show advantages of the modified Elman neural network and the discussed MPC algorithm. The modified neural model is more precise and has a lower number of parameters in comparison with the classical Elman structure. The discussed MPC algorithm with on-line linearization gives similar trajectories as MPC with nonlinear optimization repeated at each sampling instant.

Methods for evaluation the manufacturability of a vehicle

2020 ◽  
pp. 152-160
Keyword(s):  
Neural Network ◽  
Initial Data ◽  
Comparative Data ◽  
Training Algorithm ◽  
Neural Network Method ◽  
The Neural Network ◽  
Network Method ◽  
Calculation Results ◽  
Production And Operation

Methods for evaluation the manufacturability of a vehicle in the field of production and operation based on an energy indicator, expert estimates and usage of a neural network are stated. By using the neural network method the manufacturability of a car in a complex and for individual units is considered. The preparation of the initial data at usage a neural network for predicting the manufacturability of a vehicle is shown; the training algorithm and the architecture for calculating the manufacturability of the main units are given. According to the calculation results, comparative data on the manufacturability vehicles of various brands are given.

scholarly journals Thermal-wet model of knitted double jersey based on backpropagation algorithm of neural network

2020 ◽  
Vol 15 ◽  
pp. 155892501990083
Author(s):  
Xintong Li ◽  
Honglian Cong ◽  
Zhe Gao ◽  
Zhijia Dong
Keyword(s):  
Neural Network ◽  
Water Vapor ◽  
Thermal Resistance ◽  
Resistance Test ◽  
Training Algorithm ◽  
Backpropagation Algorithm ◽  
Optimal Network ◽  
Resistance Model ◽  
Hidden Layer ◽  
The Relationship

In this article, thermal resistance test and water vapor resistance test were experimented to obtain data of heat and humidity performance. Canonical correlation analysis was used on determining influence of basic fabric parameters on heat and humidity performance. Thermal resistance model and water vapor resistance model were established with a three-layered feedforward-type neural network. For the generalization of the network and the difficulty of determining the optimal network structure, trainbr was chosen as training algorithm to find the relationship between input factors and output data. After training and verification, the number of hidden layer neurons in the thermal resistance model was 12, and the error reached 10−3. In the water vapor resistance model, the number of hidden layer neurons was 10, and the error reached 10−3.

Sign in / Sign up

Export Citation Format

Share Document