The amount prediction of gas emitted via wavelet neural network with improving training algorithm

Accurately predicting the amount of gas emitted from the mine is a very important matter for safety. As back-propagation neural networks (BPNN) have the shortcomings of slow convergence and easily falling into local optimums, wavelet neutral network (WNN) is applied to the prediction system with new...

Full description

Saved in:
Bibliographic Details
Main Authors: Pengqian Xue, Xiaoyu Zhang, Yumin Pan
Format: Conference Proceeding
Language:English
Subjects:
Artificial neural networks
Convergence
gas emission quantity
Neurons
nonlinear
predicting
Prediction algorithms
Training
Wavelet analysis
wavelet neural network
Wavelet transforms
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Accurately predicting the amount of gas emitted from the mine is a very important matter for safety. As back-propagation neural networks (BPNN) have the shortcomings of slow convergence and easily falling into local optimums, wavelet neutral network (WNN) is applied to the prediction system with new amended training algorithm. The simulation results obtained show that the new prediction system has faster convergence and more accurate prediction.
ISSN:2157-9555
DOI:10.1109/ICNC.2010.5583329