BP neural network in classification of fabric defect based on particle swarm optimization

2008 ◽  
Author(s):  
Su-Yi Liu ◽  
Le-Duo Zhang ◽  
Qian Wang ◽  
Jing-Jing Liu
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Bp Neural Network ◽  
Particle Swarm ◽  
Swarm Optimization ◽  
Fabric Defect

scholarly journals An Improved Method for NURBS Surface Based on Particle Swarm Optimization BP Neural Network

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 184656-184663
Author(s):  
Xiaoqiang Tian ◽  
Lingfu Kong ◽  
Deming Kong ◽  
Li Yuan ◽  
Dehan Kong
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Bp Neural Network ◽  
Particle Swarm ◽  
Nurbs Surface ◽  
Improved Method ◽  
Swarm Optimization

scholarly journals The application of particle swarm optimization using neural network to optimize classification of employee performance assessment

2019 ◽  
Vol 1175 ◽  
pp. 012067
Author(s):  
Mohammad Humam ◽  
Oman Somantri ◽  
Maylane Boni Abdillah ◽  
Syaefani Arif Romadhon ◽  
Mohammad Khambali ◽  
...  
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Performance Assessment ◽  
Employee Performance ◽  
Particle Swarm ◽  
Swarm Optimization

New Research on Identification and Classification of Grid Power Quality Disturbances

2014 ◽  
Vol 986-987 ◽  
pp. 1431-1434
Author(s):  
Ning Xia Yang ◽  
Mao Fa Gong ◽  
Xiao Fei Wang ◽  
Hui Ting Ge ◽  
Yu Qing Lin ◽  
...  
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Wavelet Transform ◽  
Power Quality ◽  
Particle Swarm ◽  
Interference Signal ◽  
Swarm Optimization ◽  
Frequency Information ◽  
Power Quality Disturbances

To improve accuracy and speed of recognising and classifying grid power quality disturbances, this paper presents a new method which combines complex wavelet transform and particle swarm optimization (PSO) neural network to identify and classify the disturbance . This method extract both amplitude-frequency and phase frequency information of the interference signal to make up for the lack of traditional wavelet transform which only extract the amplitude-frequency information. And on this basis, using particle swarm optimization, we seek the optimal solution of neural network weights and thresholds for the identification and classification of power quality. The MATLAB simulation result has verified the accuracy and rapidity of this method compared with the traditional method .

Sign in / Sign up

Export Citation Format

Share Document