| 基于蚁群算法和BP神经网络的矿井通风机故障诊断 |
| |
| 引用本文： | 黄明,郭立楠,朱伟,许军,曹建全.基于蚁群算法和BP神经网络的矿井通风机故障诊断[J].煤矿机械,2012,32(7):258-259. |
| |
| 作者姓名： | 黄明 郭立楠 朱伟 许军 曹建全 |
| |
| 作者单位： | 安徽理工大学电气与信息工程学院,安徽淮南,232001 |
| |
| 摘 要： | 采用蚁群算法代替BP算法来训练神经网络的权值和阈值,通过比较2种算法的训练结果,基于蚁群优化的神经网络具有较快的收敛速度,而且能够克服BP算法易于陷入局部最优解的缺陷。采用蚁群算法训练后的神经网络对矿井通风机进行了故障诊断,实验结果表明,该方法是一种有效的故障诊断方法,具有较好的故障诊断效果。
|
| 关 键 词： | 矿井通风机 故障诊断 蚁群算法 BP神经网络 |
Fault Diagnosis of Mine Ventilator Based on Neural Network of Ant Colony Algorithm |
| |
| HUANG Ming
,
GUO Li-nan
,
ZHU Wei
,
XU Jun
,
CAO Jian-quan.Fault Diagnosis of Mine Ventilator Based on Neural Network of Ant Colony Algorithm[J].Coal Mine Machinery,2012,32(7):258-259. |
| |
| Authors: | HUANG Ming GUO Li-nan ZHU Wei XU Jun CAO Jian-quan |
| |
| Affiliation: | (Institute of Electric and Information Technology,Anhui University of Science and Technology,Huainan 232001,China) |
| |
| Abstract: | Ant colony algorithm(ACO) is used to train weights and thresholds of neural network instead of BP algorithm.The training results of these two algorithms show that neural network based on ACO has faster convergence speed and can avoid involving local extremum.The trained neural network by ACO is tested to diagnose faults of mine ventilator,and the test result shows this method has better faults diagnosis effect and it is a valid method. |
| |
| Keywords: | mine ventilator fault diagnosis ant colony algorithm(ACO) BP neural network |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
