基于AGA优化BP神经网络的矿井通风机故障诊断  

Fault Diagnosis of Mine Ventilator Based on AGA Optimized BP Neural Network

作　　者：余发山[1] 高勇[1] 

机构地区：[1]河南理工大学电气工程与自动化学院,河南焦作454000

出　　处：《软件导刊》2017年第9期154-157,共4页Software Guide

摘　　要：矿井通风机稳定运行对煤矿安全生产具有十分重要的意义。为提高通风机故障诊断的准确率,通过分析通风机振动信号频率成分与通风机故障类型之间的关系,提出一种基于自适应遗传算法(AGA)优化BP神经网络的矿井通风机故障诊断方法。采用AGA优化BP神经网络的连接权值和阈值,提高BP神经网络的学习能力和泛化能力;建立基于BP神经网络的通风机故障诊断模型,并进行仿真实验。实验结果表明,AGA优化的BP神经网络能够有效识别通风机故障类型,故障诊断准确率高。The stable operation of the mine ventilator is of great significance to the safe production of the coal mine. In order to improve the accuracy of the mine ventilator fault diagnosis, based on the analysis of the relationship between the frequency com- ponents of the vibration signal and the fault type of the mine ventilator, a fault diagnosis method of mine ventilator based on a- daptive genetic algorithm optimized BP neural network is proposed. Using adaptive genetic algorithm to optimize the connection weights and thresholds of BP neural network, improve the learning ability and generalization ability of BP neural network; the fault diagnosis model of mine ventilator based on BP neural network is established,and the simulation experiment is carried out. The simulation experiment results show that the BP neural network optimized by adaptive genetic algorithm can effectively iden- tify the fault types of mine ventilator, and it has a high accuracy of fault diagnosis.

关 键 词：矿井通风机 故障诊断 自适应遗传算法 神经网络 

分 类 号：TP319[自动化与计算机技术—计算机软件与理论]