基于bp神经网络的异步电机故障诊断.doc
约46页DOC格式手机打开展开
基于bp神经网络的异步电机故障诊断,基于bp神经网络的异步电机故障诊断1.88万字我自己原创的毕业论文,仅在本站独家提交,大家放心使用目 录第一章 绪论11.1神经网络 11.1.1 神经网络分类及简单介绍 11.1.2 bp神经网络51.2异步电动机工作原理及用途 81.3异步电动机常见故障类型及方法 81.3.1异步电动机常见故障类型 91.3.2异...
内容介绍
此文档由会员 小花仙66 发布
基于BP神经网络的异步电机故障诊断
1.88万字
我自己原创的毕业论文,仅在本站独家提交,大家放心使用
目 录
第一章 绪论………………………………………………………………………1
1.1神经网络……………………………………………………………………… 1
1.1.1 神经网络分类及简单介绍………………………………………………… 1
1.1.2 BP神经网络…………………………………………………………………………5
1.2异步电动机工作原理及用途………………………………………………… 8
1.3异步电动机常见故障类型及方法…………………………………………… 8
1.3.1异步电动机常见故障类型………………………………………………… 9
1.3.2异步电动机电气故障分析………………………………………………………………9
1.4电动机故障诊断的主要方法……………………………………………………11
1.4.1基于人工神经网络故障诊断…………………………………………………13
1.4.2基于专家系统故障诊断………………………………………………………13
1.4.3基于信息融合技术故障诊断…………………………………………………14
1.4.4基于小波变换故障诊断………………………………………………………14
第二章异步电动机在MATLAB中的建模仿真及故障设置……………….16
2.1 BP神经网络在异步电机故障诊断中的应用……………………………………………..15
2.2异步电动机在MATLAB中的建模(频谱法)………………………………… 16
2.2.1选择并搭建模块………………………………………………………………….16
2.2.2模块参数设定…………………………………………………………………….19
2.3三相异步电动机故障设置及故障特征提取………………………………………22
第三章BP网络异步电动机故障诊断实例………………………………….23
3.1 BP神经网络算法的原理……………………………………………………………28
3.1.1人工神经元的模型……………………………………………………………… 28
3.1.2 BP 神经网络算法的原理…………………………………………………………28
3.2 BP神经网络的构建………………………………………………………………… 29
3.2.1 输入输出神经元数确定………………………………………………………… 29
3.2.2.隐含层层数的确定……………………………………………………………… 29
3.3 BP网络训练与测试………………………………………………………………. 30
第四章 总结与展望…………………………………………………………….40
4.1 总结……………………………………………………………………………………………40
4.2 展望………………………………………………………………………………………………41
致谢……………………………………………………………………………42
参考文献………………………………………………………………………43
摘要:近年来由于我国经济迅速发展,电气设备的应用范围逐步由城市转向农村,三相异步电动机因其物美价廉的特点,被普遍应用于工业生产的各个领域。如果电机故障,将给人们的生产和生活造成巨大损失,因此电动机故障诊断具有重要的现实意义。
首先,神经网络,分类的原则,应用和前景进行了介绍,然后,异步电动机的基本原理,故障分类和故障诊断方法。介绍了一种基于BP神经网络模型的故障诊断方法,着重对异步电动机各相接地短路故障,利用FFT频谱法分析, 将仿真实验得到的数据作为其训练样本数据。处理与归一化这些数据后,把他们作为神经网络的输入,经过学习与训练,最终可以识别系统的故障类型。
通过MATLAB软件,并通过对BP神经网络基本原理的概要介绍,说明建立基于BP网络的故障诊断架构,并通过实验得到足够的样本数据来训练神经网络,,从而实现了对电机的诊断。本文建立的BP神经网络故障诊断系统一种颇具成效的故障诊断方法,技术也日臻成熟,对于三相异步电动机的故障诊断研究具有重要的参考价值。
关键词:异步电动机 ; 故障诊断; BP 神经网络;matlab
The faults diagnosis of asynchronous motorsbased on BP neural network
Abstract: With the rapid development of the economy in our country , electrification is used more and more widely, asynchronous motors have been widely applied in industrial production in various fields because of its economy, high efficiency . If the motors failure, it will cause a great loss to the production activity and people's life, so the fault diagnosis of motor has the important significance in reality.
Firstly, the classification, the application and prospects of the neural network is introduced, and the structure of asynchronous motor, the basic working principle, the fault classification and diagnosis of the motor is proposed. Aimed at the faults of three-phase asynchronous motors like a ground fault, Introduces one method of fault diagnosis based on BP neural network, then takes advantage of FFT analysis, the frequency information of vibration which is achieved from the experiment is used as the training sample of neural network. Then using these characteristic parameters as the inputs of the neura1 network,through studying and training, recognizes the type of fault.
Through the MATLAB and the principle of the BP neural network, the fault diagnosis based on BP network architecture is proposed,.By selecting enough fault samples to train neural network, the diagnosis of motor is realized. The fault type of the BP neural network established in this paper can accurately and efficiently diagnose motor, as well as is a kind of e..
1.88万字
我自己原创的毕业论文,仅在本站独家提交,大家放心使用
目 录
第一章 绪论………………………………………………………………………1
1.1神经网络……………………………………………………………………… 1
1.1.1 神经网络分类及简单介绍………………………………………………… 1
1.1.2 BP神经网络…………………………………………………………………………5
1.2异步电动机工作原理及用途………………………………………………… 8
1.3异步电动机常见故障类型及方法…………………………………………… 8
1.3.1异步电动机常见故障类型………………………………………………… 9
1.3.2异步电动机电气故障分析………………………………………………………………9
1.4电动机故障诊断的主要方法……………………………………………………11
1.4.1基于人工神经网络故障诊断…………………………………………………13
1.4.2基于专家系统故障诊断………………………………………………………13
1.4.3基于信息融合技术故障诊断…………………………………………………14
1.4.4基于小波变换故障诊断………………………………………………………14
第二章异步电动机在MATLAB中的建模仿真及故障设置……………….16
2.1 BP神经网络在异步电机故障诊断中的应用……………………………………………..15
2.2异步电动机在MATLAB中的建模(频谱法)………………………………… 16
2.2.1选择并搭建模块………………………………………………………………….16
2.2.2模块参数设定…………………………………………………………………….19
2.3三相异步电动机故障设置及故障特征提取………………………………………22
第三章BP网络异步电动机故障诊断实例………………………………….23
3.1 BP神经网络算法的原理……………………………………………………………28
3.1.1人工神经元的模型……………………………………………………………… 28
3.1.2 BP 神经网络算法的原理…………………………………………………………28
3.2 BP神经网络的构建………………………………………………………………… 29
3.2.1 输入输出神经元数确定………………………………………………………… 29
3.2.2.隐含层层数的确定……………………………………………………………… 29
3.3 BP网络训练与测试………………………………………………………………. 30
第四章 总结与展望…………………………………………………………….40
4.1 总结……………………………………………………………………………………………40
4.2 展望………………………………………………………………………………………………41
致谢……………………………………………………………………………42
参考文献………………………………………………………………………43
摘要:近年来由于我国经济迅速发展,电气设备的应用范围逐步由城市转向农村,三相异步电动机因其物美价廉的特点,被普遍应用于工业生产的各个领域。如果电机故障,将给人们的生产和生活造成巨大损失,因此电动机故障诊断具有重要的现实意义。
首先,神经网络,分类的原则,应用和前景进行了介绍,然后,异步电动机的基本原理,故障分类和故障诊断方法。介绍了一种基于BP神经网络模型的故障诊断方法,着重对异步电动机各相接地短路故障,利用FFT频谱法分析, 将仿真实验得到的数据作为其训练样本数据。处理与归一化这些数据后,把他们作为神经网络的输入,经过学习与训练,最终可以识别系统的故障类型。
通过MATLAB软件,并通过对BP神经网络基本原理的概要介绍,说明建立基于BP网络的故障诊断架构,并通过实验得到足够的样本数据来训练神经网络,,从而实现了对电机的诊断。本文建立的BP神经网络故障诊断系统一种颇具成效的故障诊断方法,技术也日臻成熟,对于三相异步电动机的故障诊断研究具有重要的参考价值。
关键词:异步电动机 ; 故障诊断; BP 神经网络;matlab
The faults diagnosis of asynchronous motorsbased on BP neural network
Abstract: With the rapid development of the economy in our country , electrification is used more and more widely, asynchronous motors have been widely applied in industrial production in various fields because of its economy, high efficiency . If the motors failure, it will cause a great loss to the production activity and people's life, so the fault diagnosis of motor has the important significance in reality.
Firstly, the classification, the application and prospects of the neural network is introduced, and the structure of asynchronous motor, the basic working principle, the fault classification and diagnosis of the motor is proposed. Aimed at the faults of three-phase asynchronous motors like a ground fault, Introduces one method of fault diagnosis based on BP neural network, then takes advantage of FFT analysis, the frequency information of vibration which is achieved from the experiment is used as the training sample of neural network. Then using these characteristic parameters as the inputs of the neura1 network,through studying and training, recognizes the type of fault.
Through the MATLAB and the principle of the BP neural network, the fault diagnosis based on BP network architecture is proposed,.By selecting enough fault samples to train neural network, the diagnosis of motor is realized. The fault type of the BP neural network established in this paper can accurately and efficiently diagnose motor, as well as is a kind of e..