没有合适的资源?快使用搜索试试~ 我知道了~
基于多尺度卷积神经网络的故障诊断方法研究.doc
1.该资源内容由用户上传,如若侵权请联系客服进行举报
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
版权申诉
5星 · 超过95%的资源 1 下载量 163 浏览量
2023-09-10
15:53:34
上传
评论
收藏 4.05MB DOC 举报
温馨提示
试读
89页
基于多尺度卷积神经网络的故障诊断方法研究.doc
资源推荐
资源详情
资源评论
I
摘 要
在现代工业生产设备不断朝着结构化、自动化和智能化方向发展的过程中,
电机仍是主要的动力输出设备。若电机在运行过程中出现故障,会导致其运行效
率降低,系统能耗上升等问题,严重时甚至造成电机损坏,使整体系统设备长时
间停机维修,造成严重的经济损失。因此,研究电机智能故障诊断技术,对保障
生产设备高效运行的稳定性、可靠性具有重要意义。随着科技的不断创新和发展,
信号处理、人工智能等技术不断取得突破,故障诊断技术也更加精确化、智能化。
本文结合实际生产过程中常见的电机变工况和强噪声环境下的故障诊断问题,在
分析故障产生机理的基础上对电机智能故障诊断方法展开深入研究。
(1) 首先利用试验台采集的振动信号对电机不同故障的产生机理进行分析,
探究其处于故障状态时的振动频率特性。在此基础上,研究基于信号处理和机器
学 习 算 法 的 故 障 诊 断 方 法 , 分 析 经 验 模 态 分 解 (Empirical Mode
Decomposition,EMD)存在的优势和不足,利用其改进算法集合经验模态分解
(Ensemble Empirical Mode Decomposition,EEMD)对信号进行分解,得到反映原始
信号不同频率成分的本征模态函数(Intrinsic Mode Function.IMF)分量,通过相关
性与原始信号相关系数较高前 4 阶 IMF 分量,最后对其进行谱分析得到多个序
列作为样本信号用于特征提取。
(2) 对多序列样本信号中 9 种不同的时、频域统计特征进行计算,得到原始
特征集,并在对其采用聚类算法分析的基础上,提出一种基于调整互信息和标准
差的敏感特征选择方法,从原始特征集筛选特征构建敏感特征集用于电机故障诊
断。并且,针对特征集中存在的特征干扰、冗余等问题,提出利用特征降维方法
实现对特征的维数约简。最后分别利用支持向量机(Support Vector Machines,SVM)
和极限学习机(Extreme Learning Machine,ELM)两种较为流行的机器学习算法实
现电机故障诊断,并通过对比实验进行验证。
(3) 针对基于信号处理的传统智能故障诊断方法中存在的流程复杂、人为干
预过多的问题,研究端到端式的卷积神经网络算法用于电机故障诊断。针对一维
时序信号的特点,分析一维卷积神经网络(One-Dimensional Convolutional Neural
Network,1D-CNN)在以原始一维振动信号为基础进行故障诊断的优势。为了提取
II
信号中不同尺度的互补特征,提出利用不同尺度核的卷积层提出一种多尺度融合
框架,构建了基于多尺度一维卷积神经网络的电机故障诊断方法。最后通过实验
验证了所提方法在变工况和噪声干扰情况下的优越性。
(4) 为了提升 MS-1DCNN 在电机变工况和强噪声干扰环境下故障诊断方法
的识别效率和准确率,在残差网络结构的基础上构建多尺度特征融合框架。分别
研究挤压与激励(Squeeze and Excitation,SE)模块和卷积注意力模块(Convolutional
Block Attention Module ,CBAM)两种注意力机制算法的实现原理,设计适用于一
维残差网络的注意力模块,并将其嵌入到残差模块中,构建出多尺度注意力残差
网络(Multi-scale attention residual network,MSA-ResNet)模型,最后利用实验台数
据验证所提模型的有效性和优越性。
该论文有图 44 幅,表 18 个,参考文献 92 篇。
关键词:电机;故障诊断;多尺度特征;卷积神经网络;注意力机制
III
Abstract
In the process of modern industrial production equipment continuously moving
towards the direction of structure, automation and intelligence, motors are still the
main power output equipment. Failure of the motor during operation will cause
problems such as reduced operating efficiency and increased system energy
consumption. In severe cases, the motor will be damaged, causing the overall system
equipment to be stopped for maintenance for a long time, causing serious economic
losses. Therefore, the research of motor intelligent fault diagnosis technology is of
great significance for ensuring the stability and reliability of efficient operation of
production equipment. With the continuous innovation and development of science
and technology, breakthroughs have been made in signal processing, artificial
intelligence and other technologies, and fault diagnosis technology has become more
precise and intelligent. The thesis combines the common fault diagnosis problems of
the motor in the actual production process and the fault diagnosis in the strong noise
environment. Based on the analysis of the failure mechanism, the intelligent fault
diagnosis method of the motor is studied in depth.
(1) Firstly, the intelligent fault diagnosis method based on signal processing is
studied, the mechanism of motor fault generation based on vibration signals is
explored. Based on the analysis of the motor fault characteristics under different
operating states, the signal analysis method based on empirical mode decomposition
is studied, and aimed at it Existing modal aliasing is proposed to use set empirical
modal decomposition to analyze the motor vibration signals, select the first 4 orders
of IMF components through correlation analysis and calculate the corresponding
envelope spectrum and marginal spectrum as the feature extracted signal sequence.
(2) Calculate 9 different time and frequency domain statistical features in the
multi-sequence sample signal to obtain the original feature set. Based on the analysis
of the clustering algorithm, a sensitive feature based on adjusting mutual information
and standard deviation is proposed. Select a method to filter features from the original
IV
feature set to construct a sensitive feature set for motor fault diagnosis. In addition, in
view of the problems of feature interference and redundancy in the feature set, a
feature dimension reduction method is proposed to reduce the feature dimension.
Finally, two more popular machine learning algorithms, Support Vector Machines and
Extreme Learning Machine, are used to implement motor fault diagnosis and verified
by comparison experiments.
(3) Aiming at the problems of complicated processes and excessive human
intervention in traditional intelligent fault diagnosis methods based on signal
processing, the advantages of one-dimensional convolutional neural networks on
one-dimensional time series are analyzed, and faults based on end-to-end 1DCNN
networks are studied. A diagnostic method and a multi-scale feature fusion framework
using convolutional layers with different scale kernels are proposed. A multi-scale
one-dimensional convolutional neural network based motor fault diagnosis method is
constructed. Finally, the superiority of the proposed method under variable operating
conditions and noise interference is verified through experiments.
(4) In order to improve the recognition efficiency and accuracy of the fault
diagnosis method under variable operating conditions and strong noise interference
environment, a multi-scale feature fusion framework is built on the basis of the
residual network structure. Study the algorithm implementation principle of attention
mechanism, design the attention module suitable for one-dimensional residual
network, and embed it in the residual module to build a multi-scale attention residual
network model. Finally, the validity and superiority of the proposed model are
verified using experimental bench data.
The article has 40 figures, 18 tables and 92 references.
Keywords: motor; fault diagnosis; multi-scale features; convolutional neural network;
attention mechanism
V
剩余88页未读,继续阅读
资源评论
- 星,尘光2024-04-22资源很实用,对我启发很大,有很好的参考价值,内容详细。
南抖北快东卫
- 粉丝: 70
- 资源: 5584
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功