摘要
人工智能技术作为有效手段广泛用于机械系统故障诊断,但故障样本的缺乏严重制约人工智能模型走向高精度诊断的工程应用。针对故障样本不足的问题,提出一种基于小波包分解与高斯云模型的故障诊断方法,通过对小样本的故障信号做小波包分解并计算每个子频带的能量以建立故障特征向量,对特征向量建立高斯云模型并正向云计算生成大量云滴以扩充故障样本。基于凯斯西储大学的轴承数据和支持向量机的故障分类实验结果表明,所提方法能有效扩充故障样本,提高故障诊断精度。
Artificial intelligence technology is widely used in mechanical system fault diagnosis as an effective means,but the lack of fault samples seriously restricts the engineering application of artificial intelligence models to high-precision diagnosis.In order to overcome the lack of fault samples,a fault diagnosis method based on gaussian cloud model and wavelet packet decomposition is proposed.The fault feature vectors are established by decomposing the fault signals of small samples into wavelet packets and calculating the energy of each sub-band.The gaussian cloud model is established for the feature vectors and a large number of cloud drops are generated by positive cloud computing to expand the fault samples.The experimental results based on the bearing data of Case Western Reserve University and support vector machine show that the proposed method can effectively expand the fault samples and improve the fault diagnosis accuracy.
作者
窦唯
刘晓阳
Dou Wei;Liu Xiaoyang(Beijing Aerospace Propulsion Institute,Beijing,100076,China;Cryogenic Liquid Propulsion Technology Laboratory of China Aerospace Science and Technology Co.,Ltd.,Beijing,100076,China;School of Mechatronic Engineering and Automation,Shanghai University,Shanghai,200444,China)
出处
《机械设计与制造工程》
2023年第1期107-111,共5页
Machine Design and Manufacturing Engineering
基金
国防技术基础科研项目(JSZL2019203A003)。
关键词
小波包分解
高斯云模型
样本扩充
支持向量机
故障诊断
wavelet packet decomposition
gauss cloud model
sample expansion
support vector machines
faults diagnosis