摘要
在对一级齿轮箱的振动信号进行快速傅里叶变换和小波包变换的基础上,提取各个小波包系数的峭度和偏态,并选择分辨率较高的小波包系数的峭度和偏态作为齿轮裂纹的故障特征。最后通过基于粒子群优化算法(Particle swarm optimization,PSO)的支持向量机(Support vector machine,SVM)模型进行齿轮裂纹故障特征分类,其中,PSO主要用来优化SVM模型的核函数的关键参数,避免出现局部最优和过拟合的问题。计算结果表明,和其它算法相比,提出的齿轮裂纹故障诊断方法在分类精度和计算效率方面具有综合优势。
On the basis of fast Fourier transform and wavelet packet transform,the kurtosis and skewness of each wavelet packet coefficient are extracted,and the kurtosis and skewness of wavelet packet coefficient with higher resolution are selected as fault features of gear cracks.Finally,the support vector machine(SVM)model based on particle swarm optimization(PSO)is used to classify the fault features of gear cracks.PSO is mainly used to optimize the key parameters of the kernel function of SVM model,avoiding the problems of local optimization and over fitting.The results show that,compared with other algorithms,the method proposed in this paper has comprehensive advantages in classification accuracy and calculation efficiency.
作者
王二化
刘忠杰
刘颉
WANG Er-hua;LIU Zhong-jie;LIU Jie(Changzhou City Lab of Intelligent Technology for Advanced Manufacturing Equipment,Changzhou College of Information Technology,Changzhou Jiangsu 213164,China;School of Hydropower and Information Engineering,Huazhong University of Science and Technology,Wuhan 430074,China)
出处
《组合机床与自动化加工技术》
北大核心
2021年第4期126-129,共4页
Modular Machine Tool & Automatic Manufacturing Technique
基金
常州市高端制造装备智能化技术重点实验室(CM20183004)
江苏省青蓝工程中青年学术带头人,2019年江苏省高等教育教改研究课题““双高”背景下高水平专业群建设的理论与实践研究”(2019JSJG431)
2020年江苏高校“青蓝工程”优秀青年骨干教师项目资助,常州信息职业技术学院“1+1+1”协同培育工程建设项目。
关键词
齿轮裂纹
故障诊断
小波包变换
支持向量机
粒子群优化
gear crack
fault diagnosis
wavelet packet transform
support vector machine
particle swarm optimization
