欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
特征提取与特征选择是实现轴承故障诊断的关键。针对特征提取,首先将轴承振动加速度信号进行经验模态分解(empirical mode decomposition,简称EMD),得到一组固有模态函数(intrinsic mode function,简称IMF),计算各IMF的能量和IMF矩阵的奇异值分布,采用Shannon熵、Renyi熵度量能量和奇异值分布,同时提取原信号的部分统计特征共同构成原始特征子集;针对特征选择,采用遗传算法(genetic algorithm,简称GA)和最小二乘支持向量机(least square supportvector machine,简称LS-SVM)的Wrapper方法选择最优特征子集。在实际轴承故障诊断中的应用,表明文中所提方法的有效性。
英文摘要：
Feature extraction and selection are the most important step for bearing diagnosis.A method based on the empirical mode decomposition(EMD) and GA-SVM(genetic algorithm-support vector machine) is proposed.Firstly, in order to extract the features from the signal,the bearing vibration signals are decomposed to several intrinsic mode functions(IMF).The energy of every IMF and the singular value of the IMF matrix were calculated as features.The Shannon and Renyi entropy of the energy and singular value distribu...
同期刊论文项目
同项目期刊论文
期刊信息
位置：