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：
提出了一种基于小波包分析（WPA）和支持向量机（SVM）的异步电机转子断条故障诊断方法。针对异步电机转子断条故障时定子电流出现的边频分量（1＋2s）f进行小波包分析，提取动态条件下各频带能量作为故障特征向量，削弱了负载变化及噪声对诊断准确性的影响。采用多个最小二乘支持向量机组成故障分类器，兼顾了训练误差和计算效率，将故障特征向量输入支持向量机进行训练，从而实现在小样本情况下转子断条故障的在线识别。试验结果表明：基于小波包分析提取的故障特征明显，由WPA和SVM构成的诊断系统，具有良好的分类能力和泛化能力，有效提高了异步电机转子断条故障在线诊断的准确率。
英文摘要：
A fault diagnosis method was presented for motor rotor broken bar fault based on wavelet packet analysis （WPS） and support vector machine （SVM）. The sideband frequency （1 ＋2s ）f current reflecting the broken bar fault was analyzed with the technology of wavelet packet decomposition. The frequency segment power under operating states was abstracted as fault characteristic vectors which weakened the influences of variable load and noise. In order to diagnose the rotor broken bar fault under small samples, the fault elassifiier was composed by the least square SVMs trained by the fault characteristic vectors. And it also took the training errors and the calculating efficiency into consideration. Experimental results show that the fault characteristic vectors abstracted by WPA are evident. This method has good classification and generalization abilities, and improves the accuracy of detection for rotor broken bar fault in induction machines.
同期刊论文项目
同项目期刊论文
Design of test stimuli and minimisation of ambiguity in fault diagnosis of analogue circuits with to
Nonlinear correction of photoelectric displacement sensor based on least square support vector machi
A Novel Localization Algorithm Based on Isomap and Partial Least Squares for Wireless Sensor Network
Analysis of Electromagnetic Force Distribution on End winding of Electrical Submersible Motor During
期刊信息
位置：