摘要
针对有源电力滤波器APF(active power filter)逆变器中IGBT易发生故障的问题,对APF中IGBT开路故障的仿真、故障分类、特征提取、故障诊断等方面进行了研究。对IGBT开路故障与故障特征进行了分析,提出了一种基于快速傅里叶变换(FFT)和神经网络的APF故障诊断方法,用FFT提取的故障特征向量来训练神经网络,并将训练好的神经网络诊断系统对IGBT开路故障进行了测试。实验结果表明,该诊断方法能用于APF运行状态监测,并可快速有效地识别IGBT故障位置。
Aiming at the easily damaged characteristic of IGBT in the inverter, simulation, fault classification, feature extraction and fault diagnosis of IGBT open circuit fault in active power filter(APF) were researched. After the analysis of IGBT open circuit fault and fault fea- ture, a method was presented to diagnose the fault of APF based on fast fourier transform (FFT) and neural network, the BP network was trained with fault feature vector, and the well-trained neural network was tested by IGBT open circuit fault. The experimental results indicate that the diagnosis method can monitor the condition of APF and effectively identify the fault location of IGBT.
出处
《机电工程》
CAS
2014年第11期1495-1498,共4页
Journal of Mechanical & Electrical Engineering
基金
国家自然科学基金资助项目(61205076)
国家科技部政府间科技合作资助项目(2009014)
关键词
有源电力滤波器
故障诊断
快速傅里叶变换
神经网络
active power filter(APF)
fault diagnosis
fast fourier transform(FFF)
neural network