期刊
IEEE TRANSACTIONS ON POWER ELECTRONICS
卷 35, 期 12, 页码 13281-13294出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TPEL.2020.2994351
关键词
Circuit faults; Insulated gate bipolar transistors; Inverters; Fault diagnosis; Voltage control; Observers; Pulse width modulation; Fault diagnosis; insulated gate bipolar transistor (IGBT) open-circuit fault; random vector functional link (RVFL) network; sensor fault; three-phase pulsewidth modulation (PWM) inverter
资金
- National Natural Science Foundation of China [51907163, U1934204]
- Chengdu Guojia Electrical Engineering Corporation, Ltd. [NEEC-2017-B06]
This article presents an online data-driven diagnosis method for multiple insulated gate bipolar transistors (IGBTs) open-circuit faults and current sensor faults in the three-phase pulsewidth modulation inverter. The fast Fourier transform (FFT) algorithm is used to extract the fault frequency spectrum features of the three-phase currents. Then, a feature selection method named ReliefF is introduced to select the most critical features by removing redundant and irrelevant features. In addition, as novel fast learning technology, a random vector functional link network is applied to learn the faulty knowledge from the historical dataset. Based on the well-learned model, the fault type and location of the converter can be accurately identified as long as the three-phase current signals are measured. Offline test results verify that the proposed method can identify the IGBT and sensor faults with an accuracy of 98.83% and outperforms the state-of-the-art learning algorithms. Moreover, the real-time hardware-in-the-loop test results show that the proposed method can successfully identify the IGBT faults and current sensor faults within 22 ms. It is robust to the dc-link voltage fluctuations, model parameters, and speed or load variations. The extensibility of the proposed method is also validated based on the test results in terms of other fault modes and drive systems.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据