A comparison of various open-circuit fault detection methods in the IGBT-based DC/AC inverter used in electric vehicle. (February 2019)

• Record Type: Journal Article
• Authors: Moosavi, S.S.; Kazemi, A.; Akbari, H.
• Is Part Of: Engineering failure analysis. Volume 96(2019)
• Page Start: 223
• Page End: 235
• Publication Date: 2019-02
• Subjects: Voltage source inverter (VSI) -- Fault detection -- Open-circuit fault -- Artificial Intelligent (AI) -- Super vector machine (SVM) -- Discrete wavelet transform (DWT); System failures (Engineering) -- Periodicals; Fracture mechanics -- Periodicals; Reliability (Engineering) -- Periodicals; Pannes -- Périodiques; Rupture, Mécanique de la -- Périodiques; Fiabilité -- Périodiques; Fracture mechanics; Reliability (Engineering); System failures (Engineering); Periodicals; Electronic journals; 620.112
• DOI: 10.1016/j.engfailanal.2018.09.020
• Languages: English
• ISSNs: 1350-6307

Abstract

Abstract: Fault detection can increase the reliability and efficiency of power electronic converters employed in the power systems. Among the converters in the power system, voltage source inverters are used to drive electric motors. Due to high pressure and complex work in this environment, these inverters are prone to breakdowns and faults. That's why providing a way to recognize faults in the inverters is very important. This article studies the open-circuit fault of IGBT in an electric vehicle in dynamic conditions. The three-phase current and wavelet transform is used to identify the state of the system and extracting the current waveform. MLP Neural network algorithms, SVM, SOM, and K-means is used to detect and classify the faults. A comparison of various algorithms used in this paper was done. Electric vehicles have been studied and analyzed in 5 dynamics and 5 static modes in a total of 220 fault cases. The results show the detection and recognition of all forms of faults.