An intelligent technique for fault detection and localization of three-level ANPC inverter with NP connection for electric vehicles. (February 2023)

• Record Type: Journal Article
• Authors: Selvakumar, P.; Muthukumaran, G.
• Is Part Of: Advances in engineering software. Volume 176(2023)
• Publication Date: 2023-02
• Subjects: Fault detection -- ANPC inverter -- Fault location -- SVM -- Redundancy -- DNN -- Electric vehicles; Computer-aided engineering -- Periodicals; Engineering -- Computer programs -- Periodicals; Engineering -- Software -- Periodicals; Periodicals; 620.0028553
• DOI: 10.1016/j.advengsoft.2022.103354
• Languages: English
• ISSNs: 0965-9978

Abstract

Highlights: The highlights of the article are given below for your kind perusal. Kindly, consider and forward my article for further processes. This paper introduces an intelligent approach for detecting the faults of an ANPC inverter with NP connection for EVs. This is the first work that utilizes an SVM for detecting the faulty phase and DNN for locating the faulty switch in the 3-level ANPC inverter of EV to enhance the performance. The proposed technique integrates the advantages of both the classifiers for obtaining enhanced performance outcomes. Furthermore, on observing the outcomes, it's clear that the accuracy of the proposed scheme is 0.9222, whereas for all the other conventional methods it's less. This also accounts for a precise fault detection and localization. Abstract: An intelligent technique for detecting and localizing an inverter switch fault or phase fault of a Three-Level Active Neutral Point Clamped (ANPC) inverter is proposed in this research. Moreover, a 3L-ANPC inverter can gain the controllability of EV's power train and not need to be stalled even after the occurrence of the fault. Hence, an efficient fault diagnosis methodology is required to identify the type of phase fault by a Support Vector Machine (SVM), a machine learning model consisting of sets of labeled training data with regression and classification challenges. Finally, when the fault occurs, the location of the switch fault can be identified by a Deep Neural Network (DNN), which consists of layers of neurons between the input and output layers which fuses the feature extraction process with increased accuracy. Thus, the detection and localization of the open-circuit fault of the switches in the ANPC inverter help overcome all single faults, hence gaining its current controllability without stopping the vehicle. The accuracy of fault detection is improved in a precise manner. Finally, the performance of the proposed work is evaluated over other conventional models concerning varied metrics like the accuracy of identification and localization.