Enhancing Open End Winding Induction Motor Performance for Fault-Tolerant All-Wheel Drive EVs with ANN-Based DTC

Kaif Ahmed Lodi; Abdul R. Beig; Khaled Ali Al Jaafari

doi:10.1109/TTE.2025.3566711

Enhancing Open End Winding Induction Motor Performance for Fault-Tolerant All-Wheel Drive EVs with ANN-Based DTC

Electrical Engineering

Research output: Contribution to journal › Article › peer-review

6 Scopus citations

Abstract

This paper presents an advanced control strategy for all-wheel drive (AWD) electric vehicles (EVs) based on artificial neural network (ANN)-enhanced direct torque control (DTC) for open-end winding induction motors (OEWIMs). The proposed ANN dynamically adapts to various inverter faults by optimally utilizing asymmetric voltage vectors, eliminating the need for fault-specific control mechanisms. The proposed control was validated under the FTP 75 drive cycle, demonstrating stable vehicle operation and delivers maximum available torque during faults by adjusting the flux trajectory. The experimental results demonstrate stable and improved EV operation under normal and fault conditions throughout the drive cycles.

Original language	British English
Journal	IEEE Transactions on Transportation Electrification
DOIs	https://doi.org/10.1109/TTE.2025.3566711
State	Accepted/In press - 2025

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

artificial neural network
direct torque control
Electric drives
model predictive control
multi-level converter
open-end winding induction motor

Access to Document

10.1109/TTE.2025.3566711

Cite this

@article{7d8e62bd4bda4e619102f50d04bb190f,

title = "Enhancing Open End Winding Induction Motor Performance for Fault-Tolerant All-Wheel Drive EVs with ANN-Based DTC",

abstract = "This paper presents an advanced control strategy for all-wheel drive (AWD) electric vehicles (EVs) based on artificial neural network (ANN)-enhanced direct torque control (DTC) for open-end winding induction motors (OEWIMs). The proposed ANN dynamically adapts to various inverter faults by optimally utilizing asymmetric voltage vectors, eliminating the need for fault-specific control mechanisms. The proposed control was validated under the FTP 75 drive cycle, demonstrating stable vehicle operation and delivers maximum available torque during faults by adjusting the flux trajectory. The experimental results demonstrate stable and improved EV operation under normal and fault conditions throughout the drive cycles.",

keywords = "artificial neural network, direct torque control, Electric drives, model predictive control, multi-level converter, open-end winding induction motor",

author = "Lodi, \{Kaif Ahmed\} and Beig, \{Abdul R.\} and Jaafari, \{Khaled Ali Al\}",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.",

year = "2025",

doi = "10.1109/TTE.2025.3566711",

language = "British English",

journal = "IEEE Transactions on Transportation Electrification",

issn = "2332-7782",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Enhancing Open End Winding Induction Motor Performance for Fault-Tolerant All-Wheel Drive EVs with ANN-Based DTC

AU - Lodi, Kaif Ahmed

AU - Beig, Abdul R.

AU - Jaafari, Khaled Ali Al

PY - 2025

Y1 - 2025

N2 - This paper presents an advanced control strategy for all-wheel drive (AWD) electric vehicles (EVs) based on artificial neural network (ANN)-enhanced direct torque control (DTC) for open-end winding induction motors (OEWIMs). The proposed ANN dynamically adapts to various inverter faults by optimally utilizing asymmetric voltage vectors, eliminating the need for fault-specific control mechanisms. The proposed control was validated under the FTP 75 drive cycle, demonstrating stable vehicle operation and delivers maximum available torque during faults by adjusting the flux trajectory. The experimental results demonstrate stable and improved EV operation under normal and fault conditions throughout the drive cycles.

AB - This paper presents an advanced control strategy for all-wheel drive (AWD) electric vehicles (EVs) based on artificial neural network (ANN)-enhanced direct torque control (DTC) for open-end winding induction motors (OEWIMs). The proposed ANN dynamically adapts to various inverter faults by optimally utilizing asymmetric voltage vectors, eliminating the need for fault-specific control mechanisms. The proposed control was validated under the FTP 75 drive cycle, demonstrating stable vehicle operation and delivers maximum available torque during faults by adjusting the flux trajectory. The experimental results demonstrate stable and improved EV operation under normal and fault conditions throughout the drive cycles.

KW - artificial neural network

KW - direct torque control

KW - Electric drives

KW - model predictive control

KW - multi-level converter

KW - open-end winding induction motor

UR - https://www.scopus.com/pages/publications/105004601117

U2 - 10.1109/TTE.2025.3566711

DO - 10.1109/TTE.2025.3566711

M3 - Article

AN - SCOPUS:105004601117

SN - 2332-7782

JO - IEEE Transactions on Transportation Electrification

JF - IEEE Transactions on Transportation Electrification

ER -

Enhancing Open End Winding Induction Motor Performance for Fault-Tolerant All-Wheel Drive EVs with ANN-Based DTC

Abstract

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this