AI-Integrated Sensorless Control of BLDC Motors for Energy-Efficient Electric Vehicles

Abstract

Electric Vehicles (EVs) are gaining prominence as a sustainable and eco-friendly mode of transportation. Brushless DC (BLDC) motors are widely implemented in EVs due to their high efficiency, compact size, and operational reliability. Conventional BLDC motor control methods depend on mechanical sensors, which not only raise costs but also introduce potential points of failure. The proposed sensorless control strategy addresses these limitations by eliminating mechanical sensors, thereby improving reliability and reducing overall system costs. This study introduces an advanced control framework that integrates Artificial Neural Networks (ANN), Fuzzy Logic Controllers (FLC), and Machine Learning (ML) techniques for accurate rotor position estimation—an essential factor for optimizing BLDC motor performance in EVs. ANN provides adaptive learning for complex nonlinear relationships, FLC enables robust decision-making under uncertainty, and ML supports predictive modeling for performance enhancement. The paper emphasizes theoretical design, control logic, and integration of these AI-driven methods within the Sensorless control architecture, without dependence on physical prototypes or simulations. The proposed conceptual framework offers a foundation for future simulation or hardware validation, highlighting its cost-effectiveness, scalability, and robustness for next-generation EV applications.