ABSTRACT
Electric drives are widely used in electric vehicles, robotics, industries, and renewable energy systems. Conventional control methods like PI, PID, vector control, and direct torque control are effective but they suffer from parameter sensitivity, nonlinearity issues, and performance degradation under uncertainties. In recent years, Artificial Intelligence (AI) and Machine Learning (ML) techniques are increasingly applied for improving the performance of electric drive control. Intelligent controllers such as fuzzy logic, artificial neural networks, genetic algorithms, reinforcement learning, and deep learning provide adaptive, self learning, and robust control under varying operating conditions. This paper presents a detailed review of AI/ML-based intelligent control strategies used in electric drives, highlighting their principles, advantages, limitations, and real-time implementation challenges. Comparative analysis with conventional controllers is also discussed. The study aims to provide a comprehensive understanding for researchers working on next generation smart drives.
KEYWORDS: Electric drives, Intelligent control, Artificial Neural Network, Fuzzy logic, Reinforcement learning, Sensorless control, AI in drives
Full Issue
| View or download the full issue | PDF 48-60 |