Estimation of Induction Motor Power Factor Using Machine Learning

Accurate power factor estimation is essential for optimizing the performance and efficiency of induction motors in industrial applications. This study proposes a machine learning-based model for predicting the power factor of induction motors across various power ratings, leveraging manufacturer data from sources such as ABB and Siemens. The proposed approach utilizes a comprehensive dataset to train and validate the model, ensuring high accuracy in PF estimation for motors ranging from low to high horsepower. A discussion of the machine learning algorithm, including its architecture, feature selection, and training methodology, is provided. The model’s prediction is evaluated by comparing estimated power factor values with actual data. The results underscore the potential of machine learning-driven power factor prediction in enhancing industrial energy efficiency, facilitating informed decision-making in motor selection, power quality management, and energy cost optimization.