Kumar, Shahil and Malai, Michael and Kororua, Ganitoga and Groza, Voicu and Assaf, Mansour and Kumar, Rahul R. (2023) Synchronous Machine Modelling Using Linear Regression Approaches. [Conference Proceedings]
Full text not available from this repository.Abstract
Synchronous motors (SMs) play an important role in various industrial applications due to their unique characteristics and advantages. One of the key advantages of a synchronous motor (SM) is its ability to operate at a constant speed, making them suitable for applications where precise speed control is required. SMs also have a high-power factor, which means they consume less reactive power. The excitation current of a SM is crucial for optimal motor performance and efficiency, as insufficient current can reduce speed and power output while excessive current can overheat the motor and reduce efficiency. Thus, it is essential to estimate the excitation current of a SM. Accurate estimation and control of the excitation current can be achieved through synchronous machine data modeling. The study showcases the estimation of the excitation current of a SM using regression-based approaches. In particular, the usage of Principal Component Analysis has generally improved the performance of the regression models. The best models belong to the family of Linear Regressors as highlighted in the results.
Item Type: | Conference Proceedings |
---|---|
Uncontrolled Keywords: | Reactive power;Analytical models;Linear regression;Velocity control;Estimation;Predictive models;Synchronous motors;Neural networks;Regression learner;Principal Component Analysis |
Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science T Technology > TK Electrical engineering. Electronics Nuclear engineering |
Divisions: | School of Information Technology, Engineering, Mathematics and Physics (STEMP) |
Depositing User: | Rahul Kumar |
Date Deposited: | 07 Mar 2024 21:15 |
Last Modified: | 14 Mar 2024 22:54 |
URI: | https://repository.usp.ac.fj/id/eprint/14454 |
Actions (login required)
View Item |