Offline artificial neural network rotor flux estimator for induction motor

• Main Authors: Siti Nursyuhada, Mahsahirun, Zulkifli, Md Yusof, Nik Rumzi, Nik Idris
• Format: Conference or Workshop Item
• Language: English; English
• Published: Institute of Electrical and Electronics Engineers Inc. 2020
• Subjects: T Technology (General); TA Engineering (General). Civil engineering (General); TJ Mechanical engineering and machinery; TK Electrical engineering. Electronics Nuclear engineering; TS Manufactures
• Online Access: http://umpir.ump.edu.my/id/eprint/42436/1/Offline%20artificial%20neural%20network%20rotor%20flux%20estimator.pdf; http://umpir.ump.edu.my/id/eprint/42436/2/Offline%20artificial%20neural%20network%20rotor%20flux%20estimator%20for%20induction%20motor_ABS.pdf; http://umpir.ump.edu.my/id/eprint/42436/; https://doi.org/10.1109/IICAIET49801.2020.9257845

Rotor flux is an important parameter in field-oriented control of induction motor (IM). It can be obtained through direct physical measurement at the air-gap or indirectly by using estimators. In this paper, the feedforward Artificial Neural Network (ANN) model for rotor flux estimation is proposed and analyzed. The network is trained using equivalent circuit model data and the Levenberg-Marquardt algorithm. The result shows that the proposed ANN rotor flux estimator is able to perform IM rotor flux estimation with 2.99e-05 MSE.