Premium
Optimization of wireless power transfer using artificial neural network: A review
Author(s) -
Ali Azuwa,
Mohd Yasin Mohd Najib,
Jusoh Muzammil,
Ahmad Hambali Nor Azura Malini,
Abdul Rahim Siti Rafidah
Publication year - 2020
Publication title -
microwave and optical technology letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.304
H-Index - 76
eISSN - 1098-2760
pISSN - 0895-2477
DOI - 10.1002/mop.32089
Subject(s) - wireless power transfer , artificial neural network , wireless , computer science , electronic engineering , process (computing) , engineering , control engineering , artificial intelligence , telecommunications , operating system
Wireless power transfer (WPT) is widely explored and applied nowadays because of its simplicity in transferring power without using wire, easy maintenance, and equipment mobility. Due to mobility and compatibility attributes, WPT is utilized in powering biomedical devices, small electronic equipment, wireless sensor, mobile phones, and high voltage applications (eg, electric vehicles). The implementation of artificial neural network (ANN) in WPT has emerged as a powerful/prominent tool for estimating the performance parameters due to its learning and significant features. Such implementation can minimize design complexity and time‐consuming calculations. An early application of ANN employs the information derived from the collectively measured processes for training the ANN algorithm. After a suitable training process, the network output can be considered in place of computationally thorough representations to speed up the result search. To obtain precise result and optimize the parameters in WPT, several popular ANN algorithms have been used by researchers. This review paper highlighted the latest research specifically regarding the implementation of ANN in WPT, which included the types of ANN implemented in WPT, current WPT problem investigation that used ANN, and a comparison between the techniques. Moreover, the challenges and constraints of ANN techniques were elucidated at the end of this paper.