Gain characteristics estimation of heteromorphic RFID antennas using neuro‐space mapping. Issue 13 (4th September 2020)

• Record Type: Journal Article
• Authors: Shi, Weiguang; Gao, Junchao; Cao, Yu; Yu, Yang; Liu, Penghui; Ma, Yongtao; Ni, Chunya; Yan, Shuxia
• Is Part Of: IET microwaves, antennas & propagation. Volume 14:Issue 13(2020)
• Page Start: 1555
• Page End: 1565
• Publication Date: 2020-09-04
• Subjects: particle swarm optimisation -- neural nets -- data acquisition -- radiofrequency identification; gain estimation model -- RF antennas -- gain characteristics estimation -- heteromorphic RFID antennas -- gain estimation methods -- radio frequency antennas -- rigorous facilities -- expensive experimental facilities -- classic structure -- application scopes -- accessible method -- heteromorphic RF identification antennas -- main innovations -- estimation framework -- neuro‐space mapping technique -- time consumption -- laborsome measurement processes -- diverse extraction integration strategy -- training data acquisition -- estimation accuracy -- training data size -- adaptive particle swarm optimiser -- scale elaboration strategy; Microwaves -- Periodicals; Microwave antennas -- Periodicals; Antennas (Electronics) -- Periodicals; Radio wave propagation -- Periodicals; Microwave communication systems -- Periodicals; 621.381305
• DOI: 10.1049/iet-map.2020.0105
• Languages: English
• ISSNs: 1751-8725

Abstract

Abstract : Existing gain estimation methods for radio frequency (RF) antennas often rely on rigorous and expensive experimental facilities or are only implemented for classic structure. They perform limited application scopes. To address the challenges, this study provides an accessible method for gain estimation of heteromorphic RF identification (RFID) antennas. There are three main innovations in the proposed method. An estimation framework is proposed based on neuro‐space mapping technique which effectively reduces the time consumption and avoids laborsome measurement processes. A diverse extraction integration strategy is designed for training data acquisition, to balance the estimation accuracy and the training data size. A new adaptive particle swarm optimiser embedded with scale elaboration strategy is developed, which tackles the approximation problem from the gain estimation model to the gain from high‐fidelity simulations. The proposed method is tested by four types of RF antennas. Simulations results demonstrate the method possesses high accuracy and strong applicability.