Artificial Neural Network Modeling of Meander Lines for Delay based Applications
Kah Seng Sam1, Chan Hong Goay2, Nur Syazreen Ahmad3, Patrick Goh4
1Kah Seng Sam, Department of Electrical and Electronic Engineering, University Sains Malaysia, Nibong Tebal, Penang, Malaysia.
2Chan Hong Goay, Department of Electrical and Electronic Engineering, University Sains Malaysia, Nibong Tebal, Penang, Malaysia.
3Nur Syazreen Ahmad, Department of Electrical and Electronic Engineering, University Sains Malaysia, Nibong Tebal, Penang, Malaysia.
4Patrick Goh, Department of Electrical and Electronic Engineering, University Sains Malaysia, Nibong Tebal, Penang, Malaysia.
Manuscript received on 21 August 2019 | Revised Manuscript received on 11 September 2019 | Manuscript Published on 17 September 2019 | PP: 1372-1377 | Volume-8 Issue-2S8 August 2019 | Retrieval Number: B10690882S819/2019©BEIESP | DOI: 10.35940/ijrte.B1069.0882S819
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This paper presents the application of artificial neural networks (ANNs) for meander line modeling. In this work, meander lines on microstrips will be investigated to determine a correlation between the physical parameters and the propagation delay of the lines. The simulation of the meander lines is done using the Momentum electromagnetics simulator in Keysight’s Advanced Design System (ADS) to generate the S-parameters which will be used in a transient simulation to determine the propagation delay. Neural network models are then created for propagation delay prediction. Finally, both the ADS and ANN results for simulated delay times of meander lines are compared to validate the performance and to justify the proposed method. Results show that the ANN model is able to accurately predict the delay of the meander lines with an accuracy above 99.5% with a speed-up of over 2000×.
Keywords: Artificial Neural Network, Meander Lines, Propagation Delay, S-Parameter.
Scope of the Article: Network Architectures