Displacement Estimation via 3D-Printed RFID Sensors for Structural Health Monitoring: Leveraging Machine Learning and...

Area of Science:

• Electrical Engineering and Computer Science
• Materials Science
• Structural Engineering

Background:

• Structural Health Monitoring (SHM) relies on accurate object displacement tracking.
• Radio Frequency Identification (RFID) sensors offer a viable solution for displacement monitoring.
• Machine Learning (ML) algorithms improve displacement estimation using RFID data, particularly azimuth angle prediction.

Purpose of the Study:

• To address data gaps in RFID sensor arrays caused by increased sensor numbers, which hinder ML-based displacement estimation.
• To propose a novel photoluminescence-based RF signal enhancement technique for 3D-printed passive RFID sensor arrays.
• To improve the sensitivity and reliability of RFID sensor systems for SHM and other applications.

Main Methods:

• Development and implementation of a photoluminescence-based technique to enhance RF signal strength in passive RFID sensors.
• Integration of 3D-printed passive RFID sensor arrays with the novel enhancement method.
• Evaluation of the technique's effectiveness in boosting received RF signal levels across near-field and far-field propagation modes.

Main Results:

• The photoluminescence technique successfully enhanced received RF signal levels by 2 dB to 8 dB.
• The proposed method effectively mitigated issues related to missing data in RFID sensor arrays.
• No increase in transmit power or sensor count was required to achieve improved data quality.

Conclusions:

• The photoluminescence-based RF signal enhancement is a promising solution for overcoming data gaps in RFID sensor systems.
• This technique enables remote control of radiation patterns, opening new avenues for smart antenna development.
• The approach has significant potential for applications beyond SHM, including biomedicine and aerospace.