Work

Non-Contact Resistance Prediction of SWCNT-Coated Conductive Fabrics with Color Variations Using Residual Neural Network

Year: 2025

Type: article

Abstract: This study proposes a Residual Neural Network (ResNet) Convolutional Neural Network (CNN) model for predicting the resistance of colorized conductive fabrics (white, red, green, and blue) fabricated through the Single-Walled Carbon Nanotube dip-coating process using a non-contact image analysis approach. The Analysis of Variance (ANOVA) resulted in a p-value of 2.48426 × 10−8, confirming a statistically significant relationship between the brightness and resistance of conductive fabrics. Histogram equalization preprocessing was applied to enhance the efficiency of model training. The ResNet model achieved an RMSE of 0.0622 and a coefficient of determination of 0.941585, demonstrating approximately a 58% improvement in performance compared to the baseline CNN. The non-contact resistance evaluation method proposed in this study opens new possibilities for the development of wearable electronic devices and smart textiles, offering a foundational approach for real-time process monitoring and automated quality control in manufacturing.

Source: Processes

DOI: 10.3390/pr13040959

Authors: Erin Kim, Sang-Un Kim, Jong-Chan Lee, Minji Jeong, Joo-Yong Kim

Institution: Soongsil University

Language: English

Topic: Industrial Vision Systems and Defect Detection

Subfield: Industrial and Manufacturing Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,896

Funder: Ministry of Trade, Industry and Energy