Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

An Empirical Study on Fault Detection and Root Cause Analysis of Indium Tin Oxide Electrodes by Processing S-parameter Patterns

Tae Yeob Kang, Haebom Lee, Sungho Suh

TL;DR

This study develops an in situ fault-diagnosis framework for indium tin oxide (ITO) electrodes using full S-parameter patterns collected from a two-port RF network. By constructing a comprehensive defect-state database (Normal, mechanical M1–M3, photodegradation P1–P3) and applying deep learning models (MLP, CNN, Transformer) to multi-channel inputs such as $S_{11}$ and $S_{21}$, the approach achieves high diagnostic accuracy and simultaneous root-cause analysis without destructive testing. The CNN with fused $S_{11}$ and $S_{21}$ channels reaches $99.12\%$ accuracy at 5 dB noise, and remains robust under 10 dB noise (CNN $87.58\%$, Transformer $83.15\%$), while DC resistance shows limited sensitivity to defect type. This method supports non-destructive, in situ monitoring with potential for online fault detection in optoelectronic devices, reducing repair costs and improving reliability.

Abstract

In the field of optoelectronics, indium tin oxide (ITO) electrodes play a crucial role in various applications, such as displays, sensors, and solar cells. Effective fault diagnosis and root cause analysis of the ITO electrodes are essential to ensure the performance and reliability of the devices. However, traditional visual inspection is challenging with transparent ITO electrodes, and existing fault diagnosis methods have limitations in determining the root causes of the defects, often requiring destructive evaluations and secondary material characterization techniques. In this study, a fault diagnosis method with root cause analysis is proposed using scattering parameter (S-parameter) patterns, offering early detection, high diagnostic accuracy, and noise robustness. A comprehensive S-parameter pattern database is obtained according to various defect states of the ITO electrodes. Deep learning (DL) approaches, including multilayer perceptron (MLP), convolutional neural network (CNN), and transformer, are then used to simultaneously analyze the cause and severity of defects. Notably, it is demonstrated that the diagnostic performance under additive noise levels can be significantly enhanced by combining different channels of the S-parameters as input to the learning algorithms, as confirmed through the t-distributed stochastic neighbor embedding (t-SNE) dimension reduction visualization of the S-parameter patterns.

An Empirical Study on Fault Detection and Root Cause Analysis of Indium Tin Oxide Electrodes by Processing S-parameter Patterns

TL;DR

This study develops an in situ fault-diagnosis framework for indium tin oxide (ITO) electrodes using full S-parameter patterns collected from a two-port RF network. By constructing a comprehensive defect-state database (Normal, mechanical M1–M3, photodegradation P1–P3) and applying deep learning models (MLP, CNN, Transformer) to multi-channel inputs such as and , the approach achieves high diagnostic accuracy and simultaneous root-cause analysis without destructive testing. The CNN with fused and channels reaches accuracy at 5 dB noise, and remains robust under 10 dB noise (CNN , Transformer ), while DC resistance shows limited sensitivity to defect type. This method supports non-destructive, in situ monitoring with potential for online fault detection in optoelectronic devices, reducing repair costs and improving reliability.

Abstract

In the field of optoelectronics, indium tin oxide (ITO) electrodes play a crucial role in various applications, such as displays, sensors, and solar cells. Effective fault diagnosis and root cause analysis of the ITO electrodes are essential to ensure the performance and reliability of the devices. However, traditional visual inspection is challenging with transparent ITO electrodes, and existing fault diagnosis methods have limitations in determining the root causes of the defects, often requiring destructive evaluations and secondary material characterization techniques. In this study, a fault diagnosis method with root cause analysis is proposed using scattering parameter (S-parameter) patterns, offering early detection, high diagnostic accuracy, and noise robustness. A comprehensive S-parameter pattern database is obtained according to various defect states of the ITO electrodes. Deep learning (DL) approaches, including multilayer perceptron (MLP), convolutional neural network (CNN), and transformer, are then used to simultaneously analyze the cause and severity of defects. Notably, it is demonstrated that the diagnostic performance under additive noise levels can be significantly enhanced by combining different channels of the S-parameters as input to the learning algorithms, as confirmed through the t-distributed stochastic neighbor embedding (t-SNE) dimension reduction visualization of the S-parameter patterns.
Paper Structure (11 sections, 2 equations, 13 figures, 2 tables)

This paper contains 11 sections, 2 equations, 13 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Experimental Methodology
  3. Specimen Preparation
  4. Acquisition of S-parameters of ITO electrodes
  5. In-situ fault diagnosis using S-parameter patterns
  6. Implementation Details
  7. Experimental results
  8. Signal measurement results
  9. Quantitative Evaluation on Diagnostic Performance
  10. Qualitative Evaluation on Diagnostic Performance
  11. Conclusion

Figures (13)

  • Figure 1: Major defects in ITO electrodes
  • Figure 2: Simplified structures of optoelectronic devices including ITO electrodes: the ITO electrodes are placed between other layers
  • Figure 3: Fabrication of ITO electrodes and the specimen batch
  • Figure 4: ITO electrodes with various defect states
  • Figure 5: Two-port network of S-parameters comprised of the ITO electrode
  • ...and 8 more figures