Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Non-destructive Fault Diagnosis of Electronic Interconnects by Learning Signal Patterns of Reflection Coefficient in the Frequency Domain

Tae Yeob Kang, Haebom Lee, Sungho Suh

TL;DR

This work proposes a novel, non-destructive approach for early fault detection and accurate diagnosis of interconnect defects, with improved noise resilience, and introduces a novel severity rating ensemble learning (SREL) approach, which enhances diagnostic accuracy and robustness in noisy environments.

Abstract

Fault detection and diagnosis of the interconnects are crucial for prognostics and health management (PHM) of electronics. Traditional methods, which rely on electronic signals as prognostic factors, often struggle to accurately identify the root causes of defects without resorting to destructive testing. Furthermore, these methods are vulnerable to noise interference, which can result in false alarms. To address these limitations, in this paper, we propose a novel, non-destructive approach for early fault detection and accurate diagnosis of interconnect defects, with improved noise resilience. Our approach uniquely utilizes the signal patterns of the reflection coefficient across a range of frequencies, enabling both root cause identification and severity assessment. This approach departs from conventional time-series analysis and effectively transforms the signal data into a format suitable for advanced learning algorithms. Additionally, we introduce a novel severity rating ensemble learning (SREL) approach, which enhances diagnostic accuracy and robustness in noisy environments. Experimental results demonstrate that the proposed method is effective for fault detection and diagnosis and has the potential to extend to real-world industrial applications.

Non-destructive Fault Diagnosis of Electronic Interconnects by Learning Signal Patterns of Reflection Coefficient in the Frequency Domain

TL;DR

This work proposes a novel, non-destructive approach for early fault detection and accurate diagnosis of interconnect defects, with improved noise resilience, and introduces a novel severity rating ensemble learning (SREL) approach, which enhances diagnostic accuracy and robustness in noisy environments.

Abstract

Fault detection and diagnosis of the interconnects are crucial for prognostics and health management (PHM) of electronics. Traditional methods, which rely on electronic signals as prognostic factors, often struggle to accurately identify the root causes of defects without resorting to destructive testing. Furthermore, these methods are vulnerable to noise interference, which can result in false alarms. To address these limitations, in this paper, we propose a novel, non-destructive approach for early fault detection and accurate diagnosis of interconnect defects, with improved noise resilience. Our approach uniquely utilizes the signal patterns of the reflection coefficient across a range of frequencies, enabling both root cause identification and severity assessment. This approach departs from conventional time-series analysis and effectively transforms the signal data into a format suitable for advanced learning algorithms. Additionally, we introduce a novel severity rating ensemble learning (SREL) approach, which enhances diagnostic accuracy and robustness in noisy environments. Experimental results demonstrate that the proposed method is effective for fault detection and diagnosis and has the potential to extend to real-world industrial applications.
Paper Structure (20 sections, 4 equations, 14 figures, 3 tables)

This paper contains 20 sections, 4 equations, 14 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Proposed Method
  4. Acquisition of Reflection Coefficient Signal Patterns
  5. Severity Rating Ensemble Learning (SREL) Approach for Fault Diagnosis of Electronic Interconnects
  6. Experimental Design
  7. Test Vehicles and Measurements
  8. Fabrication of test vehicles
  9. Inducing and evaluating defects
  10. Electronic signal measurements: DC resistance, TDR, S-parameters, and reflection coefficient patterns
  11. Comparison Models
  12. Data Description and Implementation Details
  13. Experimental Results and Discussion
  14. Measurement Results: DC resistances, TDR, S-parameters at a Designated Frequency and Signal Patterns of Reflection Coefficient
  15. Visualization of Reflection Coefficient Patterns by t-SNE method
  16. ...and 5 more sections

Figures (14)

  • Figure 1: Comparison between our work and previous studies for fault detection and diagnosis of electronic packages using electrical signals
  • Figure 2: IC packaging and electronic interconnects (Cu interconnects) placed inside the package
  • Figure 3: Schematic of the reflection coefficient measurement
  • Figure 4: Structure of the proposed SREL approach for fault diagnosis utilizing signal patterns of interconnects
  • Figure 5: Working principle of the SREL approach used in our study to distinguish mechanical and corrosion defects with various severity levels
  • ...and 9 more figures