Verifying the Efficiency of AI-based Inspection in Detecting Oxidation in Soldering Leads of Electronic Components during Assembly: A Case Study
The efficiency of AI-based Inspection-
Verifying the Efficiency of AI-based Inspection in Detecting Oxidation in Soldering Leads of Electronic Components during Assembly: A Case Study
Abstract
The efficiency of AI-based Inspection:
Corrosion on electronic component leads during assembly can lead to the failure of electronic devices. The leads of electronic components are susceptible to corrosion when exposed to moisture during and before the assembly process. This corrosion can cause physical damage to the leads, resulting in poor electrical contact and possible failure of the electronic component. In this paper, we present a case study where an automotive production line utilized Cybord’s AIbased inspection system to detect and prevent contamination in the soldering leads of electronic components. The system interfaced with the vision system of pick-and-place machines in real-time and collected bottom-side images of all components placed on printed circuit boards (PCBs).
The AI algorithm
based on a 3 billion component database, detected evidence of corrosion, mold, and other contaminants on each component and allowed the removal of poor-quality components from production. The reel was disqualified and sent to a lab for SEMEDX analysis, which confirmed the findings of the AI algorithm, that the issue was evidence of oxidation contamination. The results of this case study demonstrate the effectiveness of using AI-based inspection in detecting and preventing contamination in electronic assembly, boosting the overall quality and reliability of the final product
INTRODUCTION
CORROSION and corrosive contamination on electronic component leads during assembly is a major issue that can result in the failure of electronic devices[1], [2]. The leads of electronic components are typically made of metal and are susceptible to corrosion when exposed to moisture and other corrosive agents during and before the assembly process [3]–[6]. This corrosion can cause physical damage to the leads, resulting in poor electrical contact and possible failure of the electronic component. Additionally, corrosion can also cause electrical failures, resulting in poor performance or complete system failure[7].
Efficiency of AI-based Inspection
Understanding the causes and mechanisms of corrosion on electronic component leads [8]–[10]during assembly is crucial for preventing it from happening in the first place and for mitigating its effects. This can be achieved by using the appropriate materials, inspection. assembly processes Images of chip resistors 1K .5% 0402 -55/125 63MW with detected contamination on the soldering leads (A), vs uncontaminated soldering leads (B) .The presented system [12] addresses this issue by interfacing with the vision system of pick-and-place machines in real time and collecting bottom-side images of all components placed on printed circuit boards (see an example in Fig. 1) [13], [14].
AI algorithm
An AI algorithm, based on a 3 billion component database, detects evidence of corrosion, mold, and other contaminants on each component and allows the removal of poor-quality components from production [14], [15]. Disqualifying an entire reel or indicating the location of the defective component for automatic or manual replacement can accomplish this.
I. CASE STUDY
In this work, we present a case study where an automotive production line utilized the proposed system to flag a reel as suspicious due to evidence of oxidation [16] on terminals that did not comply with IPC standards [1]. Fig. 1 illustrates an example of a chip resistor with contaminated leads, as well as a comparison example of components without contamination, both taken from the same reel. Based on the system’s recommendation, the reel was disqualified and torn down. Fig. 2 illustrates the system’s detection and recommendation methodology, highlighting the process of identifying contamination and the subsequent actions taken to address it.
The reel
Afterward, the lab received the reel for SEM-EDX analysis, which confirmed the findings and identified the contamination as oxidation. The uniformity of the level of contamination on the reel was not consistent, similar to what was presented on the homogeneity of apparent age in reels [12]. The system identified and flagged the most severe cases of contamination, and upon surpassing the acceptable defects-per-million (DPM) rate, it disqualified the reel from further use in the assembly process.
Efficiency of AI-based Inspection
This non-uniform distribution of contamination can have significant implications for the performance and reliability of the electronic components, as some areas of the reel may be more affected than others [17]The DPM rate is a widely utilized metric for evaluating the quality of electronic components and assemblies. It offers a quantitative measure, indicating the number of defective components per million components.
Efficiency of AI-based
The acceptable DPM rate varies depending on the application and industry standards. However, there is a general consensus that a lower DPM rate is desirable as it signifies a higher level of quality and reliability. The DPM rate exceeded the acceptable level, indicating the reel’s unsuitability for the assembly process and necessitating disqualification. Monitoring and controlling contamination levels throughout the reel during assembly are crucial for ensuring electronic component and assembly quality and reliability.
Efficiency of AI-based Inspection
This can be achieved through the use of advanced inspection and monitoring techniques, such as those employed by the presented system [12], [14], [16], as well as by implementing appropriate materials, assembly processes, and storage conditions to minimize the risk of contamination. The laboratory received the reel with all the unused components from the production process. They determined the severe defect rate to be 1740 DPM, which represents only 0.17% of the total components on the reel.
contamination
Traditional sampling methods are unable to effectively detect this level of contamination since it falls below the threshold of detection. To circumvent this limitation, the laboratory selected random cases of mild contamination to analyze the composition of the contamination. Even with a low contamination level, it remains significant enough to impact the performance of electronic components and potentially lead to system failure. This highlights the importance of implementing advanced inspection and monitoring techniques, such as those used by the presented system, to detect and prevent contamination at early stages.
Efficiency of AI-based Inspection
Figure 3 presented microscope images that visually depicted the contamination found on the reel, providing an additional complement to the analysis. These images can aid in the identification of the specific contaminants present and help to inform the development of appropriate mitigation strategies. The collected samples from the reel underwent analysis using Scanning Electron Microscopy with Energy Dispersive X-ray Spectroscopy (SEM-EDX). This analysis aimed to determine the composition of the contamination.SEM-EDX [18] is a powerful analytical technique that allows for the identification of elemental composition of a sample at a high resolution.The technique was chosen because it can analyze samples in their natural state without the need for sample preparation. Additionally, it can detect a wide range of elements.