Defect patterns study of pick-and-place machine using automated optical inspection data

Purpose This paper aims to study the component pick-and-place (P&P) defect patterns for different root causes based on automated optical inspection data and develop a root cause identification model using machine learning. Design/methodology/approach This study conducts experiments to simulate the P&P machine errors including nozzle size and nozzle pick-up position. The component placement qualities with different errors are inspected. This study uses various machine learning methods to develop a root cause identification model based on the inspection result. Findings The experimental results revealed that the wrong nozzle size could increase the mean and the standard deviation of component placement offset and the probability of component drop during the transfer process. Moreover, nozzle pick-up position can affect the rotated component placement offset. These root causes of defects can be traced back using machine learning methods. Practical implications This study provides operators in surface mount technology assembly lines to understand the P&P machine error symptoms. The developed model can trace back the root causes of defects automatically in real line production. Originality/value The findings are expected to lead the regular preventive maintenance to data-driven predictive and reactive maintenance.

The Dissimilar Self-Alignment Characteristics of Smaller Passive Components in the Length and Width Directions

Motivation: As passive components’ size gets smaller, quality rejects due to overhang and misalignment after the reflow appear more frequently. This situation is partly because the pass-fail criterion is set based on the offset concerning the component dimensions. Therefore, understanding the self-alignment characteristics of electronic components becomes very critical for surface-mount assembly yield. This research investigates the dissimilarity of self-alignment in the length and width directions. Approach: To avoid the argument of sample to sample variations, data are collected from 81 printed circuit boards (PCB) and 182,250 assembled components. Within a PCB, 25 different solder paste printing offset locations and 81 component placement offset settings are implemented. Component-placement positions before and after the reflow are monitored. The results are compared to identify different component sizes’ self-alignment characteristics in the length and width directions. Key findings: The misalignment of smaller passive components, e.g., R0402M(0.40 mm × 0.20 mm), is worse than the larger component under the identical solder paste printing and component placement conditions. Furthermore, the self-alignment characteristic in the length direction of these passive components, e.g., R0402M, to R1005M (1.00 mm × 0.50 mm) is superior to that of width direction. The observations are not consistent with the results found in earlier research that reported on larger components, e.g., C0402M(0.40 mm × 0.20 mm), to C3216M(3.20 mm × 1.50 mm).