In Case You Missed It
Defect Detection
“Multidimensional Computed Measurement for Highly Accurate PCBA Defect Detection”
Authors: Zefang Chen, et. al.
Abstract: Accurate defect detection in industrial automated optical inspection (AOI) directly affects product quality and production efficiency. Although numerous techniques have been developed for industrial defect detection, most of them rely on single-texture image data. This dependence limits the accuracy and robustness of the defect detection due to inadequate optical source information. To overcome the problem of low accuracy owing to the lack of 3-D topographic information, a multidimensional information fusion (MIF) module is proposed that fuses texture image and depth image features. The MIF module includes tailored mechanisms to fully extract complementary semantic information from space and channel dimensions. A hierarchical fusion strategy further improves feature integration by enabling higher-layer feature fusion via lower-layer transformer blocks and efficiently removing redundant features. Afterward, feature extraction is performed on the fused feature map, and output is obtained. To enhance the detection accuracy, the position information mask (PIM) module is introduced for post-processing. The PIM module uses surface mount devices (SMDs) position data from Gerber files to create a position information mask. The mask helps filter out defects that are often misidentified owing to missing design information. The results of the comparative experiments demonstrate that the average accuracy of the authors’ method on the printed circuit board assembly (PCBA) defect dataset is 99.93%, which is 5.64% higher than that of conventional YOLOV5. Further, a comprehensive ablation study is conducted to elucidate the contribution of the proposed MIF and PIM modules. It demonstrated that the present model serves as a valuable reference for PCBA surface defect detection. (Optics Express, February 2025, https://doi.org/10.1364/OE.551868)
Design Reconstruction
“Automated 3-D Semantic Segmentation of PCB X-ray CT Images and Netlist Extraction”
Authors: Adrian Phoulady, et. al.
Abstract: Printed circuit board (PCB) design reconstruction is essential for addressing part obsolescence, intellectual property recovery, compliance, quality assurance, and enhancing national capabilities. Traditional methods for PCB design extraction, both non-geometry-based and geometry-based, have limitations in accuracy, efficiency, and scalability. This work presents an automated approach, combining image processing and machine learning, to achieve 3-D semantic segmentation of PCB x-ray computed tomography (x-ray CT) images and subsequent netlist extraction. By employing a 3-D U-Net architecture with a ResNet-18 backbone and training on synthetic data, the authors introduce a first-of-its-kind method for direct 3-D semantic segmentation, significantly improving previous efforts. The authors’ approach eliminates the need for extensive labeled datasets by using inherently labeled synthetic data. Further, this method enhances the ease of segmentation by significantly reducing or eliminating the preprocessing effort required for 2-D image stacks. It also improves universality by expanding the scope of application beyond images with specific 2-D stack criteria, segmenting the 3-D image in its entirety. Additionally, this method enables the processing of images of PCBs that have undergone bending, which is common among PCBs with a thickness below a certain threshold. The implications of this approach extend beyond PCBs, finding applications in various physical and biological sciences where 3-D image segmentation is crucial. This methodology includes high-resolution 3-D imaging, watershed segmentation, machine learning-based semantic segmentation and netlist extraction. Validation with both synthetic and real-world PCB datasets shows high accuracy and robustness, offering a scalable solution for PCB design reconstruction. (Scientific Reports, Jan. 17, 2025, https://doi.org/10.1038/s41598-024-84635-2)
Electrochemical Migration
“Nanoscale Monitoring of the Initial Stage of Water Condensation on a Printed Circuit Board”
Authors: Alekszej Romanenko, et. al.
Abstract: Electrochemical migration is a critical factor contributing to failures in electronics due to humidity. When moisture accumulates on conductor-dielectric-conductor systems under bias voltage, electrochemical processes can be triggered, leading to the growth of metallic dendrites that may ultimately result in system failure. Despite its significance, many aspects of electrochemical migration remain unresolved, particularly regarding the physical characteristics of liquid buildup that facilitate dendrite growth and short circuit currents. While a few techniques can measure water adsorption on the nanoscale, most conventional methods focus on water droplets within the size range of visible light wavelengths. In this study, the authors implemented a combined electrical-optical-ellipsometric measurement on FR-4 printed circuit boards featuring Sn surface finishes. The authors’ experimental setup allowed measurement of water condensation across a range of thicknesses, while simultaneously monitoring solder mask and metal electrodes during cooling. The ambient temperature of 25°C and relative humidity of 60% were constant during measurement. By employing this approach, the authors elucidated the mechanisms of dendrite formation and short circuit currents, demonstrating that the water film remains continuous between droplets on the solder mask surface. Compared to Sn, the nucleation was delayed on the solder mask with a larger surface coverage at smaller thicknesses. This comprehensive methodology provides crucial insights into the electrochemical migration process, enhancing understanding of the underlying phenomena that contribute to electronic failures due to humidity. The authors’ work highlighted the complementary nature of ellipsometry and optical imaging. (Heliyon, Jan. 30, 2025, https://doi.org/10.1016/j.heliyon.2025.e42117)
Printed Electronics
“Inkjet-Printed Electronics for Rapid and Low-Cost Prototyping of Digital Microfluidic Devices Using an Off-the-Shelf Printer”
Authors: Babak Kamali Doust Azad, et. al.
Abstract: Digital microfluidics (DMF) is revolutionizing point-of-care diagnostics by advancing lab-on-a-chip technology. To accelerate translation to real-life applications, it is crucial to devise rapid and low-cost methods for prototyping to test various design ideas. Here, the authors present one such method using an unmodified desktop inkjet printer and inexpensive materials. Inkjet printing eliminates the need for costly printed circuit board technology or fabrication facilities, significantly lowering the barriers to entry for researchers in the field of DMF technology. Here, an inkjet printer is characterized to print conductive tracks of Ag-ink on polyethylene terephthalate (PET) and glass slide substrates, delivering a maximum surface conductance of 7.69Ω-1/cm2. Functional DMF chips are fabricated using tape, parafilm, and SU8 as dielectric and silicone oil as the hydrophobic layers, enabling actuation voltages as low as 144 VDC and 92 VAC@100kHz for a whole-blood droplet. The authors detail their actuation and control circuitry, designed entirely with standard electronic modules and components. To showcase their approach, the authors fabricated a DMF micromixer and assessed its performance using image processing, proving the quality of the mixing. Leveraging affordable inkjet printing, the authors’ approach paves the way for highly accessible research and development in DMF-based point-of-care diagnostics. (Scientific Reports, Feb. 7, 2025, https://doi.org/10.1038/s41598-025-89343-z)
